Make the autoplan docs say what lean and full runs actually load (GST-1985) (#4186)

* Make the autoplan docs say what lean and full runs actually load (GST-1985)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* Keep the autoplan description at its size pin and say when the eng checklist is sent

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

README.md

@@ -143,7 +143,7 @@ gstack is a process, not a collection of tools. The skills run in the order a sp
 
 **Think → Plan → Build → Review → Test → Ship → Reflect**
 
-Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-ceo-review` reads. `/autoplan`'s eng phase writes a test plan that `/qa` picks up. `/review` catches bugs that `/ship` verifies are fixed. Nothing falls through the cracks because every step knows what came before it.
+Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-ceo-review` reads. An interactive `/autoplan` run's eng phase writes a test plan that `/qa` picks up. `/review` catches bugs that `/ship` verifies are fixed. Nothing falls through the cracks because every step knows what came before it.
 
 | Skill | Your specialist | What they do |
 |-------|----------------|--------------|
@@ -180,7 +180,7 @@ Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-
 | `/browse` | **QA Engineer** | Give the agent eyes. Drives your [Aside](https://aside.com) browser first — your real sessions, real clicks, real screenshots — through deterministic `aside repl` scripts. No Aside? It falls back to gstack's own Chromium: real clicks, ~100ms per command, and `/open-gstack-browser` shows it headed with sidebar, anti-bot stealth, and auto model routing. Every other browser skill stands on it. |
 | `/scrape` | **Data Extractor** | Pull structured data off a web page — tables, lists, prices — in your Aside browser with the page's real logged-in state. On the fallback browser, `/skillify` turns the flow into a permanent browser-skill that runs in ~200ms next time. |
 | `/setup-browser-cookies` | **Session Manager** | Copy selected cookies from Chrome, Chromium, Brave, Edge, Windows-only Opera and Opera GX, or macOS-only Comet and Arc into gstack's bundled browser. Choose your profile and domains; copying and sign-in verification are separate. Only needed on the fallback path — Aside already has your sessions. |
-| `/autoplan` | **Review Pipeline** | One command, fully reviewed plan. Runs CEO → design → DX → eng review automatically (eng always last, so the shipping gate reviews the final amended plan) with encoded decision principles. Surfaces only taste decisions for your approval. |
+| `/autoplan` | **Review Pipeline** | One command, reviewed plan. In an interactive session it runs CEO → design → DX → eng review from each skill's own method (eng always last, so the shipping gate reviews the final amended plan) with encoded decision principles, and surfaces only taste decisions for your approval. A run driven by `gstack-autoplan` (the Capy default) gives its reviewers short checklists instead of those methods: the lean run is one reviewer, `--full` one per phase ([what each run loads](docs/skills.md#what-each-run-loads)). |
 | `/spec` | **Spec Author** | Turn vague intent into a precise, executable spec in five phases (why, scope, technical with mandatory code-reading, draft, file). Outside-review quality gate before filing (Claude Code on Codex; Codex on other harnesses; blocks below 7/10), fail-closed secret redaction, dedupe against existing issues, archive to `$GSTACK_STATE_ROOT/projects/$SLUG/specs/` for team-corpus recall. `--execute` spawns `claude -p` in a fresh worktree; `/ship` auto-closes the source issue on merge. Plan-mode aware. |
 | `/learn` | **Memory** | Manage what gstack learned across sessions. Review, search, prune, and export project-specific patterns, pitfalls, and preferences. Learnings compound across sessions so gstack gets smarter on your codebase over time. |
 | `/make-pdf` | **Publisher** | Markdown in, publication-quality document out. Mermaid and excalidraw fences render as vector diagrams, fully offline. Images scale to the page and never truncate; wide diagrams get their own landscape page. `--to html` emits one self-contained file, `--to docx` a Word doc. |

autoplan/DRIVER.md

@@ -20,7 +20,7 @@ The first `next` prints `SCOPE: ui=… (terms; visual; files) dx=… (detected)
 TODOS*, docs/** but not docs/*-policy.md, or other markdown outside a skill dir) runs CEO on the native voice only, then Eng. UI needs a rendered file path (including a named non-test `.ts`/`.js` file that holds a tagged `html`, `css` or `svg` template, such as Lit or htm) or a UI term next
 to a visual noun in the Implementation plan. To keep flags for later runs on the same plan, add
 the `SCOPE_PIN:` marker it prints (`<!-- gstack-autoplan-scope: … -->`) as the plan's first
-line yourself; gstack never writes the plan. **Kinds (R65), first `next` only.** `--kind fix` reviews nothing: it prints `AUTOPLAN: not needed (bug fix; R65)`, a `PROOF:` line and `GSTACK_RESULT: skill=autoplan status=skipped run=-`, writes nothing and needs no `--out` or `--plan`; the PR still carries the bug's proof, a repro on current main or a failing test written first. `--kind feature`, the default for an unattended run on Capy (`GSTACK_CAPY=1`) that names no kind, is the lean run. Its `phase_order` is `eng` alone with one native reviewer, whose prompt merges the CEO and Eng lenses (Design or DX only when scope detects them), always asks "Any outside terms, licences or rights involved?" and shows the draft code. The draft is `git diff` from the merge base with `--base <ref>` (default: `gstack-diff-scope`'s base, never an `origin/HEAD` naming the checked-out branch), untracked files included and the run directory left out, written to the snapshot as `draft.diff` and hashed; with no code yet it says `DRAFT: none (<why>)`. The first `next` prints `LEAN:` and each opened phase `DRAFT:`; the reviewer's line after INPUT must be `DRAFT: <sha256>` or `DRAFT: none`, or submit refuses it (`RESULT_RECEIPT_MISSING`). No outside voice, `--max-rounds 1`, no carry check and one gate revision: `revise --incorporates` applies the accepted changes without re-review and approves. `--full` brings back every phase and both voices; off Capy, and in an interactive session, the default stays full.
+line yourself; gstack never writes the plan. **Kinds (R65), first `next` only.** `--kind fix` reviews nothing: it prints `AUTOPLAN: not needed (bug fix; R65)`, a `PROOF:` line and `GSTACK_RESULT: skill=autoplan status=skipped run=-`, writes nothing and needs no `--out` or `--plan`; the PR still carries the bug's proof, a repro on current main or a failing test written first. `--kind feature`, the default for an unattended run on Capy (`GSTACK_CAPY=1`) that names no kind, is the lean run. Its `phase_order` is `eng` alone with one native reviewer, whose prompt merges the CEO and Eng lenses (Design or DX only when scope detects them), each a short role or brief plus that review skill's checklist, never the skill's own method, always asks "Any outside terms, licences or rights involved?" and shows the draft code. The draft is `git diff` from the merge base with `--base <ref>` (default: `gstack-diff-scope`'s base, never an `origin/HEAD` naming the checked-out branch), untracked files included and the run directory left out, written to the snapshot as `draft.diff` and hashed; with no code yet it says `DRAFT: none (<why>)`. The first `next` prints `LEAN:` and each opened phase `DRAFT:`; the reviewer's line after INPUT must be `DRAFT: <sha256>` or `DRAFT: none`, or submit refuses it (`RESULT_RECEIPT_MISSING`). No outside voice, `--max-rounds 1`, no carry check and one gate revision: `revise --incorporates` applies the accepted changes without re-review and approves. `--full` brings back every phase and both voices: each native reviewer gets a five-question brief and its phase's checklist, each outside reviewer a one-paragraph role, and neither the skill's own method. Off Capy, and in an interactive session, the default stays full.
 
 ## The loop
 

autoplan/DRIVER.md.tmpl

@@ -17,7 +17,7 @@ The first `next` prints `SCOPE: ui=… (terms; visual; files) dx=… (detected)
 TODOS*, docs/** but not docs/*-policy.md, or other markdown outside a skill dir) runs CEO on the native voice only, then Eng. UI needs a rendered file path (including a named non-test `.ts`/`.js` file that holds a tagged `html`, `css` or `svg` template, such as Lit or htm) or a UI term next
 to a visual noun in the Implementation plan. To keep flags for later runs on the same plan, add
 the `SCOPE_PIN:` marker it prints (`<!-- gstack-autoplan-scope: … -->`) as the plan's first
-line yourself; gstack never writes the plan. **Kinds (R65), first `next` only.** `--kind fix` reviews nothing: it prints `AUTOPLAN: not needed (bug fix; R65)`, a `PROOF:` line and `GSTACK_RESULT: skill=autoplan status=skipped run=-`, writes nothing and needs no `--out` or `--plan`; the PR still carries the bug's proof, a repro on current main or a failing test written first. `--kind feature`, the default for an unattended run on Capy (`GSTACK_CAPY=1`) that names no kind, is the lean run. Its `phase_order` is `eng` alone with one native reviewer, whose prompt merges the CEO and Eng lenses (Design or DX only when scope detects them), always asks "Any outside terms, licences or rights involved?" and shows the draft code. The draft is `git diff` from the merge base with `--base <ref>` (default: `gstack-diff-scope`'s base, never an `origin/HEAD` naming the checked-out branch), untracked files included and the run directory left out, written to the snapshot as `draft.diff` and hashed; with no code yet it says `DRAFT: none (<why>)`. The first `next` prints `LEAN:` and each opened phase `DRAFT:`; the reviewer's line after INPUT must be `DRAFT: <sha256>` or `DRAFT: none`, or submit refuses it (`RESULT_RECEIPT_MISSING`). No outside voice, `--max-rounds 1`, no carry check and one gate revision: `revise --incorporates` applies the accepted changes without re-review and approves. `--full` brings back every phase and both voices; off Capy, and in an interactive session, the default stays full.
+line yourself; gstack never writes the plan. **Kinds (R65), first `next` only.** `--kind fix` reviews nothing: it prints `AUTOPLAN: not needed (bug fix; R65)`, a `PROOF:` line and `GSTACK_RESULT: skill=autoplan status=skipped run=-`, writes nothing and needs no `--out` or `--plan`; the PR still carries the bug's proof, a repro on current main or a failing test written first. `--kind feature`, the default for an unattended run on Capy (`GSTACK_CAPY=1`) that names no kind, is the lean run. Its `phase_order` is `eng` alone with one native reviewer, whose prompt merges the CEO and Eng lenses (Design or DX only when scope detects them), each a short role or brief plus that review skill's checklist, never the skill's own method, always asks "Any outside terms, licences or rights involved?" and shows the draft code. The draft is `git diff` from the merge base with `--base <ref>` (default: `gstack-diff-scope`'s base, never an `origin/HEAD` naming the checked-out branch), untracked files included and the run directory left out, written to the snapshot as `draft.diff` and hashed; with no code yet it says `DRAFT: none (<why>)`. The first `next` prints `LEAN:` and each opened phase `DRAFT:`; the reviewer's line after INPUT must be `DRAFT: <sha256>` or `DRAFT: none`, or submit refuses it (`RESULT_RECEIPT_MISSING`). No outside voice, `--max-rounds 1`, no carry check and one gate revision: `revise --incorporates` applies the accepted changes without re-review and approves. `--full` brings back every phase and both voices: each native reviewer gets a five-question brief and its phase's checklist, each outside reviewer a one-paragraph role, and neither the skill's own method. Off Capy, and in an interactive session, the default stays full.
 
 ## The loop
 

autoplan/SKILL.md

@@ -2,7 +2,7 @@
 name: autoplan
 preamble-tier: 3
 version: 1.0.0
-description: Auto-review pipeline — runs the CEO, design, eng (architecture, edge cases, failure modes, tests) and DX reviews in order, auto-deciding by 6 principles. (gstack)
+description: "Auto-review pipeline — runs the CEO, design, eng (architecture, edge cases, failure modes, tests) and DX reviews (lean run: one reviewer), auto-deciding. (gstack)"
 triggers:
   - run all reviews
   - automatic review pipeline

autoplan/SKILL.md.tmpl

@@ -4,7 +4,7 @@ preamble-tier: 3
 version: 1.0.0
 description: |
   Auto-review pipeline — runs the CEO, design, eng (architecture, edge cases, failure
-  modes, tests) and DX reviews in order, auto-deciding by 6 principles. Surfaces
+  modes, tests) and DX reviews (lean run: one reviewer), auto-deciding. Surfaces
   taste decisions (close approaches, borderline scope, outside-review disagreements) at
   one approval gate. Use when asked to "auto review", "autoplan", "run all reviews",
   "review this plan automatically", "review the architecture", "engineering review", or

autoplan/sections/unattended.md

@@ -5,7 +5,7 @@
 `SESSION_KIND: unattended`: a parent drives the run through
 `~/.claude/skills/gstack/bin/gstack-autoplan` (`next`/`submit`/`answer --gate-rev`/
 `export`; docs/unattended.md) and reads artifacts, never prose. Phases close
-themselves, Eng runs last, the outside voice runs through `gstack-outside-voice`,
+themselves, Eng runs last, the outside voice (none when lean) runs through `gstack-outside-voice`,
 and the run stops at `status=gate_pending`: never approve. `gstack-artifact
 validate <dir>/run.json` is the completion check. End with
 `GSTACK_RESULT: skill=autoplan status=<status> run=<dir>`.

autoplan/sections/unattended.md.tmpl

@@ -3,7 +3,7 @@
 `SESSION_KIND: unattended`: a parent drives the run through
 `~/.claude/skills/gstack/bin/gstack-autoplan` (`next`/`submit`/`answer --gate-rev`/
 `export`; docs/unattended.md) and reads artifacts, never prose. Phases close
-themselves, Eng runs last, the outside voice runs through `gstack-outside-voice`,
+themselves, Eng runs last, the outside voice (none when lean) runs through `gstack-outside-voice`,
 and the run stops at `status=gate_pending`: never approve. `gstack-artifact
 validate <dir>/run.json` is the completion check. End with
 `GSTACK_RESULT: skill=autoplan status=<status> run=<dir>`.

bin/gstack-autoplan

@@ -77,7 +77,7 @@ DRIVER: ${driverFile()}
           --ceo-only (first next, command line only): the CEO phase alone, no gate; ends status=reviewed with <out>/ceo-review.md, never approved
           --estimate-usd: reserved per new attempt, kept for the rest of the run; with --spend-cap any run (or an unattended run on Capy) reserves a default so the cap binds
           --scaffold (first next): a plan missing one of its two sections is reviewed from <out>/plan-source.md with the heading added
-          --light loads each phase's checklist plus the sections its scope needs (the unattended default); interactive kinds load everything
+          --light puts each phase's checklist in its native prompt (the unattended default); other sections are only recorded, never sent; without it an interactive kind sends no checklist
           --no-carry-forward (first next): every later gate revision goes to the owner, even one that asks nothing new
           --carry-check-cap <usd> (first next): the most one delta check may reserve before a carry (default ${DEFAULT_CARRY_CHECK_CAP_USD.toFixed(2)})
           the first next prints REVIEW_ESTIMATE: the most the review can reserve at this scope and round cap

changelog.d/autoplan-docs-say-what-lean-and-full-runs-load.md

@@ -0,0 +1 @@
+- **The /autoplan docs now say what each kind of run actually gives its reviewers.** README.md, docs/skills.md, docs/unattended.md, autoplan/DRIVER.md, crew/docs/captain.md, the skill's description and the `gstack-autoplan --help` text described a full-depth, two-voice review for every run. That is true only of an interactive session, where the model reads each review skill's own method. The lean run (the Capy default) is one engineering reviewer whose prompt holds the eng brief and short CEO, eng, design and DX checklists (28 to 37 lines each), never those skills' methods, with no outside voice. A `--full` run has a reviewer pair per phase, each with a short brief, plus the checklist for the native one. docs/skills.md has a new "What each run loads" section. No runner behavior, prompt, mode or default changed (GEVA-412, GST-1985).

crew/docs/captain.md

@@ -282,8 +282,11 @@ from a problem list that was already diagnosed and audited, where that list is t
 Any other bug fix is exempt too (R65; the brief's reason is `bug fix (R65)`): `gstack-autoplan next --kind fix` prints
 `AUTOPLAN: not needed (bug fix; R65)` and writes nothing, and the PR carries the bug's
 proof, a repro on current main or a failing test written first. A feature gets the lean
-run, `--kind feature`: one reviewer reading the plan and the draft code together, one gate
-revision and no carry check (docs/unattended.md). `--full` brings back the full run.
+run, `--kind feature`: one reviewer reading the plan and the draft code together against
+short CEO and eng checklists (design and DX when scope has them), not those review skills'
+own methods, one gate revision and no carry check (docs/unattended.md). `--full` brings
+back a phase per area with two voices, each still working from a short brief (the native
+one also gets that phase's checklist).
 A crew may add exemptions
 in its rules file with the owner's words and date; it does not remove these. The brief
 says which applies, `Plan: required | approved: <run id or approval row id> | exempt: <reason>`, so an

docs/skills.md

@@ -32,7 +32,7 @@ Detailed guides for every gstack skill — philosophy, workflow, and examples.
 | [`/retro`](#retro) | **Eng Manager** | Team-aware weekly retro. Per-person breakdowns, shipping streaks, test health trends, growth opportunities. |
 | [`/browse`](#browse) | **QA Engineer** | Give the agent eyes. Drives your Aside browser first — real sessions, real clicks, real screenshots — through deterministic `aside repl` scripts, and falls back to gstack's own Chromium (~100ms per command) when Aside isn't there. |
 | [`/setup-browser-cookies`](#setup-browser-cookies) | **Session Manager** | Copy selected cookies from Chrome, Chromium, Brave, Edge, Windows-only Opera and Opera GX, or macOS-only Comet and Arc into the fallback browser. Choose your profile and domains; check sign-in separately. Unnecessary on Aside, which already has your sessions. |
-| [`/autoplan`](#autoplan) | **Review Pipeline** | One command, fully reviewed plan. Runs CEO → design → DX → eng review automatically (eng always last, so the shipping gate reviews the final amended plan) with encoded decision principles. Surfaces only taste decisions for your approval. |
+| [`/autoplan`](#autoplan) | **Review Pipeline** | One command, reviewed plan. In an interactive session it runs CEO → design → DX → eng review from each skill's own method (eng always last, so the shipping gate reviews the final amended plan) with encoded decision principles, and surfaces only taste decisions for your approval. A run driven by `gstack-autoplan` (the Capy default) gives its reviewers short checklists instead of those methods: the lean run is one reviewer, `--full` one per phase ([what each run loads](#what-each-run-loads)). |
 | [`/plan-devex-review`](#plan-devex-review) | **DX Reviewer** | Plan-stage DX review. TTHW (time-to-hello-world), magical moments, friction points, persona traces, and error messages scored for the agents that read them ([agent-ready errors](agent-ready-errors.md)). Three modes: Expansion, Polish, Triage. |
 | [`/devex-review`](#devex-review) | **DX Reviewer (live)** | Live developer experience audit. Walks the actual onboarding flow, measures TTHW, catches the docs lies, and triggers CLI errors the way an agent meets them (no terminal, contained, redacted) through `gstack-error-capture`. |
 | [`/plan-tune`](#plan-tune) | **Question Tuner** | Self-tune AskUserQuestion sensitivity per question. Mark questions as never-ask, always-ask, or only-for-one-way. |
@@ -187,7 +187,7 @@ Visions and decisions are persisted to `~/.gstack/projects/` so they survive bey
 
 `/plan-eng-review` was cut on 2026-11-06 (GST-1698) after two evals found no gain. In the seeded-flaw panel, plain Opus 5.5 with no gstack found the planted engineering flaws in 15 of 16 reviews. In the wave 1 outcome test, plain Opus 5.5 built 22 of 22 planned features correctly, and a session told to use the skill cost 7.1 times a plain one. The evidence is in GST-1218 and gstack-evals#253.
 
-The standalone skill no longer installs, and `./setup` removes an existing gstack-owned `/plan-eng-review` entry on every host. Its review methodology stays as `/autoplan`'s eng phase (Phase 3), unchanged. To review a plan's architecture, data flow, edge cases and tests, run `/autoplan`. `/review` covers the diff before `/ship`.
+The standalone skill no longer installs, and `./setup` removes an existing gstack-owned `/plan-eng-review` entry on every host. Its review methodology stays as `/autoplan`'s eng phase (Phase 3), unchanged, in an interactive session. A run driven by `gstack-autoplan` (the Capy default) gives its reviewer only the skill's 36-line checklist, not the methodology. To review a plan's architecture, data flow, edge cases and tests, run `/autoplan`. `/review` covers the diff before `/ship`.
 
 ### Review Readiness Dashboard
 
@@ -1241,7 +1241,7 @@ This is my **review autopilot mode**.
 
 Running `/plan-ceo-review`, `/plan-design-review` and `/plan-devex-review` individually means answering 15-30 intermediate questions. Each question is valuable, but sometimes you want the gauntlet to run without stopping for every decision.
 
-`/autoplan` reads the review skills from disk and runs them sequentially: CEO → Design (if UI scope) → DX (if developer-facing scope) → Eng, always last — the required shipping gate reviews the final amended plan, not a stale one. It makes decisions automatically: each question resolves to its recommended option by default, with six encoded principles (prefer completeness, match existing patterns, choose reversible options, prefer the option the user chose for similar past decisions, defer ambiguous items, and escalate security) breaking ties and deciding questions that carry no recommendation. Taste decisions (close approaches, borderline scope expansions, cross-model disagreements) get saved and presented at a final approval gate.
+In an interactive session, `/autoplan` reads the review skills from disk and runs them sequentially: CEO → Design (if UI scope) → DX (if developer-facing scope) → Eng, always last — the required shipping gate reviews the final amended plan, not a stale one. It makes decisions automatically: each question resolves to its recommended option by default, with six encoded principles (prefer completeness, match existing patterns, choose reversible options, prefer the option the user chose for similar past decisions, defer ambiguous items, and escalate security) breaking ties and deciding questions that carry no recommendation. Taste decisions (close approaches, borderline scope expansions, cross-model disagreements) get saved and presented at a final approval gate.
 
 One command, fully reviewed plan out.
 
@@ -1263,6 +1263,16 @@ You:    1) Yes, add search. 2) Option A.
 Claude: Plan complete. 9 decisions auto-resolved, 2 taste decisions approved.
 ```
 
+### What each run loads
+
+How deep the review goes depends on who drives the run.
+
+- **Interactive session** (no parent agent): the session model reads each phase's review skill, its SKILL.md and review sections, and works through that method itself. Each phase also sends the plan to a native reviewer subagent, which gets a five-question brief but not the skill, and to an outside voice from another model family (Codex) when one is available.
+- **Lean run** (`--kind feature`, the default for an unattended run on Capy): one engineering reviewer and nothing else. Its prompt holds the five-question eng brief, the 36-line eng checklist (unattended or `--light` runs only), a one-paragraph CEO role with the 37-line CEO checklist, the 28-line design and 34-line DX checklists only when scope detects UI or developer-facing work, and the draft code. It does not run the CEO, design or DX skills' own methods. There is no outside voice and one round.
+- **Full run** (`--full`, and the default for an unattended run off Capy): a phase per area, CEO → design → DX → eng, each with two voices. The native reviewer gets the five-question brief, the plan and, in an unattended or `--light` run, that phase's checklist; the outside reviewer gets a one-paragraph role and the plan. Neither gets the review skill's own method.
+
+The lean and full kinds are runs a parent agent drives through `gstack-autoplan` ([autoplan/DRIVER.md](../autoplan/DRIVER.md), [unattended.md](unattended.md)). An interactive session that sees `SESSION_KIND: unattended` hands off to the same runner.
+
 ---
 
 ## `/learn`

docs/unattended.md

@@ -441,7 +441,12 @@ The example above is the full run. The first `next` also takes `--kind`:
   (`GSTACK_CAPY=1`) that names no kind, is the lean run. The run is the `eng`
   phase alone with one native reviewer, whose prompt merges the CEO and Eng
   lenses (Design and DX only when scope detects them) and always asks "Any
-  outside terms, licences or rights involved?". The reviewer reads the draft
+  outside terms, licences or rights involved?". Each lens is short: the eng
+  lens is a five-question brief plus plan-eng-review's 36-line checklist when
+  the run is unattended or `--light`, the
+  others a one-paragraph role and that skill's checklist (CEO 37 lines, design
+  28, DX 34). The reviewer never gets those skills' own methods
+  (`lib/autoplan-lean.ts` `leanPrompt`). The reviewer reads the draft
   code with the plan: `git diff` from the merge base with `--base <ref>`
   (default `origin/HEAD`), untracked files included and the run directory
   left out, written into the phase's snapshot directory as `draft.diff` and
@@ -471,7 +476,11 @@ The example above is the full run. The first `next` also takes `--kind`:
   without re-review (`APPLIED: … (lean run: one gate revision; …)`) and
   approves. The gate and `gstack-owner-brief render --captain` relay work as
   in the full run. A paid-eval prereg counts as a feature.
-- **`--full`** restores every phase and both voices. Off Capy, and in an
+- **`--full`** restores every phase and both voices. Each phase's native
+  reviewer gets a five-question brief, the plan and that phase's checklist
+  (`--light`, the unattended default); the outside reviewer gets a
+  one-paragraph role and the plan. Neither gets the review skill's own
+  method, which only an interactive `/autoplan` session reads. Off Capy, and in an
   interactive session, the default stays full; `--ceo-only` stays its own run.
 
 1. **Dispatch each `ATTEMPT:`.** The native voice is a subagent on the parent's

gstack/llms.txt

@@ -10,7 +10,7 @@ Conventions:
 
 ## Skills
 
-- [/autoplan](autoplan/SKILL.md): Auto-review pipeline — runs the CEO, design, eng (architecture, edge cases, failure modes, tests) and DX reviews in order, auto-deciding by 6 principles.
+- [/autoplan](autoplan/SKILL.md): Auto-review pipeline — runs the CEO, design, eng (architecture, edge cases, failure modes, tests) and DX reviews (lean run: one reviewer), auto-deciding.
 - [/benchmark](benchmark/SKILL.md): Web performance regression detection.
 - [/benchmark-models](benchmark-models/SKILL.md): Cross-model benchmark for gstack skills.
 - [/browse](browse/SKILL.md): Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors.