feat: Confusion Protocol, Hermes + GBrain hosts, brain-first resolver (v0.18.0.0) (#1005)

* feat: add Confusion Protocol to preamble resolver Injects a high-stakes ambiguity gate at preamble tier >= 2 so all workflow skills get it. Fires when Claude encounters architectural decisions, data model changes, destructive operations, or contradictory requirements. Does NOT fire on routine coding. Addresses Karpathy failure mode #1 (wrong assumptions) with an inline STOP gate instead of relying on workflow skill invocation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add Hermes and GBrain host configs Hermes: tool rewrites for terminal/read_file/patch/delegate_task, paths to ~/.hermes/skills/gstack, AGENTS.md config file. GBrain: coding skills become brain-aware when GBrain mod is installed. Same tool rewrites as OpenClaw (agents spawn Claude Code via ACP). GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS NOT suppressed on gbrain host, enabling brain-first lookup and save-to-brain behavior. Both registered in hosts/index.ts with setup script redirect messages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: GBrain resolver — brain-first lookup and save-to-brain New scripts/resolvers/gbrain.ts with two resolver functions: - GBRAIN_CONTEXT_LOAD: search brain for context before skill starts - GBRAIN_SAVE_RESULTS: save skill output to brain after completion Placeholders added to 4 thinking skill templates (office-hours, investigate, plan-ceo-review, retro). Resolves to empty string on all hosts except gbrain via suppressedResolvers. GBRAIN suppression added to all 9 non-gbrain host configs. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: wire slop:diff into /review as advisory diagnostic Adds Step 3.5 to the review template: runs bun run slop:diff against the base branch to catch AI code quality issues (empty catches, redundant return await, overcomplicated abstractions). Advisory only, never blocking. Skips silently if slop-scan is not installed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: add Karpathy compatibility note to README Positions gstack as the workflow enforcement layer for Karpathy-style CLAUDE.md rules (17K stars). Links to forrestchang/andrej-karpathy-skills. Maps each Karpathy failure mode to the gstack skill that addresses it. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: improve native OpenClaw thinking skills office-hours: add design doc path visibility message after writing ceo-review: add HARD GATE reminder at review section transitions retro: add non-git context support (check memory for meeting notes) Mirrors template improvements to hand-crafted native skills. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: update tests and golden fixtures for new hosts - Host count: 8 → 10 (hermes, gbrain) - OpenClaw adapter test: expects undefined (dead code removed) - Golden ship fixtures: updated with Confusion Protocol + vendoring Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: regenerate all SKILL.md files Regenerated from templates after Confusion Protocol, GBrain resolver placeholders, slop:diff in review, HARD GATE reminders, investigation learnings, design doc visibility, and retro non-git context changes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: update project documentation for v0.18.0.0 - CHANGELOG: add v0.18.0.0 entry (Confusion Protocol, Hermes, GBrain, slop in review, Karpathy note, skill improvements) - CLAUDE.md: add hermes.ts and gbrain.ts to hosts listing - README.md: update agent count 8→10, add Hermes + GBrain to table - VERSION: bump to 0.18.0.0 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: sync package.json version to 0.18.0.0 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: extract Step 0 from review SKILL.md in E2E test The review-base-branch E2E test was copying the full 1493-line review/SKILL.md into the test fixture. The agent spent 8+ turns reading it in chunks, leaving only 7 turns for actual work, causing error_max_turns on every attempt. Now extracts only Step 0 (base branch detection, ~50 lines) which is all the test actually needs. Follows the CLAUDE.md rule: "NEVER copy a full SKILL.md file into an E2E test fixture." Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: update GBrain and Hermes host configs for v0.10.0 integration GBrain: add 'triggers' to keepFields so generated skills pass checkResolvable() validation. Add version compat comment. Hermes: un-suppress GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS. The resolvers handle GBrain-not-installed gracefully, so Hermes agents with GBrain as a mod get brain features automatically. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: GBrain resolver DX improvements and preamble health check Resolver changes: - gbrain query → gbrain search (fast keyword search, not expensive hybrid) - Add keyword extraction guidance for agents - Show explicit gbrain put_page syntax with --title, --tags, heredoc - Add entity enrichment with false-positive filter - Name throttle error patterns (exit code 1, stderr keywords) - Add data-research routing for investigate skill - Expand skillSaveMap from 4 to 8 entries - Add brain operation telemetry summary Preamble changes: - Add gbrain doctor --fast --json health check for gbrain/hermes hosts - Parse check failures/warnings count - Show failing check details when score < 50 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: preserve keepFields in allowlist frontmatter mode The allowlist mode hard-coded name + description reconstruction but never iterated keepFields for additional fields. Adding 'triggers' to keepFields was a no-op because the field was silently stripped. Now iterates keepFields and preserves any field beyond name/description from the source template frontmatter, including YAML arrays. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat: add triggers to all 38 skill templates Multi-word, skill-specific trigger keywords for GBrain's RESOLVER.md router. Each skill gets 3-6 triggers derived from its "Use when asked to..." description text. Avoids single generic words that would collide across skills (e.g., "debug this" not "debug"). These are distinct from voice-triggers (speech-to-text aliases) and serve GBrain's checkResolvable() validation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: regenerate all SKILL.md files and update golden fixtures Regenerated from updated templates (triggers, brain placeholders, resolver DX improvements, preamble health check). Golden fixtures updated to match. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: settings-hook remove exits 1 when nothing to remove gstack-settings-hook remove was exiting 0 when settings.json didn't exist, causing gstack-uninstall to report "SessionStart hook" as removed on clean systems where nothing was installed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: update project documentation for GBrain v0.10.0 integration ARCHITECTURE.md: added GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS to resolver table. CHANGELOG.md: expanded v0.18.0.0 entry with GBrain v0.10.0 integration details (triggers, expanded brain-awareness, DX improvements, Hermes brain support), updated date. CLAUDE.md: added gbrain to resolvers/ directory comment. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: routing E2E stops writing to user's ~/.claude/skills/ installSkills() was copying SKILL.md files to both project-level (.claude/skills/ in tmpDir) and user-level (~/.claude/skills/). Writing to the user's real install fails when symlinks point to different worktrees or dangling targets (ENOENT on copyFileSync). Now installs to project-level only. The test already sets cwd to the tmpDir, so project-level discovery works. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: scale Gemini E2E back to smoke test Gemini CLI gets lost in worktrees on complex tasks (review times out at 600s, discover-skill hits exit 124). Nobody uses Gemini for gstack skill execution. Replace the two failing tests (gemini-discover-skill and gemini-review-findings) with a single smoke test that verifies Gemini can start and read the README. 90s timeout, no skill invocation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-01 19:25:10 +02:00 · 2026-04-16 10:41:38 -07:00
parent 2300067267
commit b805aa0113
111 changed files with 1504 additions and 112 deletions
@@ -13,6 +13,8 @@ bin/gstack-global-discover
 .slate/
 .cursor/
 .openclaw/
+.hermes/
+.gbrain/
 .context/
 extension/.auth.json
 .gstack-worktrees/
@@ -209,6 +209,8 @@ Templates contain the workflows, tips, and examples that require human judgment.
 | `{{DESIGN_SETUP}}` | `resolvers/design.ts` | Discovery pattern for `$D` design binary, mirrors `{{BROWSE_SETUP}}` |
 | `{{DESIGN_SHOTGUN_LOOP}}` | `resolvers/design.ts` | Shared comparison board feedback loop for /design-shotgun, /plan-design-review, /design-consultation |
 | `{{UX_PRINCIPLES}}` | `resolvers/design.ts` | User behavioral foundations (scanning, satisficing, goodwill reservoir, trunk test) for /design-html, /design-shotgun, /design-review, /plan-design-review |
+| `{{GBRAIN_CONTEXT_LOAD}}` | `resolvers/gbrain.ts` | Brain-first context search with keyword extraction, health awareness, and data-research routing. Injected into 10 brain-aware skills. Suppressed on non-brain hosts. |
+| `{{GBRAIN_SAVE_RESULTS}}` | `resolvers/gbrain.ts` | Post-skill brain persistence with entity enrichment, throttle handling, and per-skill save instructions. 8 skill-specific save formats. |

 This is structurally sound — if a command exists in code, it appears in docs. If it doesn't exist, it can't appear.

@@ -1,5 +1,25 @@
 # Changelog

+## [0.18.0.0] - 2026-04-15
+
+### Added
+- **Confusion Protocol.** Every workflow skill now has an inline ambiguity gate. When Claude hits a decision that could go two ways (which architecture? which data model? destructive operation with unclear scope?), it stops and asks instead of guessing. Scoped to high-stakes decisions only, so it doesn't slow down routine coding. Addresses Karpathy's #1 AI coding failure mode.
+- **Hermes host support.** gstack now generates skill docs for [Hermes Agent](https://github.com/nousresearch/hermes-agent) with proper tool rewrites (`terminal`, `read_file`, `patch`, `delegate_task`). `./setup --host hermes` prints integration instructions.
+- **GBrain host + brain-first resolver.** GBrain is a "mod" for gstack. When installed, your coding skills become brain-aware: they search your brain for relevant context before starting and save results to your brain after finishing. 10 skills are now brain-aware: /office-hours, /investigate, /plan-ceo-review, /retro, /ship, /qa, /design-review, /plan-eng-review, /cso, and /design-consultation. Compatible with GBrain >= v0.10.0.
+- **GBrain v0.10.0 integration.** Agent instructions now use `gbrain search` (fast keyword lookup) instead of `gbrain query` (expensive hybrid). Every command shows full CLI syntax with `--title`, `--tags`, and heredoc examples. Keyword extraction guidance helps agents search effectively. Entity enrichment auto-creates stub pages for people and companies mentioned in skill output. Throttle errors are named so agents can detect and handle them. A preamble health check runs `gbrain doctor --fast --json` at session start and names failing checks when the brain is degraded.
+- **Skill triggers for GBrain router.** All 38 skill templates now include `triggers:` arrays in their frontmatter, multi-word keywords like "debug this", "ship it", "brainstorm this". These power GBrain's RESOLVER.md skill router and pass `checkResolvable()` validation. Distinct from `voice-triggers:` (speech-to-text aliases).
+- **Hermes brain support.** Hermes agents with GBrain installed as a mod now get brain features automatically. The resolver fallback logic ("if GBrain is not available, proceed without") handles non-GBrain Hermes installs gracefully.
+- **slop:diff in /review.** Every code review now runs `bun run slop:diff` as an advisory diagnostic, catching AI code quality issues (empty catches, redundant abstractions, overcomplicated patterns) before they land. Informational only, never blocking.
+- **Karpathy compatibility.** README now positions gstack as the workflow enforcement layer for [Karpathy-style CLAUDE.md rules](https://github.com/forrestchang/andrej-karpathy-skills) (17K stars). Maps each failure mode to the gstack skill that addresses it.
+
+### Changed
+- **CEO review HARD GATE reinforcement.** "Do NOT make any code changes. Review only." now repeats at every STOP point (12 locations), not just the top. Prompt repetition measurably reduces the "starts implementing" failure mode.
+- **Office-hours design doc visibility.** After writing the design doc, the skill now prints the full path so downstream skills (/plan-ceo-review, /plan-eng-review) can find it.
+- **Investigate investigation history.** Each investigation now logs to the learnings system with `type: "investigation"` and affected file paths. Future investigations on the same files surface prior root causes automatically. Recurring bugs in the same area = architectural smell.
+- **Retro non-git context.** If `~/.gstack/retro-context.md` exists, the retro now reads it for meeting notes, calendar events, and decisions that don't appear in git history.
+- **Native OpenClaw skills improved.** The 4 hand-crafted ClawHub skills (office-hours, ceo-review, investigate, retro) now mirror the template improvements above.
+- **Host count: 8 to 10.** Hermes and GBrain join Claude, Codex, Factory, Kiro, OpenCode, Slate, Cursor, and OpenClaw.
+
 ## [0.17.0.0] - 2026-04-14

 ### Added
@@ -68,14 +68,15 @@ gstack/
 ├── hosts/           # Typed host configs (one per AI agent)
 │   ├── claude.ts    # Primary host config
 │   ├── codex.ts, factory.ts, kiro.ts  # Existing hosts
-│   ├── opencode.ts, slate.ts, cursor.ts, openclaw.ts  # New hosts
+│   ├── opencode.ts, slate.ts, cursor.ts, openclaw.ts  # IDE hosts
+│   ├── hermes.ts, gbrain.ts  # Agent runtime hosts
 │   └── index.ts     # Registry: exports all, derives Host type
 ├── scripts/         # Build + DX tooling
 │   ├── gen-skill-docs.ts  # Template → SKILL.md generator (config-driven)
 │   ├── host-config.ts     # HostConfig interface + validator
 │   ├── host-config-export.ts  # Shell bridge for setup script
 │   ├── host-adapters/     # Host-specific adapters (OpenClaw tool mapping)
-│   ├── resolvers/   # Template resolver modules (preamble, design, review, etc.)
+│   ├── resolvers/   # Template resolver modules (preamble, design, review, gbrain, etc.)
 │   ├── skill-check.ts     # Health dashboard
 │   └── dev-skill.ts       # Watch mode
 ├── test/            # Skill validation + eval tests
@@ -110,7 +110,7 @@ These are conversational skills. Your OpenClaw agent runs them directly via chat

 ### Other AI Agents

-gstack works on 8 AI coding agents, not just Claude. Setup auto-detects which
+gstack works on 10 AI coding agents, not just Claude. Setup auto-detects which
 agents you have installed:

 ```bash
@@ -128,6 +128,8 @@ Or target a specific agent with `./setup --host <name>`:
 | Factory Droid | `--host factory` | `~/.factory/skills/gstack-*/` |
 | Slate | `--host slate` | `~/.slate/skills/gstack-*/` |
 | Kiro | `--host kiro` | `~/.kiro/skills/gstack-*/` |
+| Hermes | `--host hermes` | `~/.hermes/skills/gstack-*/` |
+| GBrain (mod) | `--host gbrain` | `~/.gbrain/skills/gstack-*/` |

 **Want to add support for another agent?** See [docs/ADDING_A_HOST.md](docs/ADDING_A_HOST.md).
 It's one TypeScript config file, zero code changes.
@@ -236,6 +238,10 @@ Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-

 **[Deep dives with examples and philosophy for every skill →](docs/skills.md)**

+### Karpathy's four failure modes? Already covered.
+
+Andrej Karpathy's [AI coding rules](https://github.com/forrestchang/andrej-karpathy-skills) (17K stars) nail four failure modes: wrong assumptions, overcomplexity, orthogonal edits, imperative over declarative. gstack's workflow skills enforce all four. `/office-hours` forces assumptions into the open before code is written. The Confusion Protocol stops Claude from guessing on architectural decisions. `/review` catches unnecessary complexity and drive-by edits. `/ship` transforms tasks into verifiable goals with test-first execution. If you already use Karpathy-style CLAUDE.md rules, gstack is the workflow enforcement layer that makes them stick across entire sprints, not just single prompts.
+
 ## Parallel sprints

 gstack works well with one sprint. It gets interesting with ten running at once.
@@ -11,6 +11,11 @@ allowed-tools:
  - Bash
  - Read
  - AskUserQuestion
+triggers:
+  - browse this page
+  - take a screenshot
+  - navigate to url
+  - inspect the page

 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
@@ -255,6 +260,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 **Tone:** direct, concrete, sharp, never corporate, never academic. Sound like a builder, not a consultant. Name the file, the function, the command. No filler, no throat-clearing.
@@ -11,6 +11,11 @@ allowed-tools:
  - Bash
  - Read
  - AskUserQuestion
+triggers:
+  - browse this page
+  - take a screenshot
+  - navigate to url
+  - inspect the page

 ---

@@ -1 +1 @@
-0.17.0.0
+0.18.0.0
@@ -13,6 +13,10 @@ description: |
  gauntlet without answering 15-30 intermediate questions. (gstack)
  Voice triggers (speech-to-text aliases): "auto plan", "automatic review".
 benefits-from: [office-hours]
+triggers:
+  - run all reviews
+  - automatic review pipeline
+  - auto plan review
 allowed-tools:
  - Bash
  - Read
@@ -265,6 +269,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -383,6 +389,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -15,6 +15,10 @@ voice-triggers:
  - "auto plan"
  - "automatic review"
 benefits-from: [office-hours]
+triggers:
+  - run all reviews
+  - automatic review pipeline
+  - auto plan review
 allowed-tools:
  - Bash
  - Read
@@ -9,6 +9,10 @@ description: |
  Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals",
  "bundle size", "load time". (gstack)
  Voice triggers (speech-to-text aliases): "speed test", "check performance".
+triggers:
+  - performance benchmark
+  - check page speed
+  - detect performance regression
 allowed-tools:
  - Bash
  - Read
@@ -258,6 +262,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 **Tone:** direct, concrete, sharp, never corporate, never academic. Sound like a builder, not a consultant. Name the file, the function, the command. No filler, no throat-clearing.
@@ -11,6 +11,10 @@ description: |
 voice-triggers:
  - "speed test"
  - "check performance"
+triggers:
+  - performance benchmark
+  - check page speed
+  - detect performance regression
 allowed-tools:
  - Bash
  - Read
@@ -54,7 +54,7 @@ case "$ACTION" in
    " 2>/dev/null
    ;;
  remove)
-    [ -f "$SETTINGS_FILE" ] || exit 0
+    [ -f "$SETTINGS_FILE" ] || exit 1
    GSTACK_SETTINGS_PATH="$SETTINGS_FILE" bun -e "
      const fs = require('fs');
      const settingsPath = process.env.GSTACK_SETTINGS_PATH;
@@ -9,6 +9,10 @@ description: |
  ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
  user flow, or file a bug with evidence. Use when asked to "open in browser", "test the
  site", "take a screenshot", or "dogfood this". (gstack)
+triggers:
+  - browse a page
+  - headless browser
+  - take page screenshot
 allowed-tools:
  - Bash
  - Read
@@ -257,6 +261,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 **Tone:** direct, concrete, sharp, never corporate, never academic. Sound like a builder, not a consultant. Name the file, the function, the command. No filler, no throat-clearing.
@@ -9,6 +9,10 @@ description: |
  ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a
  user flow, or file a bug with evidence. Use when asked to "open in browser", "test the
  site", "take a screenshot", or "dogfood this". (gstack)
+triggers:
+  - browse a page
+  - headless browser
+  - take page screenshot
 allowed-tools:
  - Bash
  - Read
@@ -14,6 +14,10 @@ allowed-tools:
  - Write
  - Glob
  - AskUserQuestion
+triggers:
+  - monitor after deploy
+  - canary check
+  - watch for errors post-deploy
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -257,6 +261,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -375,6 +381,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -14,6 +14,10 @@ allowed-tools:
  - Write
  - Glob
  - AskUserQuestion
+triggers:
+  - monitor after deploy
+  - canary check
+  - watch for errors post-deploy
 ---

 {{PREAMBLE}}
@@ -7,6 +7,10 @@ description: |
  User can override each warning. Use when touching prod, debugging live systems,
  or working in a shared environment. Use when asked to "be careful", "safety mode",
  "prod mode", or "careful mode". (gstack)
+triggers:
+  - be careful
+  - warn before destructive
+  - safety mode
 allowed-tools:
  - Bash
  - Read
@@ -7,6 +7,10 @@ description: |
  User can override each warning. Use when touching prod, debugging live systems,
  or working in a shared environment. Use when asked to "be careful", "safety mode",
  "prod mode", or "careful mode". (gstack)
+triggers:
+  - be careful
+  - warn before destructive
+  - safety mode
 allowed-tools:
  - Bash
  - Read
@@ -17,6 +17,10 @@ allowed-tools:
  - Glob
  - Grep
  - AskUserQuestion
+triggers:
+  - save progress
+  - checkpoint this
+  - resume where i left off
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -260,6 +264,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -378,6 +384,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -17,6 +17,10 @@ allowed-tools:
  - Glob
  - Grep
  - AskUserQuestion
+triggers:
+  - save progress
+  - checkpoint this
+  - resume where i left off
 ---

 {{PREAMBLE}}
@@ -9,6 +9,10 @@ description: |
  The "200 IQ autistic developer" second opinion. Use when asked to "codex review",
  "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack)
  Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
+triggers:
+  - codex review
+  - second opinion
+  - outside voice challenge
 allowed-tools:
  - Bash
  - Read
@@ -259,6 +263,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -377,6 +383,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -12,6 +12,10 @@ voice-triggers:
  - "code x"
  - "code ex"
  - "get another opinion"
+triggers:
+  - codex review
+  - second opinion
+  - outside voice challenge
 allowed-tools:
  - Bash
  - Read
@@ -3,6 +3,10 @@ name: gstack-contrib-add-host
 description: |
  Contributor-only skill: create a new host config for gstack's multi-host system.
  NOT installed for end users. Only usable from the gstack source repo.
+triggers:
+  - add new host
+  - create host config
+  - contribute new agent host
 ---

 # /gstack-contrib-add-host — Add a New Host
@@ -19,6 +19,10 @@ allowed-tools:
  - Agent
  - WebSearch
  - AskUserQuestion
+triggers:
+  - security audit
+  - check for vulnerabilities
+  - owasp review
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -262,6 +266,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -380,6 +386,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -537,6 +556,8 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.

+
+
 # /cso — Chief Security Officer Audit (v2)

 You are a **Chief Security Officer** who has led incident response on real breaches and testified before boards about security posture. You think like an attacker but report like a defender. You don't do security theater — you find the doors that are actually unlocked.
@@ -1199,6 +1220,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Important Rules

 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix.
@@ -25,10 +25,16 @@ allowed-tools:
  - Agent
  - WebSearch
  - AskUserQuestion
+triggers:
+  - security audit
+  - check for vulnerabilities
+  - owasp review
 ---

 {{PREAMBLE}}

+{{GBRAIN_CONTEXT_LOAD}}
+
 # /cso — Chief Security Officer Audit (v2)

 You are a **Chief Security Officer** who has led incident response on real breaches and testified before boards about security posture. You think like an attacker but report like a defender. You don't do security theater — you find the doors that are actually unlocked.
@@ -609,6 +615,8 @@ If `.gstack/` is not in `.gitignore`, note it in findings — security reports s

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Important Rules

 - **Think like an attacker, report like a defender.** Show the exploit path, then the fix.
@@ -19,6 +19,10 @@ allowed-tools:
  - Grep
  - AskUserQuestion
  - WebSearch
+triggers:
+  - design system
+  - create a brand
+  - design from scratch
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -262,6 +266,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -380,6 +386,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -686,6 +705,8 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go

 ---

+
+
 ## Prior Learnings

 Search for relevant learnings from previous sessions:
@@ -1253,6 +1274,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Important Rules

 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust.
@@ -19,6 +19,10 @@ allowed-tools:
  - Grep
  - AskUserQuestion
  - WebSearch
+triggers:
+  - design system
+  - create a brand
+  - design from scratch
 ---

 {{PREAMBLE}}
@@ -79,6 +83,8 @@ If `DESIGN_NOT_AVAILABLE`: Phase 5 falls back to the HTML preview page (still go

 ---

+{{GBRAIN_CONTEXT_LOAD}}
+
 {{LEARNINGS_SEARCH}}

 ## Phase 1: Product Context
@@ -423,6 +429,8 @@ After shipping DESIGN.md, if the session produced screen-level mockups or page l

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Important Rules

 1. **Propose, don't present menus.** You are a consultant, not a form. Make opinionated recommendations based on the product context, then let the user adjust.
@@ -12,6 +12,10 @@ description: |
  "build me a page", "implement this design", or after any planning skill.
  Proactively suggest when user has approved a design or has a plan ready. (gstack)
  Voice triggers (speech-to-text aliases): "build the design", "code the mockup", "make it real".
+triggers:
+  - build the design
+  - code the mockup
+  - make design real
 allowed-tools:
  - Bash
  - Read
@@ -264,6 +268,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -382,6 +388,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -15,6 +15,10 @@ voice-triggers:
  - "build the design"
  - "code the mockup"
  - "make it real"
+triggers:
+  - build the design
+  - code the mockup
+  - make design real
 allowed-tools:
  - Bash
  - Read
@@ -19,6 +19,10 @@ allowed-tools:
  - Grep
  - AskUserQuestion
  - WebSearch
+triggers:
+  - visual design audit
+  - design qa
+  - fix design issues
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -262,6 +266,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -380,6 +386,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -555,6 +574,8 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.

+
+
 # /design-review: Design Audit → Fix → Verify

 You are a senior product designer AND a frontend engineer. Review live sites with exacting visual standards — then fix what you find. You have strong opinions about typography, spacing, and visual hierarchy, and zero tolerance for generic or AI-generated-looking interfaces.
@@ -1732,6 +1753,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Additional Rules (design-review specific)

 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
@@ -19,10 +19,16 @@ allowed-tools:
  - Grep
  - AskUserQuestion
  - WebSearch
+triggers:
+  - visual design audit
+  - design qa
+  - fix design issues
 ---

 {{PREAMBLE}}

+{{GBRAIN_CONTEXT_LOAD}}
+
 # /design-review: Design Audit → Fix → Verify

 You are a senior product designer AND a frontend engineer. Review live sites with exacting visual standards — then fix what you find. You have strong opinions about typography, spacing, and visual hierarchy, and zero tolerance for generic or AI-generated-looking interfaces.
@@ -293,6 +299,8 @@ If the repo has a `TODOS.md`:

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Additional Rules (design-review specific)

 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
@@ -9,6 +9,10 @@ description: |
  "visual brainstorm", or "I don't like how this looks".
  Proactively suggest when the user describes a UI feature but hasn't seen
  what it could look like. (gstack)
+triggers:
+  - explore design variants
+  - show me design options
+  - visual design brainstorm
 allowed-tools:
  - Bash
  - Read
@@ -259,6 +263,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -377,6 +383,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -9,6 +9,10 @@ description: |
  "visual brainstorm", or "I don't like how this looks".
  Proactively suggest when the user describes a UI feature but hasn't seen
  what it could look like. (gstack)
+triggers:
+  - explore design variants
+  - show me design options
+  - visual design brainstorm
 allowed-tools:
  - Bash
  - Read
@@ -11,6 +11,10 @@ description: |
  "test the DX", "DX audit", "developer experience test", or "try the
  onboarding". Proactively suggest after shipping a developer-facing feature. (gstack)
  Voice triggers (speech-to-text aliases): "dx audit", "test the developer experience", "try the onboarding", "developer experience test".
+triggers:
+  - live dx audit
+  - test developer experience
+  - measure onboarding time
 allowed-tools:
  - Read
  - Edit
@@ -262,6 +266,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -380,6 +386,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -15,6 +15,10 @@ voice-triggers:
  - "test the developer experience"
  - "try the onboarding"
  - "developer experience test"
+triggers:
+  - live dx audit
+  - test developer experience
+  - measure onboarding time
 allowed-tools:
  - Read
  - Edit
@@ -16,6 +16,10 @@ allowed-tools:
  - Grep
  - Glob
  - AskUserQuestion
+triggers:
+  - update docs after ship
+  - document what changed
+  - post-ship docs
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -259,6 +263,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -377,6 +383,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -16,6 +16,10 @@ allowed-tools:
  - Grep
  - Glob
  - AskUserQuestion
+triggers:
+  - update docs after ship
+  - document what changed
+  - post-ship docs
 ---

 {{PREAMBLE}}
@@ -7,6 +7,10 @@ description: |
  "fixing" unrelated code, or when you want to scope changes to one module.
  Use when asked to "freeze", "restrict edits", "only edit this folder",
  or "lock down edits". (gstack)
+triggers:
+  - freeze edits to directory
+  - lock editing scope
+  - restrict file changes
 allowed-tools:
  - Bash
  - Read
@@ -7,6 +7,10 @@ description: |
  "fixing" unrelated code, or when you want to scope changes to one module.
  Use when asked to "freeze", "restrict edits", "only edit this folder",
  or "lock down edits". (gstack)
+triggers:
+  - freeze edits to directory
+  - lock editing scope
+  - restrict file changes
 allowed-tools:
  - Bash
  - Read
@@ -6,6 +6,10 @@ description: |
  runs the upgrade, and shows what's new. Use when asked to "upgrade gstack",
  "update gstack", or "get latest version".
  Voice triggers (speech-to-text aliases): "upgrade the tools", "update the tools", "gee stack upgrade", "g stack upgrade".
+triggers:
+  - upgrade gstack
+  - update gstack version
+  - get latest gstack
 allowed-tools:
  - Bash
  - Read
@@ -10,6 +10,10 @@ voice-triggers:
  - "update the tools"
  - "gee stack upgrade"
  - "g stack upgrade"
+triggers:
+  - upgrade gstack
+  - update gstack version
+  - get latest gstack
 allowed-tools:
  - Bash
  - Read
@@ -7,6 +7,10 @@ description: |
  /freeze (blocks edits outside a specified directory). Use for maximum safety
  when touching prod or debugging live systems. Use when asked to "guard mode",
  "full safety", "lock it down", or "maximum safety". (gstack)
+triggers:
+  - full safety mode
+  - guard against mistakes
+  - maximum safety
 allowed-tools:
  - Bash
  - Read
@@ -7,6 +7,10 @@ description: |
  /freeze (blocks edits outside a specified directory). Use for maximum safety
  when touching prod or debugging live systems. Use when asked to "guard mode",
  "full safety", "lock it down", or "maximum safety". (gstack)
+triggers:
+  - full safety mode
+  - guard against mistakes
+  - maximum safety
 allowed-tools:
  - Bash
  - Read
@@ -8,6 +8,10 @@ description: |
  0-10 score, and tracks trends over time. Use when: "health check",
  "code quality", "how healthy is the codebase", "run all checks",
  "quality score". (gstack)
+triggers:
+  - code health check
+  - quality dashboard
+  - how healthy is codebase
 allowed-tools:
  - Bash
  - Read
@@ -259,6 +263,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -377,6 +383,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -8,6 +8,10 @@ description: |
  0-10 score, and tracks trends over time. Use when: "health check",
  "code quality", "how healthy is the codebase", "run all checks",
  "quality score". (gstack)
+triggers:
+  - code health check
+  - quality dashboard
+  - how healthy is codebase
 allowed-tools:
  - Bash
  - Read
@@ -24,7 +24,7 @@ const claude: HostConfig = {

  pathRewrites: [],  // Claude is the primary host — no rewrites needed
  toolRewrites: {},
-  suppressedResolvers: [],
+  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],

  runtimeRoot: {
    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
@@ -37,6 +37,8 @@ const codex: HostConfig = {
    'CODEX_SECOND_OPINION',   // review.ts:257 — Codex can't invoke itself
    'CODEX_PLAN_REVIEW',      // review.ts:541 — Codex can't invoke itself
    'REVIEW_ARMY',            // review-army.ts:180 — Codex shouldn't orchestrate
+    'GBRAIN_CONTEXT_LOAD',
+    'GBRAIN_SAVE_RESULTS',
  ],

  runtimeRoot: {
@@ -28,6 +28,8 @@ const cursor: HostConfig = {
    { from: '.claude/skills', to: '.cursor/skills' },
  ],

+  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
+
  runtimeRoot: {
    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
    globalFiles: {
@@ -43,6 +43,8 @@ const factory: HostConfig = {
    'use the Glob tool': 'find files matching',
  },

+  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
+
  runtimeRoot: {
    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
    globalFiles: {
@@ -0,0 +1,78 @@
+import type { HostConfig } from '../scripts/host-config';
+
+/**
+ * GBrain host config.
+ * Compatible with GBrain >= v0.10.0 (doctor --fast --json, search CLI, entity enrichment).
+ * When updating, check INSTALL_FOR_AGENTS.md in the GBrain repo for breaking changes.
+ */
+const gbrain: HostConfig = {
+  name: 'gbrain',
+  displayName: 'GBrain',
+  cliCommand: 'gbrain',
+  cliAliases: [],
+
+  globalRoot: '.gbrain/skills/gstack',
+  localSkillRoot: '.gbrain/skills/gstack',
+  hostSubdir: '.gbrain',
+  usesEnvVars: true,
+
+  frontmatter: {
+    mode: 'allowlist',
+    keepFields: ['name', 'description', 'triggers'],
+    descriptionLimit: null,
+  },
+
+  generation: {
+    generateMetadata: false,
+    skipSkills: ['codex'],
+    includeSkills: [],
+  },
+
+  pathRewrites: [
+    { from: '~/.claude/skills/gstack', to: '~/.gbrain/skills/gstack' },
+    { from: '.claude/skills/gstack', to: '.gbrain/skills/gstack' },
+    { from: '.claude/skills', to: '.gbrain/skills' },
+    { from: 'CLAUDE.md', to: 'AGENTS.md' },
+  ],
+  toolRewrites: {
+    'use the Bash tool': 'use the exec tool',
+    'use the Write tool': 'use the write tool',
+    'use the Read tool': 'use the read tool',
+    'use the Edit tool': 'use the edit tool',
+    'use the Agent tool': 'use sessions_spawn',
+    'use the Grep tool': 'search for',
+    'use the Glob tool': 'find files matching',
+    'the Bash tool': 'the exec tool',
+    'the Read tool': 'the read tool',
+    'the Write tool': 'the write tool',
+    'the Edit tool': 'the edit tool',
+  },
+
+  // GBrain gets brain-aware resolvers. All other hosts suppress these.
+  suppressedResolvers: [
+    'DESIGN_OUTSIDE_VOICES',
+    'ADVERSARIAL_STEP',
+    'CODEX_SECOND_OPINION',
+    'CODEX_PLAN_REVIEW',
+    'REVIEW_ARMY',
+    // NOTE: GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS are NOT suppressed here.
+    // GBrain is the only host that gets brain-first lookup and save-to-brain behavior.
+  ],
+
+  runtimeRoot: {
+    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
+    globalFiles: {
+      'review': ['checklist.md', 'TODOS-format.md'],
+    },
+  },
+
+  install: {
+    prefixable: false,
+    linkingStrategy: 'symlink-generated',
+  },
+
+  coAuthorTrailer: 'Co-Authored-By: GBrain Agent <agent@gbrain.dev>',
+  learningsMode: 'basic',
+};
+
+export default gbrain;
@@ -0,0 +1,73 @@
+import type { HostConfig } from '../scripts/host-config';
+
+const hermes: HostConfig = {
+  name: 'hermes',
+  displayName: 'Hermes',
+  cliCommand: 'hermes',
+  cliAliases: [],
+
+  globalRoot: '.hermes/skills/gstack',
+  localSkillRoot: '.hermes/skills/gstack',
+  hostSubdir: '.hermes',
+  usesEnvVars: true,
+
+  frontmatter: {
+    mode: 'allowlist',
+    keepFields: ['name', 'description'],
+    descriptionLimit: null,
+  },
+
+  generation: {
+    generateMetadata: false,
+    skipSkills: ['codex'],
+    includeSkills: [],
+  },
+
+  pathRewrites: [
+    { from: '~/.claude/skills/gstack', to: '~/.hermes/skills/gstack' },
+    { from: '.claude/skills/gstack', to: '.hermes/skills/gstack' },
+    { from: '.claude/skills', to: '.hermes/skills' },
+    { from: 'CLAUDE.md', to: 'AGENTS.md' },
+  ],
+  toolRewrites: {
+    'use the Bash tool': 'use the terminal tool',
+    'use the Write tool': 'use the patch tool',
+    'use the Read tool': 'use the read_file tool',
+    'use the Edit tool': 'use the patch tool',
+    'use the Agent tool': 'use delegate_task',
+    'use the Grep tool': 'search for',
+    'use the Glob tool': 'find files matching',
+    'the Bash tool': 'the terminal tool',
+    'the Read tool': 'the read_file tool',
+    'the Write tool': 'the patch tool',
+    'the Edit tool': 'the patch tool',
+  },
+
+  suppressedResolvers: [
+    'DESIGN_OUTSIDE_VOICES',
+    'ADVERSARIAL_STEP',
+    'CODEX_SECOND_OPINION',
+    'CODEX_PLAN_REVIEW',
+    'REVIEW_ARMY',
+    // GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS are NOT suppressed.
+    // The resolvers handle GBrain-not-installed gracefully ("proceed without brain context").
+    // If Hermes has GBrain as a mod, brain features activate automatically.
+  ],
+
+  runtimeRoot: {
+    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
+    globalFiles: {
+      'review': ['checklist.md', 'TODOS-format.md'],
+    },
+  },
+
+  install: {
+    prefixable: false,
+    linkingStrategy: 'symlink-generated',
+  },
+
+  coAuthorTrailer: 'Co-Authored-By: Hermes Agent <agent@nousresearch.com>',
+  learningsMode: 'basic',
+};
+
+export default hermes;
@@ -14,9 +14,11 @@ import opencode from './opencode';
 import slate from './slate';
 import cursor from './cursor';
 import openclaw from './openclaw';
+import hermes from './hermes';
+import gbrain from './gbrain';

 /** All registered host configs. Add new hosts here. */
-export const ALL_HOST_CONFIGS: HostConfig[] = [claude, codex, factory, kiro, opencode, slate, cursor, openclaw];
+export const ALL_HOST_CONFIGS: HostConfig[] = [claude, codex, factory, kiro, opencode, slate, cursor, openclaw, hermes, gbrain];

 /** Map from host name to config. */
 export const HOST_CONFIG_MAP: Record<string, HostConfig> = Object.fromEntries(
@@ -63,4 +65,4 @@ export function getExternalHosts(): HostConfig[] {
 }

 // Re-export individual configs for direct import
-export { claude, codex, factory, kiro, opencode, slate, cursor, openclaw };
+export { claude, codex, factory, kiro, opencode, slate, cursor, openclaw, hermes, gbrain };
@@ -30,6 +30,8 @@ const kiro: HostConfig = {
    { from: '.codex/skills', to: '.kiro/skills' },
  ],

+  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
+
  runtimeRoot: {
    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
    globalFiles: {
@@ -53,6 +53,8 @@ const openclaw: HostConfig = {
    'CODEX_SECOND_OPINION',
    'CODEX_PLAN_REVIEW',
    'REVIEW_ARMY',
+    'GBRAIN_CONTEXT_LOAD',
+    'GBRAIN_SAVE_RESULTS',
  ],

  runtimeRoot: {
@@ -69,8 +71,6 @@ const openclaw: HostConfig = {

  coAuthorTrailer: 'Co-Authored-By: OpenClaw Agent <agent@openclaw.ai>',
  learningsMode: 'basic',
-
-  adapter: './scripts/host-adapters/openclaw-adapter',
 };

 export default openclaw;
@@ -28,6 +28,8 @@ const opencode: HostConfig = {
    { from: '.claude/skills', to: '.opencode/skills' },
  ],

+  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
+
  runtimeRoot: {
    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
    globalFiles: {
@@ -28,6 +28,8 @@ const slate: HostConfig = {
    { from: '.claude/skills', to: '.slate/skills' },
  ],

+  suppressedResolvers: ['GBRAIN_CONTEXT_LOAD', 'GBRAIN_SAVE_RESULTS'],
+
  runtimeRoot: {
    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
    globalFiles: {
@@ -19,6 +19,12 @@ allowed-tools:
  - Glob
  - AskUserQuestion
  - WebSearch
+triggers:
+  - debug this
+  - fix this bug
+  - why is this broken
+  - root cause analysis
+  - investigate this error
 hooks:
  PreToolUse:
    - matcher: "Edit"
@@ -274,6 +280,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -392,6 +400,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -559,6 +580,8 @@ Fixing symptoms creates whack-a-mole debugging. Every fix that doesn't address r

 ---

+
+
 ## Phase 1: Root Cause Investigation

 Gather context before forming any hypothesis.
@@ -575,6 +598,8 @@ Gather context before forming any hypothesis.

 4. **Reproduce:** Can you trigger the bug deterministically? If not, gather more evidence before proceeding.

+5. **Check investigation history:** Search prior learnings for investigations on the same files. Recurring bugs in the same area are an architectural smell. If prior investigations exist, note patterns and check if the root cause was structural.
+
 ## Prior Learnings

 Search for relevant learnings from previous sessions:
@@ -736,6 +761,12 @@ Status:          DONE | DONE_WITH_CONCERNS | BLOCKED
 ════════════════════════════════════════
 ```

+Log the investigation as a learning for future sessions. Use `type: "investigation"` and include the affected files so future investigations on the same area can find this:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"investigate","type":"investigation","key":"ROOT_CAUSE_KEY","insight":"ROOT_CAUSE_SUMMARY","confidence":9,"source":"observed","files":["affected/file1.ts","affected/file2.ts"]}'
+```
+
 ## Capture Learnings

 If you discovered a non-obvious pattern, pitfall, or architectural insight during
@@ -761,6 +792,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ---

 ## Important Rules
@@ -19,6 +19,12 @@ allowed-tools:
  - Glob
  - AskUserQuestion
  - WebSearch
+triggers:
+  - debug this
+  - fix this bug
+  - why is this broken
+  - root cause analysis
+  - investigate this error
 hooks:
  PreToolUse:
    - matcher: "Edit"
@@ -45,6 +51,8 @@ Fixing symptoms creates whack-a-mole debugging. Every fix that doesn't address r

 ---

+{{GBRAIN_CONTEXT_LOAD}}
+
 ## Phase 1: Root Cause Investigation

 Gather context before forming any hypothesis.
@@ -61,6 +69,8 @@ Gather context before forming any hypothesis.

 4. **Reproduce:** Can you trigger the bug deterministically? If not, gather more evidence before proceeding.

+5. **Check investigation history:** Search prior learnings for investigations on the same files. Recurring bugs in the same area are an architectural smell. If prior investigations exist, note patterns and check if the root cause was structural.
+
 {{LEARNINGS_SEARCH}}

 Output: **"Root cause hypothesis: ..."** — a specific, testable claim about what is wrong and why.
@@ -186,8 +196,16 @@ Status:          DONE | DONE_WITH_CONCERNS | BLOCKED
 ════════════════════════════════════════
 ```

+Log the investigation as a learning for future sessions. Use `type: "investigation"` and include the affected files so future investigations on the same area can find this:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"investigate","type":"investigation","key":"ROOT_CAUSE_KEY","insight":"ROOT_CAUSE_SUMMARY","confidence":9,"source":"observed","files":["affected/file1.ts","affected/file2.ts"]}'
+```
+
 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ---

 ## Important Rules
@@ -13,6 +13,10 @@ allowed-tools:
  - Write
  - Glob
  - AskUserQuestion
+triggers:
+  - merge and deploy
+  - land the pr
+  - ship to production
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -256,6 +260,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -374,6 +380,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -14,6 +14,10 @@ allowed-tools:
  - Glob
  - AskUserQuestion
 sensitive: true
+triggers:
+  - merge and deploy
+  - land the pr
+  - ship to production
 ---

 {{PREAMBLE}}
@@ -8,6 +8,10 @@ description: |
  "show learnings", "prune stale learnings", or "export learnings".
  Proactively suggest when the user asks about past patterns or wonders
  "didn't we fix this before?"
+triggers:
+  - show learnings
+  - what have we learned
+  - manage project learnings
 allowed-tools:
  - Bash
  - Read
@@ -259,6 +263,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -377,6 +383,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -8,6 +8,10 @@ description: |
  "show learnings", "prune stale learnings", or "export learnings".
  Proactively suggest when the user asks about past patterns or wonders
  "didn't we fix this before?"
+triggers:
+  - show learnings
+  - what have we learned
+  - manage project learnings
 allowed-tools:
  - Bash
  - Read
@@ -23,6 +23,11 @@ allowed-tools:
  - Edit
  - AskUserQuestion
  - WebSearch
+triggers:
+  - brainstorm this
+  - is this worth building
+  - help me think through
+  - office hours
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -266,6 +271,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -384,6 +391,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -603,6 +623,8 @@ You are a **YC office hours partner**. Your job is to ensure the problem is unde

 ---

+
+
 ## Phase 1: Context Gathering

 Understand the project and the area the user wants to change.
@@ -1322,7 +1344,10 @@ PRIOR=$(ls -t ~/.gstack/projects/$SLUG/*-$BRANCH-design-*.md 2>/dev/null | head
 ```
 If `$PRIOR` exists, the new doc gets a `Supersedes:` field referencing it. This creates a revision chain — you can trace how a design evolved across office hours sessions.

-Write to `~/.gstack/projects/{slug}/{user}-{branch}-design-{datetime}.md`:
+Write to `~/.gstack/projects/{slug}/{user}-{branch}-design-{datetime}.md`.
+
+After writing the design doc, tell the user:
+**"Design doc saved to: {full path}. Other skills (/plan-ceo-review, /plan-eng-review) will find it automatically."**

 ### Startup mode design doc template:

@@ -1511,6 +1536,8 @@ Present the reviewed design doc to the user via AskUserQuestion:
 - B) Revise — specify which sections need changes (loop back to revise those sections)
 - C) Start over — return to Phase 2

+
+
 ---

 ## Phase 6: Handoff — The Relationship Closing
@@ -23,6 +23,11 @@ allowed-tools:
  - Edit
  - AskUserQuestion
  - WebSearch
+triggers:
+  - brainstorm this
+  - is this worth building
+  - help me think through
+  - office hours
 ---

 {{PREAMBLE}}
@@ -37,6 +42,8 @@ You are a **YC office hours partner**. Your job is to ensure the problem is unde

 ---

+{{GBRAIN_CONTEXT_LOAD}}
+
 ## Phase 1: Context Gathering

 Understand the project and the area the user wants to change.
@@ -462,7 +469,10 @@ PRIOR=$(ls -t ~/.gstack/projects/$SLUG/*-$BRANCH-design-*.md 2>/dev/null | head
 ```
 If `$PRIOR` exists, the new doc gets a `Supersedes:` field referencing it. This creates a revision chain — you can trace how a design evolved across office hours sessions.

-Write to `~/.gstack/projects/{slug}/{user}-{branch}-design-{datetime}.md`:
+Write to `~/.gstack/projects/{slug}/{user}-{branch}-design-{datetime}.md`.
+
+After writing the design doc, tell the user:
+**"Design doc saved to: {full path}. Other skills (/plan-ceo-review, /plan-eng-review) will find it automatically."**

 ### Startup mode design doc template:

@@ -591,6 +601,8 @@ Present the reviewed design doc to the user via AskUserQuestion:
 - B) Revise — specify which sections need changes (loop back to revise those sections)
 - C) Start over — return to Phase 2

+{{GBRAIN_SAVE_RESULTS}}
+
 ---

 ## Phase 6: Handoff — The Relationship Closing
@@ -8,6 +8,10 @@ description: |
  Use when asked to "open gstack browser", "launch browser", "connect chrome",
  "open chrome", "real browser", "launch chrome", "side panel", or "control my browser".
  Voice triggers (speech-to-text aliases): "show me the browser".
+triggers:
+  - open gstack browser
+  - launch chromium
+  - show me the browser
 allowed-tools:
  - Bash
  - Read
@@ -256,6 +260,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -374,6 +380,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -9,6 +9,10 @@ description: |
  "open chrome", "real browser", "launch chrome", "side panel", or "control my browser".
 voice-triggers:
  - "show me the browser"
+triggers:
+  - open gstack browser
+  - launch chromium
+  - show me the browser
 allowed-tools:
  - Bash
  - Read
@@ -129,6 +129,7 @@ Once selected, commit fully. Do not silently drift.
 **Anti-skip rule:** Never condense, abbreviate, or skip any review section regardless of plan type. If a section genuinely has zero findings, say "No issues found" and move on, but you must evaluate it.

 Ask the user about each issue ONE AT A TIME. Do NOT batch.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 1: Architecture Review
 Evaluate system design, component boundaries, data flow (all four paths), state machines, coupling, scaling, security architecture, production failure scenarios, rollback posture. Draw dependency graphs.
@@ -281,7 +281,8 @@ Count the signals for the closing message.

 ## Phase 5: Design Doc

-Write the design document and save it to memory.
+Write the design document and save it to memory. After writing, tell the user:
+**"Design doc saved. Other skills (/plan-ceo-review, /plan-eng-review) will find it automatically."**

 ### Startup mode design doc template:

@@ -25,6 +25,11 @@ Parse the argument to determine the time window. Default to 7 days. All times sh

 ---

+### Non-git context (optional)
+
+Check memory for non-git context: meeting notes, calendar events, decisions, and other
+context that doesn't appear in git history. If found, incorporate into the retro narrative.
+
 ### Step 1: Gather Raw Data

 First, fetch origin and identify the current user:
@@ -1,6 +1,6 @@
 {
  "name": "gstack",
-  "version": "0.16.2.0",
+  "version": "0.18.0.0",
  "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
  "license": "MIT",
  "type": "module",
@@ -9,6 +9,10 @@ description: |
  Use when asked to "pair agent", "connect agent", "share browser", "remote browser",
  "let another agent use my browser", or "give browser access". (gstack)
  Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".
+triggers:
+  - pair with agent
+  - connect remote agent
+  - share my browser
 allowed-tools:
  - Bash
  - Read
@@ -257,6 +261,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -375,6 +381,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -13,6 +13,10 @@ voice-triggers:
  - "connect agent"
  - "share my browser"
  - "remote browser access"
+triggers:
+  - pair with agent
+  - connect remote agent
+  - share my browser
 allowed-tools:
  - Bash
  - Read
@@ -19,6 +19,11 @@ allowed-tools:
  - Bash
  - AskUserQuestion
  - WebSearch
+triggers:
+  - think bigger
+  - expand scope
+  - strategy review
+  - rethink this plan
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -262,6 +267,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -380,6 +387,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -868,6 +888,8 @@ matches a past learning, display:
 This makes the compounding visible. The user should see that gstack is getting
 smarter on their codebase over time.

+
+
 ## Step 0: Nuclear Scope Challenge + Mode Selection

 ### 0A. Premise Challenge
@@ -1090,6 +1112,7 @@ After mode is selected, confirm which implementation approach (from 0C-bis) appl

 Once selected, commit fully. Do not silently drift.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ## Review Sections (11 sections, after scope and mode are agreed)

@@ -1119,6 +1142,7 @@ Evaluate and diagram:

 Required ASCII diagram: full system architecture showing new components and their relationships to existing ones.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 2: Error & Rescue Map
 This is the section that catches silent failures. It is not optional.
@@ -1148,6 +1172,7 @@ Rules for this section:
 * For each GAP (unrescued error that should be rescued): specify the rescue action and what the user should see.
 * For LLM/AI service calls specifically: what happens when the response is malformed? When it's empty? When it hallucinates invalid JSON? When the model returns a refusal? Each of these is a distinct failure mode.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 3: Security & Threat Model
 Security is not a sub-bullet of architecture. It gets its own section.
@@ -1163,6 +1188,7 @@ Evaluate:

 For each finding: threat, likelihood (High/Med/Low), impact (High/Med/Low), and whether the plan mitigates it.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 4: Data Flow & Interaction Edge Cases
 This section traces data through the system and interactions through the UI with adversarial thoroughness.
@@ -1199,6 +1225,7 @@ For each node: what happens on each shadow path? Is it tested?
 ```
 Flag any unhandled edge case as a gap. For each gap, specify the fix.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 5: Code Quality Review
 Evaluate:
@@ -1211,6 +1238,7 @@ Evaluate:
 * Under-engineering check. Anything fragile, assuming happy path only, or missing obvious defensive checks?
 * Cyclomatic complexity. Flag any new method that branches more than 5 times. Propose a refactor.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 6: Test Review
 Make a complete diagram of every new thing this plan introduces:
@@ -1251,6 +1279,7 @@ Load/stress test requirements: For any new codepath called frequently or process

 For LLM/prompt changes: Check CLAUDE.md for the "Prompt/LLM changes" file patterns. If this plan touches ANY of those patterns, state which eval suites must be run, which cases should be added, and what baselines to compare against.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 7: Performance Review
 Evaluate:
@@ -1262,6 +1291,7 @@ Evaluate:
 * Slow paths. Top 3 slowest new codepaths and estimated p99 latency.
 * Connection pool pressure. New DB connections, Redis connections, HTTP connections?
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 8: Observability & Debuggability Review
 New systems break. This section ensures you can see why.
@@ -1278,6 +1308,7 @@ Evaluate:
 **EXPANSION and SELECTIVE EXPANSION addition:**
 * What observability would make this feature a joy to operate? (For SELECTIVE EXPANSION, include observability for any accepted cherry-picks.)
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 9: Deployment & Rollout Review
 Evaluate:
@@ -1293,6 +1324,7 @@ Evaluate:
 **EXPANSION and SELECTIVE EXPANSION addition:**
 * What deploy infrastructure would make shipping this feature routine? (For SELECTIVE EXPANSION, assess whether accepted cherry-picks change the deployment risk profile.)
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 10: Long-Term Trajectory Review
 Evaluate:
@@ -1308,6 +1340,7 @@ Evaluate:
 * Platform potential. Does this create capabilities other features can leverage?
 * (SELECTIVE EXPANSION only) Retrospective: Were the right cherry-picks accepted? Did any rejected expansions turn out to be load-bearing for the accepted ones?
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 11: Design & UX Review (skip if no UI scope detected)
 The CEO calling in the designer. Not a pixel-level audit — that's /plan-design-review and /design-review. This is ensuring the plan has design intentionality.
@@ -1330,6 +1363,7 @@ Required ASCII diagram: user flow showing screens/states and transitions.

 If this plan has significant UI scope, recommend: "Consider running /plan-design-review for a deep design review of this plan before implementation."
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ## Outside Voice — Independent Plan Challenge (optional, recommended)

@@ -1797,6 +1831,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Mode Quick Reference
 ```
  ┌────────────────────────────────────────────────────────────────────────────────┐
@@ -19,6 +19,11 @@ allowed-tools:
  - Bash
  - AskUserQuestion
  - WebSearch
+triggers:
+  - think bigger
+  - expand scope
+  - strategy review
+  - rethink this plan
 ---

 {{PREAMBLE}}
@@ -190,6 +195,8 @@ Feed into the Premise Challenge (0A) and Dream State Mapping (0C). If you find a

 {{LEARNINGS_SEARCH}}

+{{GBRAIN_CONTEXT_LOAD}}
+
 ## Step 0: Nuclear Scope Challenge + Mode Selection

 ### 0A. Premise Challenge
@@ -352,6 +359,7 @@ After mode is selected, confirm which implementation approach (from 0C-bis) appl

 Once selected, commit fully. Do not silently drift.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ## Review Sections (11 sections, after scope and mode are agreed)

@@ -381,6 +389,7 @@ Evaluate and diagram:

 Required ASCII diagram: full system architecture showing new components and their relationships to existing ones.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 2: Error & Rescue Map
 This is the section that catches silent failures. It is not optional.
@@ -410,6 +419,7 @@ Rules for this section:
 * For each GAP (unrescued error that should be rescued): specify the rescue action and what the user should see.
 * For LLM/AI service calls specifically: what happens when the response is malformed? When it's empty? When it hallucinates invalid JSON? When the model returns a refusal? Each of these is a distinct failure mode.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 3: Security & Threat Model
 Security is not a sub-bullet of architecture. It gets its own section.
@@ -425,6 +435,7 @@ Evaluate:

 For each finding: threat, likelihood (High/Med/Low), impact (High/Med/Low), and whether the plan mitigates it.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 4: Data Flow & Interaction Edge Cases
 This section traces data through the system and interactions through the UI with adversarial thoroughness.
@@ -461,6 +472,7 @@ For each node: what happens on each shadow path? Is it tested?
 ```
 Flag any unhandled edge case as a gap. For each gap, specify the fix.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 5: Code Quality Review
 Evaluate:
@@ -473,6 +485,7 @@ Evaluate:
 * Under-engineering check. Anything fragile, assuming happy path only, or missing obvious defensive checks?
 * Cyclomatic complexity. Flag any new method that branches more than 5 times. Propose a refactor.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 6: Test Review
 Make a complete diagram of every new thing this plan introduces:
@@ -513,6 +526,7 @@ Load/stress test requirements: For any new codepath called frequently or process

 For LLM/prompt changes: Check CLAUDE.md for the "Prompt/LLM changes" file patterns. If this plan touches ANY of those patterns, state which eval suites must be run, which cases should be added, and what baselines to compare against.
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 7: Performance Review
 Evaluate:
@@ -524,6 +538,7 @@ Evaluate:
 * Slow paths. Top 3 slowest new codepaths and estimated p99 latency.
 * Connection pool pressure. New DB connections, Redis connections, HTTP connections?
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 8: Observability & Debuggability Review
 New systems break. This section ensures you can see why.
@@ -540,6 +555,7 @@ Evaluate:
 **EXPANSION and SELECTIVE EXPANSION addition:**
 * What observability would make this feature a joy to operate? (For SELECTIVE EXPANSION, include observability for any accepted cherry-picks.)
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 9: Deployment & Rollout Review
 Evaluate:
@@ -555,6 +571,7 @@ Evaluate:
 **EXPANSION and SELECTIVE EXPANSION addition:**
 * What deploy infrastructure would make shipping this feature routine? (For SELECTIVE EXPANSION, assess whether accepted cherry-picks change the deployment risk profile.)
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 10: Long-Term Trajectory Review
 Evaluate:
@@ -570,6 +587,7 @@ Evaluate:
 * Platform potential. Does this create capabilities other features can leverage?
 * (SELECTIVE EXPANSION only) Retrospective: Were the right cherry-picks accepted? Did any rejected expansions turn out to be load-bearing for the accepted ones?
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 ### Section 11: Design & UX Review (skip if no UI scope detected)
 The CEO calling in the designer. Not a pixel-level audit — that's /plan-design-review and /design-review. This is ensuring the plan has design intentionality.
@@ -592,6 +610,7 @@ Required ASCII diagram: user flow showing screens/states and transitions.

 If this plan has significant UI scope, recommend: "Consider running /plan-design-review for a deep design review of this plan before implementation."
 **STOP.** AskUserQuestion once per issue. Do NOT batch. Recommend + WHY. If no issues or fix is obvious, state what you'll do and move on — don't waste a question. Do NOT proceed until user responds.
+**Reminder: Do NOT make any code changes. Review only.**

 {{CODEX_PLAN_REVIEW}}

@@ -783,6 +802,8 @@ If promoted, copy the CEO plan content to `docs/designs/{FEATURE}.md` (create th

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Mode Quick Reference
 ```
  ┌────────────────────────────────────────────────────────────────────────────────┐
@@ -17,6 +17,10 @@ allowed-tools:
  - Glob
  - Bash
  - AskUserQuestion
+triggers:
+  - design plan review
+  - review ux plan
+  - check design decisions
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -260,6 +264,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -378,6 +384,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -17,6 +17,10 @@ allowed-tools:
  - Glob
  - Bash
  - AskUserQuestion
+triggers:
+  - design plan review
+  - review ux plan
+  - check design decisions
 ---

 {{PREAMBLE}}
@@ -21,6 +21,10 @@ allowed-tools:
  - Bash
  - AskUserQuestion
  - WebSearch
+triggers:
+  - developer experience review
+  - dx plan review
+  - check developer onboarding
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -264,6 +268,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -382,6 +388,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -27,6 +27,10 @@ allowed-tools:
  - Bash
  - AskUserQuestion
  - WebSearch
+triggers:
+  - developer experience review
+  - dx plan review
+  - check developer onboarding
 ---

 {{PREAMBLE}}
@@ -19,6 +19,10 @@ allowed-tools:
  - AskUserQuestion
  - Bash
  - WebSearch
+triggers:
+  - review architecture
+  - eng plan review
+  - check the implementation plan
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -262,6 +266,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -380,6 +386,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -555,6 +574,8 @@ Then write a `## GSTACK REVIEW REPORT` section to the end of the plan file:
 file you are allowed to edit in plan mode. The plan file review report is part of the
 plan's living status.

+
+
 # Plan Review Mode

 Review this plan thoroughly before making any code changes. For every issue or recommendation, explain the concrete tradeoffs, give me an opinionated recommendation, and ask for my input before assuming a direction.
@@ -1410,6 +1431,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Next Steps — Review Chaining

 After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale.
@@ -22,10 +22,16 @@ allowed-tools:
  - AskUserQuestion
  - Bash
  - WebSearch
+triggers:
+  - review architecture
+  - eng plan review
+  - check the implementation plan
 ---

 {{PREAMBLE}}

+{{GBRAIN_CONTEXT_LOAD}}
+
 # Plan Review Mode

 Review this plan thoroughly before making any code changes. For every issue or recommendation, explain the concrete tradeoffs, give me an opinionated recommendation, and ask for my input before assuming a direction.
@@ -295,6 +301,8 @@ Substitute values from the Completion Summary:

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Next Steps — Review Chaining

 After displaying the Review Readiness Dashboard, check if additional reviews would be valuable. Read the dashboard output to see which reviews have already been run and whether they are stale.
@@ -15,6 +15,10 @@ allowed-tools:
  - Write
  - AskUserQuestion
  - WebSearch
+triggers:
+  - qa report only
+  - just report bugs
+  - test but dont fix
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -258,6 +262,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -376,6 +382,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -17,6 +17,10 @@ allowed-tools:
  - Write
  - AskUserQuestion
  - WebSearch
+triggers:
+  - qa report only
+  - just report bugs
+  - test but dont fix
 ---

 {{PREAMBLE}}
@@ -21,6 +21,10 @@ allowed-tools:
  - Grep
  - AskUserQuestion
  - WebSearch
+triggers:
+  - qa test this
+  - find bugs on site
+  - test the site
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -264,6 +268,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -382,6 +388,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -596,6 +615,8 @@ branch name wherever the instructions say "the base branch" or `<default>`.

 ---

+
+
 # /qa: Test → Fix → Verify

 You are a QA engineer AND a bug-fix engineer. Test web applications like a real user — click everything, fill every form, check every state. When you find bugs, fix them in source code with atomic commits, then re-verify. Produce a structured report with before/after evidence.
@@ -1410,6 +1431,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Additional Rules (qa-specific)

 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
@@ -24,12 +24,18 @@ allowed-tools:
  - Grep
  - AskUserQuestion
  - WebSearch
+triggers:
+  - qa test this
+  - find bugs on site
+  - test the site
 ---

 {{PREAMBLE}}

 {{BASE_BRANCH_DETECT}}

+{{GBRAIN_CONTEXT_LOAD}}
+
 # /qa: Test → Fix → Verify

 You are a QA engineer AND a bug-fix engineer. Test web applications like a real user — click everything, fill every form, check every state. When you find bugs, fix them in source code with atomic commits, then re-verify. Produce a structured report with before/after evidence.
@@ -323,6 +329,8 @@ If the repo has a `TODOS.md`:

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Additional Rules (qa-specific)

 11. **Clean working tree required.** If dirty, use AskUserQuestion to offer commit/stash/abort before proceeding.
@@ -14,6 +14,10 @@ allowed-tools:
  - Write
  - Glob
  - AskUserQuestion
+triggers:
+  - weekly retro
+  - what did we ship
+  - engineering retrospective
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -257,6 +261,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -375,6 +381,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -588,6 +607,8 @@ When the user types `/retro`, run this skill.
 - `/retro global` — cross-project retro across all AI coding tools (7d default)
 - `/retro global 14d` — cross-project retro with explicit window

+
+
 ## Instructions

 Parse the argument to determine the time window. Default to 7 days if no argument given. All times should be reported in the user's **local timezone** (use the system default — do NOT set `TZ`).
@@ -647,6 +668,16 @@ matches a past learning, display:
 This makes the compounding visible. The user should see that gstack is getting
 smarter on their codebase over time.

+### Non-git context (optional)
+
+Check for non-git context that should be included in the retro:
+
+```bash
+[ -f ~/.gstack/retro-context.md ] && echo "RETRO_CONTEXT_FOUND" || echo "NO_RETRO_CONTEXT"
+```
+
+If `RETRO_CONTEXT_FOUND`: read `~/.gstack/retro-context.md`. This file is user-authored and may contain meeting notes, calendar events, decisions, and other context that doesn't appear in git history. Incorporate this context into the retro narrative where relevant.
+
 ### Step 1: Gather Raw Data

 First, fetch origin and identify the current user:
@@ -891,6 +922,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ### Step 10: Week-over-Week Trends (if window >= 14d)

 If the time window is 14 days or more, split into weekly buckets and show trends:
@@ -14,6 +14,10 @@ allowed-tools:
  - Write
  - Glob
  - AskUserQuestion
+triggers:
+  - weekly retro
+  - what did we ship
+  - engineering retrospective
 ---

 {{PREAMBLE}}
@@ -37,6 +41,8 @@ When the user types `/retro`, run this skill.
 - `/retro global` — cross-project retro across all AI coding tools (7d default)
 - `/retro global 14d` — cross-project retro with explicit window

+{{GBRAIN_CONTEXT_LOAD}}
+
 ## Instructions

 Parse the argument to determine the time window. Default to 7 days if no argument given. All times should be reported in the user's **local timezone** (use the system default — do NOT set `TZ`).
@@ -60,6 +66,16 @@ Usage: /retro [window | compare | global]

 {{LEARNINGS_SEARCH}}

+### Non-git context (optional)
+
+Check for non-git context that should be included in the retro:
+
+```bash
+[ -f ~/.gstack/retro-context.md ] && echo "RETRO_CONTEXT_FOUND" || echo "NO_RETRO_CONTEXT"
+```
+
+If `RETRO_CONTEXT_FOUND`: read `~/.gstack/retro-context.md`. This file is user-authored and may contain meeting notes, calendar events, decisions, and other context that doesn't appear in git history. Incorporate this context into the retro narrative where relevant.
+
 ### Step 1: Gather Raw Data

 First, fetch origin and identify the current user:
@@ -281,6 +297,8 @@ For each contributor (including the current user), compute:

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ### Step 10: Week-over-Week Trends (if window >= 14d)

 If the time window is 14 days or more, split into weekly buckets and show trends:
@@ -17,6 +17,11 @@ allowed-tools:
  - Agent
  - AskUserQuestion
  - WebSearch
+triggers:
+  - review this pr
+  - code review
+  - check my diff
+  - pre-landing review
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -260,6 +265,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -378,6 +385,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -842,6 +862,19 @@ git fetch origin <base> --quiet

 Run `git diff origin/<base>` to get the full diff. This includes both committed and uncommitted changes against the latest base branch.

+## Step 3.5: Slop scan (advisory)
+
+Run a slop scan on changed files to catch AI code quality issues (empty catches,
+redundant `return await`, overcomplicated abstractions):
+
+```bash
+bun run slop:diff origin/<base> 2>/dev/null || true
+```
+
+If findings are reported, include them in the review output as an informational
+diagnostic. Slop findings are advisory, never blocking. If slop:diff is not
+available (e.g., slop-scan not installed), skip this step silently.
+
 ---

 ## Prior Learnings
@@ -17,6 +17,11 @@ allowed-tools:
  - Agent
  - AskUserQuestion
  - WebSearch
+triggers:
+  - review this pr
+  - code review
+  - check my diff
+  - pre-landing review
 ---

 {{PREAMBLE}}
@@ -69,6 +74,19 @@ git fetch origin <base> --quiet

 Run `git diff origin/<base>` to get the full diff. This includes both committed and uncommitted changes against the latest base branch.

+## Step 3.5: Slop scan (advisory)
+
+Run a slop scan on changed files to catch AI code quality issues (empty catches,
+redundant `return await`, overcomplicated abstractions):
+
+```bash
+bun run slop:diff origin/<base> 2>/dev/null || true
+```
+
+If findings are reported, include them in the review output as an informational
+diagnostic. Slop findings are advisory, never blocking. If slop:diff is not
+available (e.g., slop-scan not installed), skip this step silently.
+
 ---

 {{LEARNINGS_SEARCH}}
@@ -289,6 +289,18 @@ function transformFrontmatter(content: string, host: Host): string {
    }
  }

+  // Preserve additional keepFields beyond name and description
+  if (fm.keepFields) {
+    for (const field of fm.keepFields) {
+      if (field === 'name' || field === 'description') continue;
+      // Match YAML field with possible multi-line/array value (indented lines after colon)
+      const fieldMatch = frontmatter.match(new RegExp(`^${field}:(.*(?:\\n(?:[ \\t]+.+))*)`, 'm'));
+      if (fieldMatch) {
+        newFm += `${field}:${fieldMatch[1]}\n`;
+      }
+    }
+  }
+
  // Rename fields (copy values from template frontmatter with new keys)
  if (fm.renameFields) {
    for (const [oldName, newName] of Object.entries(fm.renameFields)) {
@@ -0,0 +1,70 @@
+/**
+ * GBrain resolver — brain-first lookup and save-to-brain for thinking skills.
+ *
+ * GBrain is a "mod" for gstack. When installed, coding skills become brain-aware:
+ * they search the brain for context before starting and save results after finishing.
+ *
+ * These resolvers are suppressed on hosts that don't support brain features
+ * (via suppressedResolvers in each host config). For those hosts,
+ * {{GBRAIN_CONTEXT_LOAD}} and {{GBRAIN_SAVE_RESULTS}} resolve to empty string.
+ *
+ * Compatible with GBrain >= v0.10.0 (search CLI, doctor --fast --json, entity enrichment).
+ */
+import type { TemplateContext } from './types';
+
+export function generateGBrainContextLoad(ctx: TemplateContext): string {
+  let base = `## Brain Context Load
+
+Before starting this skill, search your brain for relevant context:
+
+1. Extract 2-4 keywords from the user's request (nouns, error names, file paths, technical terms).
+   Search GBrain: \`gbrain search "keyword1 keyword2"\`
+   Example: for "the login page is broken after deploy", search \`gbrain search "login broken deploy"\`
+   Search returns lines like: \`[slug] Title (score: 0.85) - first line of content...\`
+2. If few results, broaden to the single most specific keyword and search again.
+3. For each result page, read it: \`gbrain get_page "<page_slug>"\`
+   Read the top 3 pages for context.
+4. Use this brain context to inform your analysis.
+
+If GBrain is not available or returns no results, proceed without brain context.
+Any non-zero exit code from gbrain commands should be treated as a transient failure.`;
+
+  if (ctx.skillName === 'investigate') {
+    base += `\n\nIf the user's request is about tracking, extracting, or researching structured data (e.g., "track this data", "extract from emails", "build a tracker"), route to GBrain's data-research skill instead: \`gbrain call data-research\`. This skill has a 7-phase pipeline optimized for structured data extraction.`;
+  }
+
+  return base;
+}
+
+export function generateGBrainSaveResults(ctx: TemplateContext): string {
+  const skillSaveMap: Record<string, string> = {
+    'office-hours': 'Save the design document as a brain page:\n```bash\ngbrain put_page --title "Office Hours: <project name>" --tags "design-doc,<project-slug>" <<\'EOF\'\n<design doc content in markdown>\nEOF\n```',
+    'investigate': 'Save the root cause analysis as a brain page:\n```bash\ngbrain put_page --title "Investigation: <issue summary>" --tags "investigation,<affected-files>" <<\'EOF\'\n<investigation findings in markdown>\nEOF\n```',
+    'plan-ceo-review': 'Save the CEO plan as a brain page:\n```bash\ngbrain put_page --title "CEO Plan: <feature name>" --tags "ceo-plan,<feature-slug>" <<\'EOF\'\n<scope decisions and vision in markdown>\nEOF\n```',
+    'retro': 'Save the retrospective as a brain page:\n```bash\ngbrain put_page --title "Retro: <date range>" --tags "retro,<date>" <<\'EOF\'\n<retro output in markdown>\nEOF\n```',
+    'plan-eng-review': 'Save the architecture decisions as a brain page:\n```bash\ngbrain put_page --title "Eng Review: <feature name>" --tags "eng-review,<feature-slug>" <<\'EOF\'\n<review findings and decisions in markdown>\nEOF\n```',
+    'ship': 'Save the release notes as a brain page:\n```bash\ngbrain put_page --title "Release: <version>" --tags "release,<version>" <<\'EOF\'\n<changelog entry and deploy details in markdown>\nEOF\n```',
+    'cso': 'Save the security audit as a brain page:\n```bash\ngbrain put_page --title "Security Audit: <date>" --tags "security-audit,<date>" <<\'EOF\'\n<findings and remediation status in markdown>\nEOF\n```',
+    'design-consultation': 'Save the design system as a brain page:\n```bash\ngbrain put_page --title "Design System: <project name>" --tags "design-system,<project-slug>" <<\'EOF\'\n<design decisions in markdown>\nEOF\n```',
+  };
+
+  const saveInstruction = skillSaveMap[ctx.skillName] || 'Save the skill output as a brain page if the results are worth preserving:\n```bash\ngbrain put_page --title "<descriptive title>" --tags "<relevant,tags>" <<\'EOF\'\n<content in markdown>\nEOF\n```';
+
+  return `## Save Results to Brain
+
+After completing this skill, persist the results to your brain for future reference:
+
+${saveInstruction}
+
+After saving the page, extract and enrich mentioned entities: for each actual person name or company/organization name found in the output, \`gbrain search "<entity name>"\` to check if a page exists. If not, create a stub page:
+\`\`\`bash
+gbrain put_page --title "<Person or Company Name>" --tags "entity,person" --content "Stub page. Mentioned in <skill name> output."
+\`\`\`
+Only extract actual person names and company/organization names. Skip product names, section headings, technical terms, and file paths.
+
+Throttle errors appear as: exit code 1 with stderr containing "throttle", "rate limit", "capacity", or "busy". If GBrain returns a throttle or rate-limit error on any save operation, defer the save and move on. The brain is busy — the content is not lost, just not persisted this run. Any other non-zero exit code should also be treated as a transient failure.
+
+Add backlinks to related brain pages if they exist. If GBrain is not available, skip this step.
+
+After brain operations complete, note in your completion output: how many pages were found in the initial search, how many entities were enriched, and whether any operations were throttled. This helps the user see brain utilization over time.`;
+}
@@ -18,6 +18,7 @@ import { generateConfidenceCalibration } from './confidence';
 import { generateInvokeSkill } from './composition';
 import { generateReviewArmy } from './review-army';
 import { generateDxFramework } from './dx';
+import { generateGBrainContextLoad, generateGBrainSaveResults } from './gbrain';

 export const RESOLVERS: Record<string, ResolverFn> = {
  SLUG_EVAL: generateSlugEval,
@@ -63,4 +64,6 @@ export const RESOLVERS: Record<string, ResolverFn> = {
  REVIEW_ARMY: generateReviewArmy,
  CROSS_REVIEW_DEDUP: generateCrossReviewDedup,
  DX_FRAMEWORK: generateDxFramework,
+  GBRAIN_CONTEXT_LOAD: generateGBrainContextLoad,
+  GBRAIN_SAVE_RESULTS: generateGBrainSaveResults,
 };
@@ -98,7 +98,18 @@ if [ -d ".claude/skills/gstack" ] && [ ! -L ".claude/skills/gstack" ]; then
 fi
 echo "VENDORED_GSTACK: $_VENDORED"
 # Detect spawned session (OpenClaw or other orchestrator)
-[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true
+[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true${ctx.host === 'gbrain' || ctx.host === 'hermes' ? `
+# GBrain health check (gbrain/hermes host only)
+if command -v gbrain &>/dev/null; then
+  _BRAIN_JSON=$(gbrain doctor --fast --json 2>/dev/null || echo '{}')
+  _BRAIN_SCORE=$(echo "$_BRAIN_JSON" | grep -o '"health_score":[0-9]*' | cut -d: -f2)
+  _BRAIN_FAILS=$(echo "$_BRAIN_JSON" | grep -o '"status":"fail"' | wc -l | tr -d ' ')
+  _BRAIN_WARNS=$(echo "$_BRAIN_JSON" | grep -o '"status":"warn"' | wc -l | tr -d ' ')
+  echo "BRAIN_HEALTH: \${_BRAIN_SCORE:-unknown} (\${_BRAIN_FAILS:-0} failures, \${_BRAIN_WARNS:-0} warnings)"
+  if [ "\${_BRAIN_SCORE:-100}" -lt 50 ] 2>/dev/null; then
+    echo "$_BRAIN_JSON" | grep -o '"name":"[^"]*","status":"[^"]*","message":"[^"]*"' || true
+  fi
+fi` : ''}
 \`\`\``;
 }

@@ -270,6 +281,14 @@ touch ~/.gstack/.vendoring-warned-\${SLUG:-unknown}
 This only happens once per project. If the marker file exists, skip entirely.`;
 }

+function generateBrainHealthInstruction(ctx: TemplateContext): string {
+  if (ctx.host !== 'gbrain' && ctx.host !== 'hermes') return '';
+  return `If \`BRAIN_HEALTH\` is shown and the score is below 50, tell the user which checks
+failed (shown in the output) and suggest: "Run \\\`gbrain doctor\\\` for full diagnostics."
+If the output is not valid JSON or health_score is missing, treat GBrain as unavailable
+and proceed without brain features this session.`;
+}
+
 function generateSpawnedSessionCheck(): string {
  return `If \`SPAWNED_SESSION\` is \`"true"\`, you are running inside a session spawned by an
 AI orchestrator (e.g., OpenClaw). In spawned sessions:
@@ -426,6 +445,21 @@ Use AskUserQuestion:
 - Note in output: "Pre-existing test failure skipped: <test-name>"`;
 }

+function generateConfusionProtocol(): string {
+  return `## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.`;
+}
+
 function generateSearchBeforeBuildingSection(ctx: TemplateContext): string {
  return `## Search Before Building

@@ -730,8 +764,9 @@ export function generatePreamble(ctx: TemplateContext): string {
    generateRoutingInjection(ctx),
    generateVendoringDeprecation(ctx),
    generateSpawnedSessionCheck(),
+    generateBrainHealthInstruction(ctx),
    generateVoiceDirective(tier),
-    ...(tier >= 2 ? [generateContextRecovery(ctx), generateAskUserFormat(ctx), generateCompletenessSection()] : []),
+    ...(tier >= 2 ? [generateContextRecovery(ctx), generateAskUserFormat(ctx), generateCompletenessSection(), generateConfusionProtocol()] : []),
    ...(tier >= 3 ? [generateRepoModeSection(), generateSearchBeforeBuildingSection(ctx)] : []),
    generateCompletionStatus(ctx),
  ];
@@ -67,7 +67,29 @@ case "$HOST" in
    echo "  3. See docs/OPENCLAW.md for the full architecture"
    echo ""
    exit 0 ;;
-  *) echo "Unknown --host value: $HOST (expected claude, codex, kiro, factory, openclaw, or auto)" >&2; exit 1 ;;
+  hermes)
+    echo ""
+    echo "Hermes integration uses the same model as OpenClaw — Hermes spawns"
+    echo "Claude Code sessions, and gstack provides methodology artifacts."
+    echo ""
+    echo "To integrate gstack with Hermes:"
+    echo "  1. Tell your Hermes agent: 'install gstack for hermes'"
+    echo "  2. Or generate artifacts: bun run gen:skill-docs --host hermes"
+    echo ""
+    exit 0 ;;
+  gbrain)
+    echo ""
+    echo "GBrain is a mod for gstack — it makes coding skills brain-aware."
+    echo "GBrain generates brain-enhanced skill variants that search your brain"
+    echo "for context before starting and save results after finishing."
+    echo ""
+    echo "To generate brain-aware skills:"
+    echo "  bun run gen:skill-docs --host gbrain"
+    echo ""
+    echo "GBrain setup and brain skills ship from the GBrain repo."
+    echo ""
+    exit 0 ;;
+  *) echo "Unknown --host value: $HOST (expected claude, codex, kiro, factory, openclaw, hermes, gbrain, or auto)" >&2; exit 1 ;;
 esac

 # ─── Resolve skill prefix preference ─────────────────────────
@@ -7,6 +7,10 @@ description: |
  Opens an interactive picker UI where you select which cookie domains to import.
  Use before QA testing authenticated pages. Use when asked to "import cookies",
  "login to the site", or "authenticate the browser". (gstack)
+triggers:
+  - import browser cookies
+  - login to test site
+  - setup authenticated session
 allowed-tools:
  - Bash
  - Read
@@ -254,6 +258,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 **Tone:** direct, concrete, sharp, never corporate, never academic. Sound like a builder, not a consultant. Name the file, the function, the command. No filler, no throat-clearing.
@@ -7,6 +7,10 @@ description: |
  Opens an interactive picker UI where you select which cookie domains to import.
  Use before QA testing authenticated pages. Use when asked to "import cookies",
  "login to the site", or "authenticate the browser". (gstack)
+triggers:
+  - import browser cookies
+  - login to test site
+  - setup authenticated session
 allowed-tools:
  - Bash
  - Read
@@ -9,6 +9,10 @@ description: |
  the configuration to CLAUDE.md so all future deploys are automatic.
  Use when: "setup deploy", "configure deployment", "set up land-and-deploy",
  "how do I deploy with gstack", "add deploy config".
+triggers:
+  - configure deploy
+  - setup deployment
+  - set deploy platform
 allowed-tools:
  - Bash
  - Read
@@ -260,6 +264,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -378,6 +384,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Completion Status Protocol

 When completing a skill workflow, report status using one of:
@@ -9,6 +9,10 @@ description: |
  the configuration to CLAUDE.md so all future deploys are automatic.
  Use when: "setup deploy", "configure deployment", "set up land-and-deploy",
  "how do I deploy with gstack", "add deploy config".
+triggers:
+  - configure deploy
+  - setup deployment
+  - set deploy platform
 allowed-tools:
  - Bash
  - Read
@@ -18,6 +18,11 @@ allowed-tools:
  - Agent
  - AskUserQuestion
  - WebSearch
+triggers:
+  - ship it
+  - create a pr
+  - push to main
+  - deploy this
 ---
 <!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
 <!-- Regenerate: bun run gen:skill-docs -->
@@ -261,6 +266,8 @@ AI orchestrator (e.g., OpenClaw). In spawned sessions:
 - Focus on completing the task and reporting results via prose output.
 - End with a completion report: what shipped, decisions made, anything uncertain.

+
+
 ## Voice

 You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
@@ -379,6 +386,19 @@ AI makes completeness near-free. Always recommend the complete option over short

 Include `Completeness: X/10` for each option (10=all edge cases, 7=happy path, 3=shortcut).

+## Confusion Protocol
+
+When you encounter high-stakes ambiguity during coding:
+- Two plausible architectures or data models for the same requirement
+- A request that contradicts existing patterns and you're unsure which to follow
+- A destructive operation where the scope is unclear
+- Missing context that would change your approach significantly
+
+STOP. Name the ambiguity in one sentence. Present 2-3 options with tradeoffs.
+Ask the user. Do not guess on architectural or data model decisions.
+
+This does NOT apply to routine coding, small features, or obvious changes.
+
 ## Repo Ownership — See Something, Say Something

 `REPO_MODE` controls how to handle issues outside your branch:
@@ -593,6 +613,8 @@ branch name wherever the instructions say "the base branch" or `<default>`.

 ---

+
+
 # Ship: Fully Automated Ship Workflow

 You are running the `/ship` workflow. This is a **non-interactive, fully automated** workflow. Do NOT ask for confirmation at any step. The user said `/ship` which means DO IT. Run straight through and output the PR URL at the end.
@@ -2168,6 +2190,8 @@ staleness detection: if those files are later deleted, the learning can be flagg
 **Only log genuine discoveries.** Don't log obvious things. Don't log things the user
 already knows. A good test: would this insight save time in a future session? If yes, log it.

+
+
 ## Step 4: Version bump (auto-decide)

 **Idempotency check:** Before bumping, compare VERSION against the base branch.
@@ -19,12 +19,19 @@ allowed-tools:
  - AskUserQuestion
  - WebSearch
 sensitive: true
+triggers:
+  - ship it
+  - create a pr
+  - push to main
+  - deploy this
 ---

 {{PREAMBLE}}

 {{BASE_BRANCH_DETECT}}

+{{GBRAIN_CONTEXT_LOAD}}
+
 # Ship: Fully Automated Ship Workflow

 You are running the `/ship` workflow. This is a **non-interactive, fully automated** workflow. Do NOT ask for confirmation at any step. The user said `/ship` which means DO IT. Run straight through and output the PR URL at the end.
@@ -345,6 +352,8 @@ For each classified comment:

 {{LEARNINGS_LOG}}

+{{GBRAIN_SAVE_RESULTS}}
+
 ## Step 4: Version bump (auto-decide)

 **Idempotency check:** Before bumping, compare VERSION against the base branch.
--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .17.0.0
 .18.0.0