Files
gstack/autoplan/SKILL.md.tmpl
T
garrytan 0668443f36 Merge origin/main into the Oct 8 triage wave
# Conflicts:
#	test/helpers/carve-guards.ts
2026-10-08 14:48:14 +00:00

471 lines
22 KiB
Cheetah

---
name: autoplan
preamble-tier: 3
version: 1.0.0
description: |
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk
and runs them sequentially with auto-decisions using 6 decision principles. Surfaces
taste decisions (close approaches, borderline scope, outside-review disagreements) at a final
approval gate. One command, fully reviewed plan out.
Use when asked to "auto review", "autoplan", "run all reviews", "review this plan
automatically", or "make the decisions for me".
Proactively suggest when the user has a plan file and wants to run the full review
gauntlet without answering 15-30 intermediate questions. (gstack)
voice-triggers:
- "auto plan"
- "automatic review"
benefits-from: [office-hours]
triggers:
- run all reviews
- automatic review pipeline
- auto plan review
allowed-tools:
- Bash
- Read
- Write
- Edit
- Glob
- Grep
- WebSearch
- AskUserQuestion
{{AUTOPLAN_PUBLICATION_HOOK}}
---
{{PREAMBLE}}
{{BASE_BRANCH_DETECT}}
## Design Doc Check
```bash
setopt +o nomatch 2>/dev/null || true # zsh compat
SLUG=$(~/.claude/skills/gstack/browse/bin/remote-slug 2>/dev/null || basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null | tr '/' '-' || echo 'no-branch')
{{DESIGN_DOC_DISCOVERY}}
```
If a design doc exists, read it and use its problem statement, constraints, and
chosen approach as input to the review pipeline.
{{BENEFITS_FROM}}
# /autoplan — Auto-Review Pipeline
Read every CEO, design, DX and eng section from disk at full interactive depth.
The 6 principles answer intermediate questions; taste goes to one final approval gate.
---
{{SECTION_INDEX:autoplan}}
---
## The 6 Decision Principles
1. **Choose completeness** — Ship the whole thing. Pick the approach that covers more edge cases.
2. **Boil lakes** — Fix everything in the blast radius (files modified by this plan + direct importers). Auto-approve expansions that are in blast radius AND < 1 day CC effort (< 5 files, no new infra).
3. **Pragmatic** — If two options fix the same thing, pick the cleaner one. 5 seconds choosing, not 5 minutes.
4. **DRY** — Duplicates existing functionality? Reject. Reuse what exists.
5. **Explicit over clever** — 10-line obvious fix > 200-line abstraction. Pick what a new contributor reads in 30 seconds.
6. **Bias toward action** — Merge > review cycles > stale deliberation. Flag concerns but don't block.
**Conflict resolution (context-dependent tiebreakers):**
- **CEO phase:** P1 (completeness) + P2 (boil lakes) dominate.
- **Eng phase:** P5 (explicit) + P3 (pragmatic) dominate.
- **Design phase:** P5 (explicit) + P1 (completeness) dominate.
---
## Decision Classification
Every auto-decision is classified:
**Mechanical** — one clearly right answer. Auto-decide silently.
Examples: run the outside reviewer when enabled (always yes), run evals (always yes), reduce scope on a complete plan (always no).
**Taste** — reasonable people could disagree. Auto-decide with recommendation, but surface at the final gate. Three natural sources:
1. **Close approaches** — top two are both viable with different tradeoffs.
2. **Borderline scope** — in blast radius but 3-5 files, or ambiguous radius.
3. **{{OUTSIDE_LABEL}} disagreements** — the outside reviewer recommends differently and has a valid point.
**User Challenge** — {{NATIVE_LABEL}} and {{OUTSIDE_LABEL}} both recommend changing the
user's stated direction: merge, split, add or remove features/skills/workflows.
NEVER auto-decide these. At the final approval gate, give:
the original direction, proposed change, reasoning, blind spots and cost of being
wrong, using the Phase 4 template. Flag agreed security/feasibility risks explicitly.
The user's original direction stands unless they approve the change.
---
## Sequential Execution — MANDATORY
Phases MUST execute in strict order: CEO → Design (if UI scope) → DX (if
developer-facing scope) → Eng. Eng runs LAST, always, reviewing all prior amendments.
Keep ONE phase active, completing these gates in order:
1. Load its phase instructions and full skill/sections, recording complete Read ranges.
On Claude Code, enter through a native `Read` of the installed phase driver,
then use native `Read` for its methodology ranges. The driver Read is the
guarded entrypoint. If denied, finish or repair the preceding phase and retry
that same Read; changing file-loading tools does not satisfy the boundary.
2. Complete the phase's required preliminary work (CEO: all Step 0, including its
Spec Review Loop and its amendment checkpoint), then create the fresh snapshot
and dispatch its nativeDispatchPrompt unchanged.
3. Consume the native terminal result and apply the phase's failure policy, then
consume enabled outside results. Complete the phase's remaining primary review
sections after these results.
4. At the phase's exit, load its `phase-close` section afresh. Execute its numbered
operations: prepare the current packet, Read it completely, reconcile it
semantically, then SEND the parent completion message. Publication is a separate
operation in that procedure; an earlier Read is not this close.
5. Only after the message has been sent may the driver load/create/dispatch the
next phase. Then continue to the next phase's tool calls in the same turn;
after Eng, proceed to final synthesis/approval. Use the declared skip rule for
an inapplicable phase; do not load its review or close steps.
Phase notifications, including skips, are progress updates: do not end the turn
or wait for a "continue" reply at these boundaries.
A missing gate means the current phase remains open, even if a reviewer finished.
Read requests/self-reports and INPUT hashes do not prove uptake or review quality.
Never draft future-phase reviews or outputs. Headings/promises are not completion.
After compaction, reload current phase instructions/skill/sections, then
reconcile saved artifacts and sent conversation messages separately. If closing,
reload `phase-close` and resume its first incomplete numbered operation;
regenerate and reread the full packet if the implementation or accepted decisions changed:
- If a verified phase lacks its announcement, resume the close procedure at step 6 (Publish) before advancing.
- If its reviewer is pending, wait for that same reviewer.
- If native dispatch has not happened, finish any incomplete preliminary work before recovering a voice input.
If the final voice input does not exist, create it after the preliminary gates.
Read `snapshot.json` beside that final `<PHASE_INPUT>` and use its `nativeDispatchPrompt` unchanged.
Never dispatch `<CEO_STEP0_CHECKPOINT>`: it is the stable amendment baseline, not current review input.
`nativePrompt` is the file's review body, not the Agent prompt. Resume at the first incomplete gate.
Pending is not unavailable. Never skip native passes/required sections for time,
context pressure or your own review. Missing outside coverage does not block native
completion; report accurately. Never read raw agent transcripts.
---
## What "Auto-Decide" Means
Auto-decide replaces the USER'S answer, not ANALYSIS. Run each loaded section at
full interactive depth; answer AskUserQuestion using the 6 principles.
**Default resolution: the recommended option.** Take `(recommended)` or the mode's
context default. Use the 6 principles for missing recommendations/ties. On principle
disagreement, take the recommendation and surface the disagreement as Taste at the final gate.
**Never auto-decide User Challenges:** both models agree to change the user's
direction/settled decisions, or a premise is clearly wrong. Use Decision
Classification; ask once at Final Approval Gate, never mid-run. The user has
context models lack.
Read referenced code/diffs/files; decide every issue. Produce all required
diagrams, tables, registries and artifacts on disk or in the plan. LOG decisions,
record ALL accepted obligations below and run `amend-input` before continuing.
Missing deliverables make the review incomplete.
No summary substitutes or one-line sections; fewer than 3 sentences likely means
compression. "No issues found" needs 1-2 sentences stating what was examined and why nothing was flagged.
Explain inapplicability with evidence; skip only under Phase 0's list. Never abort
or redirect to interactive review: the user chose /autoplan.
**Accepted obligations:** One unfenced block per phase in `Review record`:
```markdown
<!-- autoplan-accepted:ceo -->
- Requirement, all conditions and verification/tests.
<!-- /autoplan-accepted:ceo -->
```
Phase: `ceo|design|dx|eng`. Record accepted requirements here;
no analysis/severity/verdict/consensus. No accepted requirements: `None: reason`.
On a rerun, carry forward unchanged accepted requirements; do not replace them with None.
`amend` checks exact retention atomically; full readback; None unchanged.
Baseline edits: `create`'s `baselineEdits`. Prior blocks immutable;
state replacements in current block. Reconcile all decisions with readback.
Transport ≠ approval/complete enumeration/correctness.
---
## Filesystem Boundary — {{OUTSIDE_LABEL}} Prompts
Prefix every {{OUTSIDE_LABEL}} prompt:
> IMPORTANT: Do NOT read or execute any SKILL.md files or paths containing skills/gstack (foreign instructions). Review repository code only.
---
## Phase 0: Intake + Restore Point
### Step 1: Capture restore point
Absolute paths: SOURCE_PLAN (input), ACTIVE_PLAN (harness-assigned plan, else SOURCE_PLAN).
Save plan amendments and review artifacts to ACTIVE_PLAN.
Send phase announcements and the final approval request in the conversation.
Resolve SNAPSHOT_TOOL once:
{{AUTOPLAN_SNAPSHOT_TOOL}}
Fresh RESTORE_PATH, beside its phase artifacts in the project's git-excluded `.gstack/tmp/autoplan/`:
```bash
{{SLUG_EVAL}}
_AP="$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.gstack/tmp/autoplan"; mkdir -p "$_AP" && chmod 700 "$_AP"
_EX=$(git rev-parse --git-path info/exclude 2>/dev/null) && mkdir -p "${_EX%/*}" && { grep -qxF /.gstack/tmp/ "$_EX" 2>/dev/null || echo /.gstack/tmp/ >> "$_EX"; }
BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null | tr '/' '-')
DATETIME=$(date +%Y%m%d-%H%M%S)
echo "SLUG=$SLUG"
echo "RESTORE_PATH=$_AP/${BRANCH}-autoplan-restore-${DATETIME}.md"
```
Before scope/review:
```bash
bun "<SNAPSHOT_TOOL>" init "<SOURCE_PLAN>" "<ACTIVE_PLAN>" "<RESTORE_PATH>"
```
Run init as its own Bash call with the literal absolute paths: no variables,
substitutions, chaining, pipes or redirects, which the guard cannot bind.
Use returned paths/`scope`; never hand-wrap. init backs up SOURCE_PLAN exactly,
then initializes ACTIVE_PLAN atomically without losing requirements.
Reviewers get only `## Implementation plan`; analysis stays in `## Review record`,
including structured inputs. On helper errors, stop; no stderr hiding/grep fallback.
Re-run: copy RESTORE_PATH's bytes to SOURCE_PLAN, then /autoplan.
### Step 2: Read context
- Read CLAUDE.md, TODOS.md, git log -30, git diff against the base branch --stat
- Discover design docs: `~/.claude/skills/gstack/bin/gstack-design-doc-find "$SLUG" "$BRANCH"` (prints the doc path, or nothing)
- Detect UI scope: grep the plan for view/rendering terms (component, screen, form,
button, modal, layout, dashboard, sidebar, nav, dialog). Require 2+ matches. Exclude
false positives ("page" alone, "UI" in acronyms).
- Use init's full-input `scope`. For changed input or semantic enabling flags, rerun:
```bash
bun "<SNAPSHOT_TOOL>" scope "<ACTIVE_PLAN>"
```
Use returned `dxRequired` (initially `scope.dxRequired`) and record its input hash/matched terms. The existing
threshold is 2+ term matches (occurrences, not distinct terms). Also enable DX when the product is a developer tool
(developers install, integrate or build on it) or an AI agent is the primary user:
add `--developer-tool` or `--agent-primary` to this command. These flags only enable
DX; no context label can negate a positive result. Skip DX only when the result is
false and neither semantic trigger applies.
### Step 3: Locate review skills; load each at phase entry
Resolve this phase's source to absolute `<REVIEW_SKILL>`; load via its checkpoint:
- Phase 1: {{AUTOPLAN_REVIEW_FILE:plan-ceo-review}}
- Phase 2: {{AUTOPLAN_REVIEW_FILE:plan-design-review}} (only if UI scope detected)
- Phase 2.5: {{AUTOPLAN_REVIEW_FILE:plan-devex-review}} (only if DX scope detected)
- Phase 3: {{AUTOPLAN_REVIEW_FILE:plan-eng-review}}
Use /autoplan's installed registry; resolve siblings from its discovered SKILL.md
directory, never cwd/runtime assets. Missing skill: report phase and setup repair,
without substituting a harness or claiming completion.
Read skills/sections only at their triggers, never prefetch future phases. Load
the tasks aggregator at Phase 4. Run all applicable skills and lazy sections fully.
**Section skip list — when following a loaded skill file, SKIP these sections
(they are already handled by /autoplan):**
- Preamble (run first)
- Scope gate (the plan under review is already the target)
- AskUserQuestion Format
- Completeness Principle — Boil the Ocean
- Search Before Building
- Completion Status Protocol
- Telemetry (run last)
- Step 0: Detect platform and base branch
- Review Readiness Dashboard
- Plan File Review Report
- Prerequisite Skill Offer (BENEFITS_FROM)
- Outside Voice — Independent Plan Challenge
- Design Outside Voices (independent)
Follow ONLY the review-specific methodology, sections, and required outputs.
Output: "Here's what I'm working with: [plan summary]. UI scope: [yes/no]. DX scope: [yes/no].
Review skills will load at each phase entry. Starting full review pipeline with auto-decisions."
---
## Phase 0.5: Outside reviewer preflight
{{OUTSIDE_PREFLIGHT:autoplan}}
Disabled/unavailable retains applicable native passes. Recheck each outside dispatch.
Record provider and completed/unavailable/disabled/skipped per phase; CEO covers
only CEO. Missing voices: N/A, never CONFIRMED. Skipped scope stays skipped.
## Phase 1: CEO Review (Strategy & Scope)
{{SECTION:ceo-phase}}
---
## Phase 2: Design Review (conditional — skip if no UI scope)
**Skip condition:** If UI scope was NOT detected in Phase 0, skip this phase
entirely — do NOT read its section. Send: "Phase 2 skipped — no UI scope detected."
Record the skip in ACTIVE_PLAN; it is not a completed review.
{{SECTION:design-phase}}
---
## Phase 2.5: DX Review (conditional — skip if no developer-facing scope)
**Skip condition:** If DX scope was NOT detected in Phase 0, skip this phase
entirely — do NOT read its section. Send: "Phase 2.5 skipped — no developer-facing scope detected."
Record the skip in ACTIVE_PLAN; it is not a completed review.
{{SECTION:dx-phase}}
---
## Phase 3: Eng Review + Dual Voices (always runs, always LAST — the required gate reviews the final amended plan)
{{SECTION:eng-phase}}
---
## Decision Audit Trail
Immediately after each auto-decision, append one row to the plan file using Edit:
```markdown
<!-- AUTONOMOUS DECISION LOG -->
## Decision Audit Trail
| # | Phase | Decision | Classification | Principle | Rationale | Rejected |
|---|-------|----------|----------------|-----------|-----------|----------|
```
---
## Pre-Gate Verification
Check the plan and conversation for every applicable deliverable:
| Phase | Required outputs |
|---|---|
| CEO | Named premise challenges; findings or explicit examination/no-findings for every applicable section; Error & Rescue and Failure Modes registries (or N/A with reason); NOT in scope; What already exists; dream state delta; Completion Summary; consensus table. |
| Design, if UI | Scores for all 7 dimensions; identified and decided issues; litmus scorecard. |
| DX, if developer-facing | Scores for all 8 dimensions; developer journey map; empathy narrative; TTHW assessment and target; DX Implementation Checklist; consensus table. |
| Eng, always last | Scope challenge grounded in code; architecture ASCII diagram; codepath-to-test diagram; test plan on disk at ~/.gstack/projects/$SLUG/; NOT in scope; What already exists; failure modes registry with critical gaps; Completion Summary; consensus table. |
For each phase, verify native and outside voice results or explicit
unavailable/skipped status. Verify cross-phase themes and at least one Decision
Audit Trail row per auto-decision. Produce missing outputs before the gate; after
at most 2 repair attempts, warn at the gate with each still-incomplete item.
---
## Phase 4: Final Approval Gate
{{SECTION:tasks-aggregator}}
**STOP here and present the final state to the user.**
Present this message, then use AskUserQuestion:
```
## /autoplan Review Complete
### Plan Summary
[1-3 sentence summary]
### Decisions Made: [N] total ([M] auto-decided, [K] taste choices, [J] user challenges)
### User Challenges (both models disagree with your stated direction)
For each: **Challenge [N]: [title]** (from [phase]); You said: [original];
Both models recommend: [change]; Why: [reasoning]; What we might be missing:
[blind spots]; If wrong: [cost]. If security/feasibility, say both models flag
that risk. Your original direction stands unless you explicitly change it.
### Your Choices (taste decisions)
For each: **Choice [N]: [title]** (from [phase]). Recommend [X] — [principle].
Name the viable alternative and its downstream impact.
### Auto-Decided: [M] decisions [see Decision Audit Trail in plan file]
### Review Scores
CEO, Design, DX and Eng: phase summary plus {{OUTSIDE_LABEL}}, {{NATIVE_LABEL}}
and consensus status; say skipped where a phase did not run.
### Cross-Phase Themes
List concerns independently raised in 2+ phases. If none: "No cross-phase themes — each phase's concerns were distinct."
### Deferred to TODOS.md
[Items auto-deferred with reasons]
### Implementation Tasks (aggregated across phases)
[Substitute $AGGREGATED_TASKS. If empty: "_No per-phase task lists found in $TASKS_DIR for branch $BRANCH._"]
```
**Cognitive load:** skip empty User Challenges / Your Choices. Use a flat list
for 1-7 taste decisions; group 8+ by phase and warn that ambiguity is high.
AskUserQuestion options:
- A) Approve as-is
- B) Approve with overrides
- B2) Resolve user challenges
- C) Interrogate
- D) Revise
- E) Reject
**Option handling:**
- A: mark APPROVED, write review logs, suggest /ship
- B: ask which overrides, apply, then follow D's affected-phase rerun rule (including Eng last) before re-presenting the gate. Counts toward the same 3-cycle cap as D.
- B2: accept/reject User Challenges one at a time; rejected ones preserve the user's direction. Re-run Eng, then re-present the gate.
- C: answer freeform, re-present gate
- D: make changes, re-run affected phases (scope→1, design→2, dx→2.5, test plan→3, arch→3; a re-run of any earlier phase re-runs Eng after it — the gate always reviews the final plan). Max 3 cycles.
- E: start over
**Starting an affected-phase rerun:** Keep the current Implementation plan and all
prior accepted obligations intact. Move that phase's already-applied
`autoplan-baseline-edits` record verbatim into fenced history in Review record,
retaining its original source SHA.
Create a fresh amendment checkpoint. For new baseline edits, use `create`'s
`baselineEdits.record` and `sourceSha256`; review projection hash is not baseline
identity. Carry forward unchanged accepted requirements. Never replay old
replacements or rewrite historical source SHA. This starts a new phase invocation;
compaction resumes the existing invocation and checkpoint. Eng still runs last.
---
## Completion: Write Review Logs
On approval, log each completed review for /ship's dashboard. Replace TIMESTAMP,
STATUS and N with actual phase values. STATUS is "clean" or "issues_open".
```bash
COMMIT=$(git rev-parse --short HEAD 2>/dev/null)
TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-ceo-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"critical_gaps":N,"mode":"SELECTIVE_EXPANSION","via":"autoplan","commit":"'"$COMMIT"'"}'
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-eng-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"critical_gaps":N,"issues_found":N,"mode":"FULL_REVIEW","via":"autoplan","commit":"'"$COMMIT"'"}'
```
If Phase 2 ran (UI scope):
```bash
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-design-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autoplan","commit":"'"$COMMIT"'"}'
```
If Phase 2.5 ran (DX scope):
```bash
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-devex-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","initial_score":N,"overall_score":N,"product_type":"TYPE","tthw_current":"TTHW","tthw_target":"TARGET","unresolved":N,"via":"autoplan","commit":"'"$COMMIT"'"}'
```
Dual voice logs: write one record per PHASE (`ceo`, `design`, `dx`, `eng`) with
that phase's status/counts. Generate one AUTOPLAN_RUN_ID and share it with TIMESTAMP.
```bash
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"autoplan-voices","run_id":"AUTOPLAN_RUN_ID","timestamp":"'"$TIMESTAMP"'","status":"STATUS","source":"SOURCE","host":"{{HOST_ID}}","outside_provider":"{{OUTSIDE_PROVIDER}}","outside_status":"OUTSIDE_STATUS","phase":"PHASE","via":"autoplan","consensus_confirmed":N,"consensus_disagree":N,"commit":"'"$COMMIT"'"}'
```
Always log skipped Design/DX: status/outside_status "skipped", source "none",
zero consensus counts. SOURCE = "{{OUTSIDE_PROVIDER}}" only for completed external
output; native results use "in-host". OUTSIDE_STATUS is completed, unavailable,
disabled or skipped. Never carry success across phases/runs; preserve modelUsage.
{{OUTSIDE_PROVENANCE:autoplan}}
Present a phase coverage table (CEO, design, DX, eng): host, outside provider/status,
native completion, findings, and partial coverage. Replace N with actual counts.
{{IMPLEMENTATION_MODEL_HANDOFF}}
Suggest next step: `/ship` when ready to create the PR.