diff --git a/.gitignore b/.gitignore
index 9e413bc56b..6bc45e7e6c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -37,3 +37,6 @@ supabase/.temp/
 
 # Throughput analysis — local-only, regenerate via scripts/garry-output-comparison.ts
 docs/throughput-*.json
+
+# gstack preamble feature-discovery state markers (written via dev symlink)
+.feature-prompted-*
diff --git a/AGENTS.md b/AGENTS.md
index c1e5595fc5..6ea9206640 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -57,6 +57,7 @@ Invoke them by name (e.g., `/office-hours`).
 | `/context-save` | Save working context (git state, decisions, remaining work). |
 | `/context-restore` | Resume from a saved context, even across Conductor workspaces. |
 | `/learn` | Manage what gstack learned across sessions. |
+| `/plan-status` | Check progress of a plan against the codebase and git log. Phase-by-phase DONE/PARTIAL/REMAINING dashboard. |
 | `/retro` | Weekly retro with per-person breakdowns and shipping streaks. |
 | `/health` | Code quality dashboard (type checker, linter, tests, dead code). |
 | `/benchmark` | Performance regression detection (page load, Core Web Vitals). |
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 937e67e37f..83fc41cb53 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,54 @@
 # Changelog
 
+## [1.34.0.0] - 2026-05-11
+
+## **`/plan-status` ships. Ask "where am I on this plan?" and get an answer in seconds.**
+## **`/ship` now warns before creating a PR if the plan has open checkboxes.**
+
+Plans have always been written by gstack. Now gstack can tell you how far along you are. `/plan-status` reads the plan that already exists, cross-references git commits and filesystem state, and produces a dashboard: a gstack Lifecycle Dashboard (which workflow skills have run, matching the Review Readiness Dashboard format) plus a phase-by-phase DONE/PARTIAL/REMAINING breakdown with a Branch Commits table. No setup, no ticket creation, no pre-registration of work. The plan is already there. The git history is already there. The skill just cross-references them.
+
+As a side effect, `/ship`'s Step 1 pre-flight now runs a 3-second open-checkbox grep. If the current branch's plan has unchecked `- [ ]` items, it surfaces an informational note before PR creation. You decide whether to proceed or check `/plan-status` first. Never blocks.
+
+### The numbers that matter
+
+Measured against v1.32.0.0 on the `plan-status-skill` branch. No external API calls, no new dependencies.
+
+| Metric | v1.32.0.0 | v1.33.0.0 | Δ |
+|---|---|---|---|
+| Skills | 40 | 41 | **+1** |
+| Gate-tier E2E tests | (prior count) | +1 | **+1** |
+| Free (Tier 1) tests | 400 | 400 | 0 |
+| SKILL.md files | 40 | 41 | **+1** |
+| LOC added (skill + test + fixture + docs) | — | ~280 | — |
+
+The `/plan-status` preamble runs in ~10s typical (gstack-update-check + gstack-slug + plan find + git log + analytics write). Evidence gathering is O(n) on file references in the plan, typically 5-20 files, 5-15 seconds. Total expected runtime: 15-40 seconds — consistent with `/learn` and `/canary`.
+
+### What this means for you
+
+If you've run `/office-hours` or `/plan-ceo-review`, you have a plan file. Run `/plan-status` on your feature branch and get a scannable dashboard in under a minute. No setup. The skill finds your plan from `~/.gstack/projects/<project>/ceo-plans/` automatically.
+
+For non-code projects (board planning, grant pipelines, accreditation prep): set `gstack-config set plan_glob "~/board-plans/*.md"` to point the skill at any folder of markdown plan files.
+
+### Itemized changes
+
+#### Added
+
+- **`/plan-status` skill** (`plan-status/SKILL.md.tmpl` + generated `SKILL.md`). Five-step flow: resolve plan file → extract phases and success-criteria checkboxes → gather git and filesystem evidence → classify DONE/PARTIAL/REMAINING/DROPPED → produce gstack Lifecycle Dashboard + Plan Detail report. Evidence sources for v1: `git log`, `git diff --name-only`, filesystem `ls`, `Gemfile` grep. All read-only. Optional `plan_glob` knob (`gstack-config set plan_glob "~/your-plans/*.md"`) for non-default plan directories.
+- **`test/fixtures/plans/sample-ruby-llm-plan.md`** — fixture plan for the E2E test (2 phases, 4 checkboxes, 2 file refs, 1 gem ref).
+- **`test/skill-e2e-plan-status.test.ts`** — gate-tier E2E test. Loose assertions: transcript contains "Plan Status" and at least one of "DONE" or "REMAINING". Classified `gate` because it's deterministic, read-only, filesystem-only fixture, < $0.50/run.
+- **`TODOS.md`** — added entry to monitor GitHub issue #1343 for maintainer response to community asks about non-code evidence sources.
+
+#### Changed
+
+- **`/ship` Step 1 pre-flight** (`ship/SKILL.md.tmpl`) — new item 5: 3-second bash grep checks for open `- [ ]` checkboxes in the current branch's plan file. Informational only, never blocks. Suggests running `/plan-status` if open items are found.
+- **`docs/skills.md`** — added `/plan-status` skill description and full section.
+- **`AGENTS.md`** — added `/plan-status` row.
+
+#### For contributors
+
+- `test/helpers/touchfiles.ts`: new entry `'plan-status': ['plan-status/**', 'test/fixtures/plans/sample-ruby-llm-plan.md']` in `E2E_TOUCHFILES` and `'plan-status': 'gate'` in `E2E_TIERS`.
+- Ship golden baselines (`test/fixtures/golden/`) regenerated to include the new pre-flight step 5.
+
 ## [1.33.2.0] - 2026-05-11
 
 ## **`./setup` no longer pollutes the global install when run from a Conductor worktree.**
@@ -155,6 +204,7 @@ If you've been hitting the 35-minute hang on `/sync-gbrain`, it's gone. The arch
 - `TODOS.md` filed P2: investigate `gbrain import` perf on large staging dirs (5,131 files takes >10 minutes when 501 takes 10 seconds — gbrain-side N+1 SQL or auto-link reconciliation suspected). P3: cache "no changes since last import" at the prepare-batch level for true no-op fast paths.
 - `Plan completion audit` ran via subagent on this branch: 17/21 DONE, 1 CHANGED (D3 made opt-in), 2 deferred (F8 benchmark harness as separate work, 24-path unit coverage went integration-only).
 
+
 ## [1.32.0.0] - 2026-05-10
 
 ## **Seven contributor PRs land. Three are security or hardening.**
diff --git a/TODOS.md b/TODOS.md
index 0516f972e1..a25344680b 100644
--- a/TODOS.md
+++ b/TODOS.md
@@ -1,5 +1,15 @@
 # TODOS
 
+## plan-status follow-on
+
+### P3: Monitor issue #1343 for community asks
+
+Check whether @wwybdd23-bot has replied to our clarifying questions on GitHub issue #1343 (non-code plan evidence: calendar, email, external services). If the maintainer engages, design an extensible evidence-source plugin interface before implementing. Scope for that work belongs in a separate PR, not this one.
+
+**Priority:** P3 (monitor only — no implementation until maintainer decision)
+
+---
+
 ## /sync-gbrain memory stage perf follow-up
 
 ### P2: Investigate `gbrain import` perf on large staging dirs
diff --git a/VERSION b/VERSION
index 0df2c524d3..41efb235e3 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.33.2.0
+1.34.0.0
diff --git a/docs/skills.md b/docs/skills.md
index b20bf665d1..50344ffc5e 100644
--- a/docs/skills.md
+++ b/docs/skills.md
@@ -32,6 +32,7 @@ Detailed guides for every gstack skill — philosophy, workflow, and examples.
 | [`/devex-review`](#devex-review) | **DX Reviewer (live)** | Live developer experience audit. Walks the actual onboarding flow, measures TTHW, catches the docs lies. |
 | [`/plan-tune`](#plan-tune) | **Question Tuner** | Self-tune AskUserQuestion sensitivity per question. Mark questions as never-ask, always-ask, or only-for-one-way. |
 | [`/learn`](#learn) | **Memory** | Manage what gstack learned across sessions. Review, search, prune, and export project-specific patterns and preferences. |
+| [`/plan-status`](#plan-status) | **Plan Status** | Check progress of a gstack plan against the codebase and git log. Phase-by-phase DONE/PARTIAL/REMAINING dashboard. gstack Lifecycle Dashboard shows which workflow skills have run. |
 | [`/context-save`](#context-save) | **Save State** | Save working context (git state, decisions, remaining work) so any future session can resume. |
 | [`/context-restore`](#context-restore) | **Restore State** | Resume from a saved context, even across Conductor workspace handoffs. |
 | [`/health`](#health) | **Code Quality Dashboard** | Wraps type checker, linter, tests, dead code detection. Computes a weighted 0-10 score; tracks trends over time. |
@@ -969,6 +970,51 @@ Claude: 23 learnings for this project (14 high confidence, 6 medium, 3 low)
 
 ---
 
+## `/plan-status`
+
+This is my **progress dashboard** for any gstack plan.
+
+After `/office-hours` or `/plan-ceo-review` writes a plan, implementation starts — and there's no way to answer "where am I?" without manually re-reading the whole plan and cross-referencing the codebase. `/plan-status` closes that gap. It reads the plan that already exists, cross-references evidence from git and the filesystem, and produces a scannable dashboard in seconds. No setup. No ticket creation.
+
+The output has two parts: a **gstack Lifecycle Dashboard** showing which workflow skills have run (matching the same format as the Review Readiness Dashboard), and a **Plan Detail** section with per-phase and per-criteria DONE/PARTIAL/REMAINING classification.
+
+```
+You:   /plan-status
+
+Claude: ## gstack Lifecycle Dashboard
+        +====================================================================================+
+        |                         GSTACK LIFECYCLE DASHBOARD                                 |
+        +====================================================================================+
+        | Phase    | Skill               | Runs | Last Run         | Status   | Required    |
+        |----------|---------------------|------|------------------|----------|-------------|
+        | Think    | /office-hours       |  1   | 2026-05-11 22:00 | DONE     | no          |
+        | Plan     | /plan-ceo-review    |  1   | 2026-05-11 22:00 | DONE     | no          |
+        |          | /plan-eng-review    |  0   | —                | —        | YES         |
+        | Build    | (commits)           |  4   | —                | DONE     | YES         |
+        ...
+        +------------------------------------------------------------------------------------+
+        | VERDICT: IN PROGRESS — 1 required skill REMAINING (plan-eng-review)                |
+        +====================================================================================+
+
+        ## Plan Status: 2026-05-11-migrate-to-ruby-llm.md
+        Branch: migrate-to-ruby-llm | As of: 2026-05-11
+
+        ### Phase Summary
+        | Phase | Status | Notes |
+        |-------|--------|-------|
+        | Phase 0: Foundation | DONE | Gems added, initializer present |
+        | Phase 1: Schema Migration | REMAINING | No migration files found |
+
+        ### Summary
+        1 of 2 phases complete. 2 of 4 success criteria met.
+        Key blockers: langchainrb still in Gemfile, no db/migrate/ files
+        Suggested next action: Run /plan-eng-review, then write the schema migration.
+```
+
+Configure a custom plan search path: `gstack-config set plan_glob "~/board-plans/*.md"` — useful for non-code projects like board planning or accreditation prep.
+
+---
+
 ## `/open-gstack-browser`
 
 This is my **co-presence mode**.
diff --git a/gstack/llms.txt b/gstack/llms.txt
index 8c5d4a3924..7e19d81fe8 100644
--- a/gstack/llms.txt
+++ b/gstack/llms.txt
@@ -44,6 +44,7 @@ Conventions:
 - [/plan-design-review](plan-design-review/SKILL.md): Designer's eye plan review — interactive, like CEO and Eng review.
 - [/plan-devex-review](plan-devex-review/SKILL.md): Interactive developer experience plan review.
 - [/plan-eng-review](plan-eng-review/SKILL.md): Eng manager-mode plan review.
+- [/plan-status](plan-status/SKILL.md): Check progress of a gstack plan against the current codebase and git log.
 - [/plan-tune](plan-tune/SKILL.md): Self-tuning question sensitivity + developer psychographic for gstack (v1: observational).
 - [/qa](qa/SKILL.md): Systematically QA test a web application and fix bugs found.
 - [/qa-only](qa-only/SKILL.md): Report-only QA testing.
diff --git a/package.json b/package.json
index d4512f5e7d..6f3dd91642 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "gstack",
-  "version": "1.33.2.0",
+  "version": "1.34.0.0",
   "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
   "license": "MIT",
   "type": "module",
diff --git a/plan-status/SKILL.md b/plan-status/SKILL.md
new file mode 100644
index 0000000000..048ec5f1b3
--- /dev/null
+++ b/plan-status/SKILL.md
@@ -0,0 +1,728 @@
+---
+name: plan-status
+preamble-tier: 1
+version: 1.0.0
+description: |
+  Check progress of a gstack plan against the current codebase and git log.
+  Reads a plan file (CEO plan, eng plan, or any gstack plan doc), extracts
+  phases and success-criteria checkboxes, cross-references git commits and
+  filesystem state, and produces a done/in-progress/remaining status report.
+  Use when: "plan status", "how far along is the plan", "what's done",
+  "what's left", "check plan progress", "where are we on the plan". (gstack)
+triggers:
+  - plan status
+  - how far along
+  - what's done on the plan
+  - what's left on the plan
+  - check plan progress
+  - where are we on the plan
+allowed-tools:
+  - Bash
+  - Read
+  - Glob
+  - Grep
+  - AskUserQuestion
+---
+<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly -->
+<!-- Regenerate: bun run gen:skill-docs -->
+
+## Preamble (run first)
+
+```bash
+_UPD=$(~/.claude/skills/gstack/bin/gstack-update-check 2>/dev/null || .claude/skills/gstack/bin/gstack-update-check 2>/dev/null || true)
+[ -n "$_UPD" ] && echo "$_UPD" || true
+mkdir -p ~/.gstack/sessions
+touch ~/.gstack/sessions/"$PPID"
+_SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
+find ~/.gstack/sessions -mmin +120 -type f -exec rm {} + 2>/dev/null || true
+_PROACTIVE=$(~/.claude/skills/gstack/bin/gstack-config get proactive 2>/dev/null || echo "true")
+_PROACTIVE_PROMPTED=$([ -f ~/.gstack/.proactive-prompted ] && echo "yes" || echo "no")
+_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
+echo "BRANCH: $_BRANCH"
+_SKILL_PREFIX=$(~/.claude/skills/gstack/bin/gstack-config get skill_prefix 2>/dev/null || echo "false")
+echo "PROACTIVE: $_PROACTIVE"
+echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
+echo "SKILL_PREFIX: $_SKILL_PREFIX"
+source <(~/.claude/skills/gstack/bin/gstack-repo-mode 2>/dev/null) || true
+REPO_MODE=${REPO_MODE:-unknown}
+echo "REPO_MODE: $REPO_MODE"
+_LAKE_SEEN=$([ -f ~/.gstack/.completeness-intro-seen ] && echo "yes" || echo "no")
+echo "LAKE_INTRO: $_LAKE_SEEN"
+_TEL=$(~/.claude/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || true)
+_TEL_PROMPTED=$([ -f ~/.gstack/.telemetry-prompted ] && echo "yes" || echo "no")
+_TEL_START=$(date +%s)
+_SESSION_ID="$$-$(date +%s)"
+echo "TELEMETRY: ${_TEL:-off}"
+echo "TEL_PROMPTED: $_TEL_PROMPTED"
+_EXPLAIN_LEVEL=$(~/.claude/skills/gstack/bin/gstack-config get explain_level 2>/dev/null || echo "default")
+if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
+echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
+_QUESTION_TUNING=$(~/.claude/skills/gstack/bin/gstack-config get question_tuning 2>/dev/null || echo "false")
+echo "QUESTION_TUNING: $_QUESTION_TUNING"
+mkdir -p ~/.gstack/analytics
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"plan-status","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}'  >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+for _PF in $(find ~/.gstack/analytics -maxdepth 1 -name '.pending-*' 2>/dev/null); do
+  if [ -f "$_PF" ]; then
+    if [ "$_TEL" != "off" ] && [ -x "~/.claude/skills/gstack/bin/gstack-telemetry-log" ]; then
+      ~/.claude/skills/gstack/bin/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true
+    fi
+    rm -f "$_PF" 2>/dev/null || true
+  fi
+  break
+done
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_LEARN_FILE="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}/learnings.jsonl"
+if [ -f "$_LEARN_FILE" ]; then
+  _LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
+  echo "LEARNINGS: $_LEARN_COUNT entries loaded"
+  if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
+    ~/.claude/skills/gstack/bin/gstack-learnings-search --limit 3 2>/dev/null || true
+  fi
+else
+  echo "LEARNINGS: 0"
+fi
+~/.claude/skills/gstack/bin/gstack-timeline-log '{"skill":"plan-status","event":"started","branch":"'"$_BRANCH"'","session":"'"$_SESSION_ID"'"}' 2>/dev/null &
+_HAS_ROUTING="no"
+if [ -f CLAUDE.md ] && grep -q "## Skill routing" CLAUDE.md 2>/dev/null; then
+  _HAS_ROUTING="yes"
+fi
+_ROUTING_DECLINED=$(~/.claude/skills/gstack/bin/gstack-config get routing_declined 2>/dev/null || echo "false")
+echo "HAS_ROUTING: $_HAS_ROUTING"
+echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
+_VENDORED="no"
+if [ -d ".claude/skills/gstack" ] && [ ! -L ".claude/skills/gstack" ]; then
+  if [ -f ".claude/skills/gstack/VERSION" ] || [ -d ".claude/skills/gstack/.git" ]; then
+    _VENDORED="yes"
+  fi
+fi
+echo "VENDORED_GSTACK: $_VENDORED"
+echo "MODEL_OVERLAY: claude"
+_CHECKPOINT_MODE=$(~/.claude/skills/gstack/bin/gstack-config get checkpoint_mode 2>/dev/null || echo "explicit")
+_CHECKPOINT_PUSH=$(~/.claude/skills/gstack/bin/gstack-config get checkpoint_push 2>/dev/null || echo "false")
+echo "CHECKPOINT_MODE: $_CHECKPOINT_MODE"
+echo "CHECKPOINT_PUSH: $_CHECKPOINT_PUSH"
+[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true
+```
+
+## Plan Mode Safe Operations
+
+In plan mode, allowed because they inform the plan: `$B`, `$D`, `codex exec`/`codex review`, writes to `~/.gstack/`, writes to the plan file, and `open` for generated artifacts.
+
+## Skill Invocation During Plan Mode
+
+If the user invokes a skill in plan mode, the skill takes precedence over generic plan mode behavior. **Treat the skill file as executable instructions, not reference.** Follow it step by step starting from Step 0; the first AskUserQuestion is the workflow entering plan mode, not a violation of it. AskUserQuestion (any variant — `mcp__*__AskUserQuestion` or native; see "AskUserQuestion Format → Tool resolution") satisfies plan mode's end-of-turn requirement. If no variant is callable, the skill is BLOCKED — stop and report `BLOCKED — AskUserQuestion unavailable` per the AskUserQuestion Format rule. At a STOP point, stop immediately. Do not continue the workflow or call ExitPlanMode there. Commands marked "PLAN MODE EXCEPTION — ALWAYS RUN" execute. Call ExitPlanMode only after the skill workflow completes, or if the user tells you to cancel the skill or leave plan mode.
+
+If `PROACTIVE` is `"false"`, do not auto-invoke or proactively suggest skills. If a skill seems useful, ask: "I think /skillname might help here — want me to run it?"
+
+If `SKILL_PREFIX` is `"true"`, suggest/invoke `/gstack-*` names. Disk paths stay `~/.claude/skills/gstack/[skill-name]/SKILL.md`.
+
+If output shows `UPGRADE_AVAILABLE <old> <new>`: read `~/.claude/skills/gstack/gstack-upgrade/SKILL.md` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined).
+
+If output shows `JUST_UPGRADED <from> <to>`: print "Running gstack v{to} (just updated!)". If `SPAWNED_SESSION` is true, skip feature discovery.
+
+Feature discovery, max one prompt per session:
+- Missing `~/.claude/skills/gstack/.feature-prompted-continuous-checkpoint`: AskUserQuestion for Continuous checkpoint auto-commits. If accepted, run `~/.claude/skills/gstack/bin/gstack-config set checkpoint_mode continuous`. Always touch marker.
+- Missing `~/.claude/skills/gstack/.feature-prompted-model-overlay`: inform "Model overlays are active. MODEL_OVERLAY shows the patch." Always touch marker.
+
+After upgrade prompts, continue workflow.
+
+If `WRITING_STYLE_PENDING` is `yes`: ask once about writing style:
+
+> v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse?
+
+Options:
+- A) Keep the new default (recommended — good writing helps everyone)
+- B) Restore V0 prose — set `explain_level: terse`
+
+If A: leave `explain_level` unset (defaults to `default`).
+If B: run `~/.claude/skills/gstack/bin/gstack-config set explain_level terse`.
+
+Always run (regardless of choice):
+```bash
+rm -f ~/.gstack/.writing-style-prompt-pending
+touch ~/.gstack/.writing-style-prompted
+```
+
+Skip if `WRITING_STYLE_PENDING` is `no`.
+
+If `LAKE_INTRO` is `no`: say "gstack follows the **Boil the Lake** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" Offer to open:
+
+```bash
+open https://garryslist.org/posts/boil-the-ocean
+touch ~/.gstack/.completeness-intro-seen
+```
+
+Only run `open` if yes. Always run `touch`.
+
+If `TEL_PROMPTED` is `no` AND `LAKE_INTRO` is `yes`: ask telemetry once via AskUserQuestion:
+
+> Help gstack get better. Share usage data only: skill, duration, crashes, stable device ID. No code, file paths, or repo names.
+
+Options:
+- A) Help gstack get better! (recommended)
+- B) No thanks
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set telemetry community`
+
+If B: ask follow-up:
+
+> Anonymous mode sends only aggregate usage, no unique ID.
+
+Options:
+- A) Sure, anonymous is fine
+- B) No thanks, fully off
+
+If B→A: run `~/.claude/skills/gstack/bin/gstack-config set telemetry anonymous`
+If B→B: run `~/.claude/skills/gstack/bin/gstack-config set telemetry off`
+
+Always run:
+```bash
+touch ~/.gstack/.telemetry-prompted
+```
+
+Skip if `TEL_PROMPTED` is `yes`.
+
+If `PROACTIVE_PROMPTED` is `no` AND `TEL_PROMPTED` is `yes`: ask once:
+
+> Let gstack proactively suggest skills, like /qa for "does this work?" or /investigate for bugs?
+
+Options:
+- A) Keep it on (recommended)
+- B) Turn it off — I'll type /commands myself
+
+If A: run `~/.claude/skills/gstack/bin/gstack-config set proactive true`
+If B: run `~/.claude/skills/gstack/bin/gstack-config set proactive false`
+
+Always run:
+```bash
+touch ~/.gstack/.proactive-prompted
+```
+
+Skip if `PROACTIVE_PROMPTED` is `yes`.
+
+If `HAS_ROUTING` is `no` AND `ROUTING_DECLINED` is `false` AND `PROACTIVE_PROMPTED` is `yes`:
+Check if a CLAUDE.md file exists in the project root. If it does not exist, create it.
+
+Use AskUserQuestion:
+
+> gstack works best when your project's CLAUDE.md includes skill routing rules.
+
+Options:
+- A) Add routing rules to CLAUDE.md (recommended)
+- B) No thanks, I'll invoke skills manually
+
+If A: Append this section to the end of CLAUDE.md:
+
+```markdown
+
+## Skill routing
+
+When the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill.
+
+Key routing rules:
+- Product ideas/brainstorming → invoke /office-hours
+- Strategy/scope → invoke /plan-ceo-review
+- Architecture → invoke /plan-eng-review
+- Design system/plan review → invoke /design-consultation or /plan-design-review
+- Full review pipeline → invoke /autoplan
+- Bugs/errors → invoke /investigate
+- QA/testing site behavior → invoke /qa or /qa-only
+- Code review/diff check → invoke /review
+- Visual polish → invoke /design-review
+- Ship/deploy/PR → invoke /ship or /land-and-deploy
+- Save progress → invoke /context-save
+- Resume context → invoke /context-restore
+```
+
+Then commit the change: `git add CLAUDE.md && git commit -m "chore: add gstack skill routing rules to CLAUDE.md"`
+
+If B: run `~/.claude/skills/gstack/bin/gstack-config set routing_declined true` and say they can re-enable with `gstack-config set routing_declined false`.
+
+This only happens once per project. Skip if `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`.
+
+If `VENDORED_GSTACK` is `yes`, warn once via AskUserQuestion unless `~/.gstack/.vendoring-warned-$SLUG` exists:
+
+> This project has gstack vendored in `.claude/skills/gstack/`. Vendoring is deprecated.
+> Migrate to team mode?
+
+Options:
+- A) Yes, migrate to team mode now
+- B) No, I'll handle it myself
+
+If A:
+1. Run `git rm -r .claude/skills/gstack/`
+2. Run `echo '.claude/skills/gstack/' >> .gitignore`
+3. Run `~/.claude/skills/gstack/bin/gstack-team-init required` (or `optional`)
+4. Run `git add .claude/ .gitignore CLAUDE.md && git commit -m "chore: migrate gstack from vendored to team mode"`
+5. Tell the user: "Done. Each developer now runs: `cd ~/.claude/skills/gstack && ./setup --team`"
+
+If B: say "OK, you're on your own to keep the vendored copy up to date."
+
+Always run (regardless of choice):
+```bash
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+touch ~/.gstack/.vendoring-warned-${SLUG:-unknown}
+```
+
+If marker exists, skip.
+
+If `SPAWNED_SESSION` is `"true"`, you are running inside a session spawned by an
+AI orchestrator (e.g., OpenClaw). In spawned sessions:
+- Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.
+- Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro.
+- Focus on completing the task and reporting results via prose output.
+- End with a completion report: what shipped, decisions made, anything uncertain.
+
+## Artifacts Sync (skill start)
+
+```bash
+_GSTACK_HOME="${GSTACK_HOME:-$HOME/.gstack}"
+# Prefer the v1.27.0.0 artifacts file; fall back to brain file for users
+# upgrading mid-stream before the migration script runs.
+if [ -f "$HOME/.gstack-artifacts-remote.txt" ]; then
+  _BRAIN_REMOTE_FILE="$HOME/.gstack-artifacts-remote.txt"
+else
+  _BRAIN_REMOTE_FILE="$HOME/.gstack-brain-remote.txt"
+fi
+_BRAIN_SYNC_BIN="~/.claude/skills/gstack/bin/gstack-brain-sync"
+_BRAIN_CONFIG_BIN="~/.claude/skills/gstack/bin/gstack-config"
+
+# /sync-gbrain context-load: teach the agent to use gbrain when it's available.
+# Per-worktree pin: post-spike redesign uses kubectl-style `.gbrain-source` in the
+# git toplevel to scope queries. Look for the pin in the worktree (not a global
+# state file) so that opening worktree B without a pin doesn't claim "indexed"
+# just because worktree A was synced. Empty string when gbrain is not
+# configured (zero context cost for non-gbrain users).
+_GBRAIN_CONFIG="$HOME/.gbrain/config.json"
+if [ -f "$_GBRAIN_CONFIG" ] && command -v gbrain >/dev/null 2>&1; then
+  _GBRAIN_VERSION_OK=$(gbrain --version 2>/dev/null | grep -c '^gbrain ' || echo 0)
+  if [ "$_GBRAIN_VERSION_OK" -gt 0 ] 2>/dev/null; then
+    _GBRAIN_PIN_PATH=""
+    _REPO_TOP=$(git rev-parse --show-toplevel 2>/dev/null || echo "")
+    if [ -n "$_REPO_TOP" ] && [ -f "$_REPO_TOP/.gbrain-source" ]; then
+      _GBRAIN_PIN_PATH="$_REPO_TOP/.gbrain-source"
+    fi
+    if [ -n "$_GBRAIN_PIN_PATH" ]; then
+      echo "GBrain configured. Prefer \`gbrain search\`/\`gbrain query\` over Grep for"
+      echo "semantic questions; use \`gbrain code-def\`/\`code-refs\`/\`code-callers\` for"
+      echo "symbol-aware code lookup. See \"## GBrain Search Guidance\" in CLAUDE.md."
+      echo "Run /sync-gbrain to refresh."
+    else
+      echo "GBrain configured but this worktree isn't pinned yet. Run \`/sync-gbrain --full\`"
+      echo "before relying on \`gbrain search\` for code questions in this worktree."
+      echo "Falls back to Grep until pinned."
+    fi
+  fi
+fi
+
+_BRAIN_SYNC_MODE=$("$_BRAIN_CONFIG_BIN" get artifacts_sync_mode 2>/dev/null || echo off)
+
+# Detect remote-MCP mode (Path 4 of /setup-gbrain). Local artifacts sync is
+# a no-op in remote mode; the brain server pulls from GitHub/GitLab on its
+# own cadence. Read claude.json directly to keep this preamble fast (no
+# subprocess to claude CLI on every skill start).
+_GBRAIN_MCP_MODE="none"
+if command -v jq >/dev/null 2>&1 && [ -f "$HOME/.claude.json" ]; then
+  _GBRAIN_MCP_TYPE=$(jq -r '.mcpServers.gbrain.type // .mcpServers.gbrain.transport // empty' "$HOME/.claude.json" 2>/dev/null)
+  case "$_GBRAIN_MCP_TYPE" in
+    url|http|sse) _GBRAIN_MCP_MODE="remote-http" ;;
+    stdio) _GBRAIN_MCP_MODE="local-stdio" ;;
+  esac
+fi
+
+if [ -f "$_BRAIN_REMOTE_FILE" ] && [ ! -d "$_GSTACK_HOME/.git" ] && [ "$_BRAIN_SYNC_MODE" = "off" ]; then
+  _BRAIN_NEW_URL=$(head -1 "$_BRAIN_REMOTE_FILE" 2>/dev/null | tr -d '[:space:]')
+  if [ -n "$_BRAIN_NEW_URL" ]; then
+    echo "ARTIFACTS_SYNC: artifacts repo detected: $_BRAIN_NEW_URL"
+    echo "ARTIFACTS_SYNC: run 'gstack-brain-restore' to pull your cross-machine artifacts (or 'gstack-config set artifacts_sync_mode off' to dismiss forever)"
+  fi
+fi
+
+if [ -d "$_GSTACK_HOME/.git" ] && [ "$_BRAIN_SYNC_MODE" != "off" ]; then
+  _BRAIN_LAST_PULL_FILE="$_GSTACK_HOME/.brain-last-pull"
+  _BRAIN_NOW=$(date +%s)
+  _BRAIN_DO_PULL=1
+  if [ -f "$_BRAIN_LAST_PULL_FILE" ]; then
+    _BRAIN_LAST=$(cat "$_BRAIN_LAST_PULL_FILE" 2>/dev/null || echo 0)
+    _BRAIN_AGE=$(( _BRAIN_NOW - _BRAIN_LAST ))
+    [ "$_BRAIN_AGE" -lt 86400 ] && _BRAIN_DO_PULL=0
+  fi
+  if [ "$_BRAIN_DO_PULL" = "1" ]; then
+    ( cd "$_GSTACK_HOME" && git fetch origin >/dev/null 2>&1 && git merge --ff-only "origin/$(git rev-parse --abbrev-ref HEAD)" >/dev/null 2>&1 ) || true
+    echo "$_BRAIN_NOW" > "$_BRAIN_LAST_PULL_FILE"
+  fi
+  "$_BRAIN_SYNC_BIN" --once 2>/dev/null || true
+fi
+
+if [ "$_GBRAIN_MCP_MODE" = "remote-http" ]; then
+  # Remote-MCP mode: local artifacts sync is a no-op (brain admin's server
+  # pulls from GitHub/GitLab). Show the user this is by design, not broken.
+  _GBRAIN_HOST=$(jq -r '.mcpServers.gbrain.url // empty' "$HOME/.claude.json" 2>/dev/null | sed -E 's|^https?://([^/:]+).*|\1|')
+  echo "ARTIFACTS_SYNC: remote-mode (managed by brain server ${_GBRAIN_HOST:-remote})"
+elif [ -d "$_GSTACK_HOME/.git" ] && [ "$_BRAIN_SYNC_MODE" != "off" ]; then
+  _BRAIN_QUEUE_DEPTH=0
+  [ -f "$_GSTACK_HOME/.brain-queue.jsonl" ] && _BRAIN_QUEUE_DEPTH=$(wc -l < "$_GSTACK_HOME/.brain-queue.jsonl" | tr -d ' ')
+  _BRAIN_LAST_PUSH="never"
+  [ -f "$_GSTACK_HOME/.brain-last-push" ] && _BRAIN_LAST_PUSH=$(cat "$_GSTACK_HOME/.brain-last-push" 2>/dev/null || echo never)
+  echo "ARTIFACTS_SYNC: mode=$_BRAIN_SYNC_MODE | last_push=$_BRAIN_LAST_PUSH | queue=$_BRAIN_QUEUE_DEPTH"
+else
+  echo "ARTIFACTS_SYNC: off"
+fi
+```
+
+
+
+Privacy stop-gate: if output shows `ARTIFACTS_SYNC: off`, `artifacts_sync_mode_prompted` is `false`, and gbrain is on PATH or `gbrain doctor --fast --json` works, ask once:
+
+> gstack can publish your artifacts (CEO plans, designs, reports) to a private GitHub repo that GBrain indexes across machines. How much should sync?
+
+Options:
+- A) Everything allowlisted (recommended)
+- B) Only artifacts
+- C) Decline, keep everything local
+
+After answer:
+
+```bash
+# Chosen mode: full | artifacts-only | off
+"$_BRAIN_CONFIG_BIN" set artifacts_sync_mode <choice>
+"$_BRAIN_CONFIG_BIN" set artifacts_sync_mode_prompted true
+```
+
+If A/B and `~/.gstack/.git` is missing, ask whether to run `gstack-artifacts-init`. Do not block the skill.
+
+At skill END before telemetry:
+
+```bash
+"~/.claude/skills/gstack/bin/gstack-brain-sync" --discover-new 2>/dev/null || true
+"~/.claude/skills/gstack/bin/gstack-brain-sync" --once 2>/dev/null || true
+```
+
+
+## Model-Specific Behavioral Patch (claude)
+
+The following nudges are tuned for the claude model family. They are
+**subordinate** to skill workflow, STOP points, AskUserQuestion gates, plan-mode
+safety, and /ship review gates. If a nudge below conflicts with skill instructions,
+the skill wins. Treat these as preferences, not rules.
+
+**Todo-list discipline.** When working through a multi-step plan, mark each task
+complete individually as you finish it. Do not batch-complete at the end. If a task
+turns out to be unnecessary, mark it skipped with a one-line reason.
+
+**Think before heavy actions.** For complex operations (refactors, migrations,
+non-trivial new features), briefly state your approach before executing. This lets
+the user course-correct cheaply instead of mid-flight.
+
+**Dedicated tools over Bash.** Prefer Read, Edit, Write, Glob, Grep over shell
+equivalents (cat, sed, find, grep). The dedicated tools are cheaper and clearer.
+
+## Voice
+
+Direct, concrete, builder-to-builder. Name the file, function, command, and user-visible impact. No filler.
+
+No em dashes. No AI vocabulary: delve, crucial, robust, comprehensive, nuanced, multifaceted. Never corporate or academic. Short paragraphs. End with what to do.
+
+The user has context you do not. Cross-model agreement is a recommendation, not a decision. The user decides.
+
+## Completion Status Protocol
+
+When completing a skill workflow, report status using one of:
+- **DONE** — completed with evidence.
+- **DONE_WITH_CONCERNS** — completed, but list concerns.
+- **BLOCKED** — cannot proceed; state blocker and what was tried.
+- **NEEDS_CONTEXT** — missing info; state exactly what is needed.
+
+Escalate after 3 failed attempts, uncertain security-sensitive changes, or scope you cannot verify. Format: `STATUS`, `REASON`, `ATTEMPTED`, `RECOMMENDATION`.
+
+## Operational Self-Improvement
+
+Before completing, if you discovered a durable project quirk or command fix that would save 5+ minutes next time, log it:
+
+```bash
+~/.claude/skills/gstack/bin/gstack-learnings-log '{"skill":"SKILL_NAME","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
+```
+
+Do not log obvious facts or one-time transient errors.
+
+## Telemetry (run last)
+
+After workflow completion, log telemetry. Use skill `name:` from frontmatter. OUTCOME is success/error/abort/unknown.
+
+**PLAN MODE EXCEPTION — ALWAYS RUN:** This command writes telemetry to
+`~/.gstack/analytics/`, matching preamble analytics writes.
+
+Run this bash:
+
+```bash
+_TEL_END=$(date +%s)
+_TEL_DUR=$(( _TEL_END - _TEL_START ))
+rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true
+# Session timeline: record skill completion (local-only, never sent anywhere)
+~/.claude/skills/gstack/bin/gstack-timeline-log '{"skill":"SKILL_NAME","event":"completed","branch":"'$(git branch --show-current 2>/dev/null || echo unknown)'","outcome":"OUTCOME","duration_s":"'"$_TEL_DUR"'","session":"'"$_SESSION_ID"'"}' 2>/dev/null || true
+# Local analytics (gated on telemetry setting)
+if [ "$_TEL" != "off" ]; then
+echo '{"skill":"SKILL_NAME","duration_s":"'"$_TEL_DUR"'","outcome":"OUTCOME","browse":"USED_BROWSE","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true
+fi
+# Remote telemetry (opt-in, requires binary)
+if [ "$_TEL" != "off" ] && [ -x ~/.claude/skills/gstack/bin/gstack-telemetry-log ]; then
+  ~/.claude/skills/gstack/bin/gstack-telemetry-log \
+    --skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \
+    --used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &
+fi
+```
+
+Replace `SKILL_NAME`, `OUTCOME`, and `USED_BROWSE` before running.
+
+## Plan Status Footer
+
+In plan mode before ExitPlanMode: if the plan file lacks `## GSTACK REVIEW REPORT`, run `~/.claude/skills/gstack/bin/gstack-review-read` and append the standard runs/status/findings table. With `NO_REVIEWS` or empty, append a 5-row placeholder with verdict "NO REVIEWS YET — run `/autoplan`". If a richer report exists, skip.
+
+PLAN MODE EXCEPTION — always allowed (it's the plan file).
+
+## Plan-status Setup
+
+```bash
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" && mkdir -p ~/.gstack/projects/$SLUG
+_REPO=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")
+_PLAN_GLOB=$(~/.claude/skills/gstack/bin/gstack-config get plan_glob 2>/dev/null || echo "")
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+echo "SLUG_RESOLVED: ${SLUG:-unknown}"
+echo "PLAN_DIR: $_PLAN_DIR"
+if [ -n "$_PLAN_GLOB" ]; then
+  _PLANS=$(ls -t $_PLAN_GLOB 2>/dev/null | head -10)
+else
+  _PLANS=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -10)
+fi
+echo "AVAILABLE_PLANS:"
+if [ -z "$_PLANS" ]; then
+  echo "No plans found in $_PLAN_DIR. Run /office-hours or /plan-ceo-review to create one."
+else
+  echo "$_PLANS"
+fi
+_GIT_LOG=$(git log --oneline $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null | head -30)
+echo "BRANCH_COMMITS:"
+echo "$_GIT_LOG"
+_ANALYTICS="$HOME/.gstack/analytics/skill-usage.jsonl"
+echo "SKILL_ANALYTICS:"
+if [ -f "$_ANALYTICS" ] && [ -n "$_REPO" ] && [ "$_REPO" != "unknown" ]; then
+  grep "\"repo\":\"$_REPO\"" "$_ANALYTICS" 2>/dev/null | tail -200
+else
+  echo "none"
+fi
+```
+
+Note: `plan_glob` is read from `~/.gstack/config.yaml` via `gstack-config` — not from environment variables or user input. Configure it with: `~/.claude/skills/gstack/bin/gstack-config set plan_glob "~/board-plans/*.md"`. Paths with spaces in directory names are not supported in v1.
+
+## Plan Mode Safe Operations
+
+In plan mode, allowed because they inform the plan: reads from `~/.gstack/`, reads from the codebase, `git log`, `git diff`, `find`, `ls`.
+
+## Skill Invocation During Plan Mode
+
+If the user invokes this skill in plan mode, follow it step by step. This skill is read-only — it never edits files. AskUserQuestion satisfies plan mode's end-of-turn requirement if no plan file is auto-resolved.
+
+---
+
+## Step 0 — Resolve the plan file
+
+If the user named a specific plan file in their message, use that path directly.
+
+Otherwise, use the `AVAILABLE_PLANS` list from the Setup block to pick the most relevant plan:
+- If only one plan exists for this project, use it.
+- If the current branch name appears in a plan filename, prefer that one.
+- If multiple plans exist with no clear match, use AskUserQuestion to let the user pick. Present a numbered list of the plan filenames and ask which one to check. This is the only case where AskUserQuestion is needed in this skill — keep the prompt simple (no D<N> format required).
+- If `AVAILABLE_PLANS` is empty, stop and display the empty-state message from Setup.
+
+Read the resolved plan file in full before proceeding.
+
+## Step 1 — Extract structure
+
+From the plan file, identify:
+
+1. **Phases** — sections headed `### Phase N` or `## Phase N` or similar. Note the name and summary of each.
+2. **Success criteria checkboxes** — lines matching `- [ ]` (incomplete) or `- [x]` (complete). These are ground truth from the plan author.
+3. **File/directory references** — any `app/`, `config/`, `db/`, `test/` paths mentioned in the plan that we can verify exist or not.
+4. **Gem/dependency references** — any gem names mentioned as "add" or "remove" that we can verify in Gemfile.
+5. **Pre-migration checklist items** — if present, extract as a separate list.
+
+## Step 2 — Gather evidence
+
+Run these checks. Do them in parallel where possible.
+
+**Git evidence:**
+```bash
+# Commits on this branch since diverging from main
+git log --oneline $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null
+
+# Files changed on this branch
+git diff --name-only $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null
+```
+
+**Filesystem evidence** — for each file/directory the plan says should exist or be deleted, check:
+```bash
+# Check existence of files the plan says should exist
+ls <path> 2>/dev/null || echo "MISSING: <path>"
+
+# Check deletion of files the plan says should be gone
+ls <path> 2>/dev/null && echo "STILL EXISTS: <path>" || echo "DELETED: <path>"
+```
+
+**Gemfile evidence** — for each gem the plan says to add or remove:
+```bash
+grep -E "gem .\"<gemname>\"" Gemfile 2>/dev/null && echo "PRESENT" || echo "ABSENT"
+```
+
+**Config/initializer evidence** — for any initializers or config the plan says to create:
+```bash
+ls config/initializers/<name>.rb 2>/dev/null && echo "EXISTS" || echo "MISSING"
+```
+
+## Step 3 — Classify each item
+
+For each phase and each success-criteria checkbox, assign one of:
+
+- **DONE** — evidence confirms it: file exists/deleted as expected, gem added/removed, commit message matches, checkbox already `[x]`
+- **PARTIAL** — some evidence but not complete (e.g. file exists but a required method is missing)
+- **REMAINING** — no evidence; checkbox still `[ ]` and no corroborating git/filesystem signal
+- **DROPPED** — plan explicitly marks it dropped/removed/n/a
+
+**Classification rules:**
+- Use the evidence conservatively. If you're uncertain, mark REMAINING rather than DONE — a false positive is worse than a false negative.
+- File existence alone is not sufficient to mark a planning artifact DONE. Require a content signal: a named section heading matching the plan's description, a completion marker, or a matching `[x]` checkbox within the file.
+- Commit message matching is a strong positive signal. If the commit message explicitly names the deliverable, weight it heavily.
+- A `[x]` checkbox in the plan file is ground truth from the plan author — mark DONE regardless of other evidence.
+
+## Step 4 — Produce the status report
+
+Output a structured report in three sections.
+
+### Section A: gstack Lifecycle Dashboard
+
+Parse the `SKILL_ANALYTICS` output from the Setup block. Each line is a JSON object:
+`{"skill":"...","ts":"2026-05-11T22:00:00Z","repo":"..."}`.
+
+For each canonical skill in the table below, count occurrences and find the most recent `ts` (format as `YYYY-MM-DD HH:MM`). For the `(commits)` row, use the `BRANCH_COMMITS` count from the Setup block.
+
+**Status per row:**
+- 0 runs: Status = `—`, Last Run = `—`
+- > 0 runs: Status = `DONE`, Last Run = most recent timestamp
+- `(commits)` row: Status = `DONE` if commits > 0, `—` if 0; Last Run = `—` always
+
+**Required column:**
+- `YES` for: `/plan-eng-review`, `(commits)`, `/review`, `/ship`
+- `no` for all others
+
+**VERDICT logic:**
+- Count required YES rows where Status = `—` (not yet run), including `(commits)` if 0 commits
+- 0 REMAINING: `CLEARED — all required lifecycle steps complete`
+- All required REMAINING (nothing run): `NOT STARTED`
+- Otherwise: `IN PROGRESS — N required skill(s) REMAINING: [names]`
+
+Display:
+
+```
++====================================================================================+
+|                         GSTACK LIFECYCLE DASHBOARD                                 |
++====================================================================================+
+| Phase    | Skill               | Runs | Last Run         | Status   | Required    |
+|----------|---------------------|------|------------------|----------|-------------|
+| Think    | /office-hours       |  0   | —                | —        | no          |
+| Plan     | /plan-ceo-review    |  0   | —                | —        | no          |
+|          | /plan-eng-review    |  0   | —                | —        | YES         |
+|          | /plan-design-review |  0   | —                | —        | no          |
+|          | /plan-devex-review  |  0   | —                | —        | no          |
+|          | /autoplan           |  0   | —                | —        | no          |
+| Build    | (commits)           |  0   | —                | —        | YES         |
+| Review   | /review             |  0   | —                | —        | YES         |
+|          | /design-review      |  0   | —                | —        | no          |
+| Test     | /qa                 |  0   | —                | —        | no          |
+|          | /qa-only            |  0   | —                | —        | no          |
+|          | /benchmark          |  0   | —                | —        | no          |
+| Ship     | /ship               |  0   | —                | —        | YES         |
+|          | /land-and-deploy    |  0   | —                | —        | no          |
+| Reflect  | /retro              |  0   | —                | —        | no          |
+|          | /document-release   |  0   | —                | —        | no          |
++------------------------------------------------------------------------------------+
+| VERDICT: NOT STARTED                                                                |
++====================================================================================+
+```
+
+Fill in real values from the analytics data; the table above shows the all-zero baseline shape.
+
+### Section B: Other Observed Skills
+
+After building the lifecycle dashboard, collect any skill names from `SKILL_ANALYTICS` that are NOT in the canonical skill list above and NOT `plan-status` itself. Display a companion table:
+
+```
++================================================+
+|          OTHER OBSERVED SKILLS                 |
+|  (not yet mapped to lifecycle dashboard)       |
++================================================+
+| Skill              | Runs | Last Run           |
+|--------------------+------+--------------------|
+| /investigate       |  2   | 2026-05-10 14:00   |
+| /codex             |  1   | 2026-05-09 11:00   |
++------------------------------------------------+
+| 2 skills observed                              |
++================================================+
+```
+
+If no unlisted skills appear:
+```
+Other observed skills: none — all analytics entries are covered by the lifecycle dashboard above.
+```
+
+This table is self-maintaining: any new gstack skill that gets invoked on the project surfaces here automatically.
+
+### Section C: Plan Detail
+
+```
+## Plan Status: <plan filename>
+Branch: <branch> | As of: <today's date>
+
+### Phase Summary
+| Phase | Status | Notes |
+|-------|--------|-------|
+| Phase 0: Foundation | DONE | All gems added, initializers present |
+| Phase 1: Schema | DONE | Migrations in db/migrate/ |
+| Phase 7: RAG migration | REMAINING | NotImplementedError stubs; no RubyLLM.embed calls |
+
+### Success Criteria
+| Item | Status |
+|------|--------|
+| [ ] ruby_llm install generator accepted | DONE |
+| [ ] langchainrb removed from Gemfile | REMAINING |
+| [ ] Cross-tenant scoping test passes | REMAINING |
+| [ ] ActsAsTenant require_tenant = true | PARTIAL — dev only, not production |
+
+### Branch Commits
+| Hash    | Message                                  | In Scope |
+|---------|------------------------------------------|----------|
+| a1b2c3d | feat: add ruby_llm gem and initializer   | YES      |
+| e4f5g6h | chore: remove langchainrb from Gemfile   | YES      |
+| i7j8k9l | fix: unrelated bug in user controller    | NO       |
+
+### Pre-Migration Checklist (if present)
+List any checklist items from the plan and their resolved status.
+
+### Summary
+X of Y phases complete. Z of W success criteria met.
+Key blockers: <list the REMAINING items that appear most critical>
+Suggested next action: <one concrete next step>
+```
+
+**Notes column:** one phrase, not a sentence. Goal is a scannable dashboard, not a prose report.
+
+**Branch Commits:** For each commit in `BRANCH_COMMITS`, classify `In Scope` as YES if the commit message or changed files directly correspond to a plan deliverable (phase name, file reference, or gem reference from Step 1). Mark NO for commits unrelated to the plan.
+
+## Step 5 — Offer next action
+
+After the report, offer one of:
+- "Want me to start on [top REMAINING item]?"
+- "Want me to update the plan file's checkboxes to reflect what's done?"
+- Nothing, if the plan is 100% complete — just say so.
+
+Do not auto-start work. User decides.
diff --git a/plan-status/SKILL.md.tmpl b/plan-status/SKILL.md.tmpl
new file mode 100644
index 0000000000..8c5fbbeb73
--- /dev/null
+++ b/plan-status/SKILL.md.tmpl
@@ -0,0 +1,272 @@
+---
+name: plan-status
+preamble-tier: 1
+version: 1.0.0
+description: |
+  Check progress of a gstack plan against the current codebase and git log.
+  Reads a plan file (CEO plan, eng plan, or any gstack plan doc), extracts
+  phases and success-criteria checkboxes, cross-references git commits and
+  filesystem state, and produces a done/in-progress/remaining status report.
+  Use when: "plan status", "how far along is the plan", "what's done",
+  "what's left", "check plan progress", "where are we on the plan". (gstack)
+triggers:
+  - plan status
+  - how far along
+  - what's done on the plan
+  - what's left on the plan
+  - check plan progress
+  - where are we on the plan
+allowed-tools:
+  - Bash
+  - Read
+  - Glob
+  - Grep
+  - AskUserQuestion
+---
+
+{{PREAMBLE}}
+
+## Plan-status Setup
+
+```bash
+{{SLUG_SETUP}}
+_REPO=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")
+_PLAN_GLOB=$(~/.claude/skills/gstack/bin/gstack-config get plan_glob 2>/dev/null || echo "")
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+echo "SLUG_RESOLVED: ${SLUG:-unknown}"
+echo "PLAN_DIR: $_PLAN_DIR"
+if [ -n "$_PLAN_GLOB" ]; then
+  _PLANS=$(ls -t $_PLAN_GLOB 2>/dev/null | head -10)
+else
+  _PLANS=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -10)
+fi
+echo "AVAILABLE_PLANS:"
+if [ -z "$_PLANS" ]; then
+  echo "No plans found in $_PLAN_DIR. Run /office-hours or /plan-ceo-review to create one."
+else
+  echo "$_PLANS"
+fi
+_GIT_LOG=$(git log --oneline $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null | head -30)
+echo "BRANCH_COMMITS:"
+echo "$_GIT_LOG"
+_ANALYTICS="$HOME/.gstack/analytics/skill-usage.jsonl"
+echo "SKILL_ANALYTICS:"
+if [ -f "$_ANALYTICS" ] && [ -n "$_REPO" ] && [ "$_REPO" != "unknown" ]; then
+  grep "\"repo\":\"$_REPO\"" "$_ANALYTICS" 2>/dev/null | tail -200
+else
+  echo "none"
+fi
+```
+
+Note: `plan_glob` is read from `~/.gstack/config.yaml` via `gstack-config` — not from environment variables or user input. Configure it with: `~/.claude/skills/gstack/bin/gstack-config set plan_glob "~/board-plans/*.md"`. Paths with spaces in directory names are not supported in v1.
+
+## Plan Mode Safe Operations
+
+In plan mode, allowed because they inform the plan: reads from `~/.gstack/`, reads from the codebase, `git log`, `git diff`, `find`, `ls`.
+
+## Skill Invocation During Plan Mode
+
+If the user invokes this skill in plan mode, follow it step by step. This skill is read-only — it never edits files. AskUserQuestion satisfies plan mode's end-of-turn requirement if no plan file is auto-resolved.
+
+---
+
+## Step 0 — Resolve the plan file
+
+If the user named a specific plan file in their message, use that path directly.
+
+Otherwise, use the `AVAILABLE_PLANS` list from the Setup block to pick the most relevant plan:
+- If only one plan exists for this project, use it.
+- If the current branch name appears in a plan filename, prefer that one.
+- If multiple plans exist with no clear match, use AskUserQuestion to let the user pick. Present a numbered list of the plan filenames and ask which one to check. This is the only case where AskUserQuestion is needed in this skill — keep the prompt simple (no D<N> format required).
+- If `AVAILABLE_PLANS` is empty, stop and display the empty-state message from Setup.
+
+Read the resolved plan file in full before proceeding.
+
+## Step 1 — Extract structure
+
+From the plan file, identify:
+
+1. **Phases** — sections headed `### Phase N` or `## Phase N` or similar. Note the name and summary of each.
+2. **Success criteria checkboxes** — lines matching `- [ ]` (incomplete) or `- [x]` (complete). These are ground truth from the plan author.
+3. **File/directory references** — any `app/`, `config/`, `db/`, `test/` paths mentioned in the plan that we can verify exist or not.
+4. **Gem/dependency references** — any gem names mentioned as "add" or "remove" that we can verify in Gemfile.
+5. **Pre-migration checklist items** — if present, extract as a separate list.
+
+## Step 2 — Gather evidence
+
+Run these checks. Do them in parallel where possible.
+
+**Git evidence:**
+```bash
+# Commits on this branch since diverging from main
+git log --oneline $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null
+
+# Files changed on this branch
+git diff --name-only $(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)..HEAD 2>/dev/null
+```
+
+**Filesystem evidence** — for each file/directory the plan says should exist or be deleted, check:
+```bash
+# Check existence of files the plan says should exist
+ls <path> 2>/dev/null || echo "MISSING: <path>"
+
+# Check deletion of files the plan says should be gone
+ls <path> 2>/dev/null && echo "STILL EXISTS: <path>" || echo "DELETED: <path>"
+```
+
+**Gemfile evidence** — for each gem the plan says to add or remove:
+```bash
+grep -E "gem .\"<gemname>\"" Gemfile 2>/dev/null && echo "PRESENT" || echo "ABSENT"
+```
+
+**Config/initializer evidence** — for any initializers or config the plan says to create:
+```bash
+ls config/initializers/<name>.rb 2>/dev/null && echo "EXISTS" || echo "MISSING"
+```
+
+## Step 3 — Classify each item
+
+For each phase and each success-criteria checkbox, assign one of:
+
+- **DONE** — evidence confirms it: file exists/deleted as expected, gem added/removed, commit message matches, checkbox already `[x]`
+- **PARTIAL** — some evidence but not complete (e.g. file exists but a required method is missing)
+- **REMAINING** — no evidence; checkbox still `[ ]` and no corroborating git/filesystem signal
+- **DROPPED** — plan explicitly marks it dropped/removed/n/a
+
+**Classification rules:**
+- Use the evidence conservatively. If you're uncertain, mark REMAINING rather than DONE — a false positive is worse than a false negative.
+- File existence alone is not sufficient to mark a planning artifact DONE. Require a content signal: a named section heading matching the plan's description, a completion marker, or a matching `[x]` checkbox within the file.
+- Commit message matching is a strong positive signal. If the commit message explicitly names the deliverable, weight it heavily.
+- A `[x]` checkbox in the plan file is ground truth from the plan author — mark DONE regardless of other evidence.
+
+## Step 4 — Produce the status report
+
+Output a structured report in three sections.
+
+### Section A: gstack Lifecycle Dashboard
+
+Parse the `SKILL_ANALYTICS` output from the Setup block. Each line is a JSON object:
+`{"skill":"...","ts":"2026-05-11T22:00:00Z","repo":"..."}`.
+
+For each canonical skill in the table below, count occurrences and find the most recent `ts` (format as `YYYY-MM-DD HH:MM`). For the `(commits)` row, use the `BRANCH_COMMITS` count from the Setup block.
+
+**Status per row:**
+- 0 runs: Status = `—`, Last Run = `—`
+- > 0 runs: Status = `DONE`, Last Run = most recent timestamp
+- `(commits)` row: Status = `DONE` if commits > 0, `—` if 0; Last Run = `—` always
+
+**Required column:**
+- `YES` for: `/plan-eng-review`, `(commits)`, `/review`, `/ship`
+- `no` for all others
+
+**VERDICT logic:**
+- Count required YES rows where Status = `—` (not yet run), including `(commits)` if 0 commits
+- 0 REMAINING: `CLEARED — all required lifecycle steps complete`
+- All required REMAINING (nothing run): `NOT STARTED`
+- Otherwise: `IN PROGRESS — N required skill(s) REMAINING: [names]`
+
+Display:
+
+```
++====================================================================================+
+|                         GSTACK LIFECYCLE DASHBOARD                                 |
++====================================================================================+
+| Phase    | Skill               | Runs | Last Run         | Status   | Required    |
+|----------|---------------------|------|------------------|----------|-------------|
+| Think    | /office-hours       |  0   | —                | —        | no          |
+| Plan     | /plan-ceo-review    |  0   | —                | —        | no          |
+|          | /plan-eng-review    |  0   | —                | —        | YES         |
+|          | /plan-design-review |  0   | —                | —        | no          |
+|          | /plan-devex-review  |  0   | —                | —        | no          |
+|          | /autoplan           |  0   | —                | —        | no          |
+| Build    | (commits)           |  0   | —                | —        | YES         |
+| Review   | /review             |  0   | —                | —        | YES         |
+|          | /design-review      |  0   | —                | —        | no          |
+| Test     | /qa                 |  0   | —                | —        | no          |
+|          | /qa-only            |  0   | —                | —        | no          |
+|          | /benchmark          |  0   | —                | —        | no          |
+| Ship     | /ship               |  0   | —                | —        | YES         |
+|          | /land-and-deploy    |  0   | —                | —        | no          |
+| Reflect  | /retro              |  0   | —                | —        | no          |
+|          | /document-release   |  0   | —                | —        | no          |
++------------------------------------------------------------------------------------+
+| VERDICT: NOT STARTED                                                                |
++====================================================================================+
+```
+
+Fill in real values from the analytics data; the table above shows the all-zero baseline shape.
+
+### Section B: Other Observed Skills
+
+After building the lifecycle dashboard, collect any skill names from `SKILL_ANALYTICS` that are NOT in the canonical skill list above and NOT `plan-status` itself. Display a companion table:
+
+```
++================================================+
+|          OTHER OBSERVED SKILLS                 |
+|  (not yet mapped to lifecycle dashboard)       |
++================================================+
+| Skill              | Runs | Last Run           |
+|--------------------+------+--------------------|
+| /investigate       |  2   | 2026-05-10 14:00   |
+| /codex             |  1   | 2026-05-09 11:00   |
++------------------------------------------------+
+| 2 skills observed                              |
++================================================+
+```
+
+If no unlisted skills appear:
+```
+Other observed skills: none — all analytics entries are covered by the lifecycle dashboard above.
+```
+
+This table is self-maintaining: any new gstack skill that gets invoked on the project surfaces here automatically.
+
+### Section C: Plan Detail
+
+```
+## Plan Status: <plan filename>
+Branch: <branch> | As of: <today's date>
+
+### Phase Summary
+| Phase | Status | Notes |
+|-------|--------|-------|
+| Phase 0: Foundation | DONE | All gems added, initializers present |
+| Phase 1: Schema | DONE | Migrations in db/migrate/ |
+| Phase 7: RAG migration | REMAINING | NotImplementedError stubs; no RubyLLM.embed calls |
+
+### Success Criteria
+| Item | Status |
+|------|--------|
+| [ ] ruby_llm install generator accepted | DONE |
+| [ ] langchainrb removed from Gemfile | REMAINING |
+| [ ] Cross-tenant scoping test passes | REMAINING |
+| [ ] ActsAsTenant require_tenant = true | PARTIAL — dev only, not production |
+
+### Branch Commits
+| Hash    | Message                                  | In Scope |
+|---------|------------------------------------------|----------|
+| a1b2c3d | feat: add ruby_llm gem and initializer   | YES      |
+| e4f5g6h | chore: remove langchainrb from Gemfile   | YES      |
+| i7j8k9l | fix: unrelated bug in user controller    | NO       |
+
+### Pre-Migration Checklist (if present)
+List any checklist items from the plan and their resolved status.
+
+### Summary
+X of Y phases complete. Z of W success criteria met.
+Key blockers: <list the REMAINING items that appear most critical>
+Suggested next action: <one concrete next step>
+```
+
+**Notes column:** one phrase, not a sentence. Goal is a scannable dashboard, not a prose report.
+
+**Branch Commits:** For each commit in `BRANCH_COMMITS`, classify `In Scope` as YES if the commit message or changed files directly correspond to a plan deliverable (phase name, file reference, or gem reference from Step 1). Mark NO for commits unrelated to the plan.
+
+## Step 5 — Offer next action
+
+After the report, offer one of:
+- "Want me to start on [top REMAINING item]?"
+- "Want me to update the plan file's checkboxes to reflect what's done?"
+- Nothing, if the plan is 100% complete — just say so.
+
+Do not auto-start work. User decides.
diff --git a/ship/SKILL.md b/ship/SKILL.md
index 25119fb391..d592c26b14 100644
--- a/ship/SKILL.md
+++ b/ship/SKILL.md
@@ -920,6 +920,31 @@ For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <
 
 Continue to Step 2 — do NOT block or ask. Ship runs its own review in Step 9.
 
+5. Check for open plan items:
+
+```bash
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
+_PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | \
+  grep -i "$(echo "$_BRANCH" | tr '/' '-')" 2>/dev/null | sort -r | head -1)
+if [ -z "$_PLAN_FILE" ]; then
+  _PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -1)
+fi
+if [ -n "$_PLAN_FILE" ]; then
+  _REMAINING=$(grep -c "- \[ \]" "$_PLAN_FILE" 2>/dev/null || echo "0")
+  echo "PLAN_FILE: $_PLAN_FILE"
+  echo "OPEN_CHECKBOXES: $_REMAINING"
+else
+  echo "PLAN_FILE: none"
+fi
+```
+
+If `OPEN_CHECKBOXES` > 0, print an informational warning (never block):
+"Note: Plan has N open checkbox(es) in `<plan filename>`. Run /plan-status to review what's REMAINING before the PR lands — or proceed if these items are intentionally deferred."
+
+If `PLAN_FILE` is none, skip silently.
+
 ---
 
 ## Step 2: Distribution Pipeline Check
diff --git a/ship/SKILL.md.tmpl b/ship/SKILL.md.tmpl
index 5a7c34661d..61265072cf 100644
--- a/ship/SKILL.md.tmpl
+++ b/ship/SKILL.md.tmpl
@@ -95,6 +95,31 @@ For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <
 
 Continue to Step 2 — do NOT block or ask. Ship runs its own review in Step 9.
 
+5. Check for open plan items:
+
+```bash
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
+_PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | \
+  grep -i "$(echo "$_BRANCH" | tr '/' '-')" 2>/dev/null | sort -r | head -1)
+if [ -z "$_PLAN_FILE" ]; then
+  _PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -1)
+fi
+if [ -n "$_PLAN_FILE" ]; then
+  _REMAINING=$(grep -c "- \[ \]" "$_PLAN_FILE" 2>/dev/null || echo "0")
+  echo "PLAN_FILE: $_PLAN_FILE"
+  echo "OPEN_CHECKBOXES: $_REMAINING"
+else
+  echo "PLAN_FILE: none"
+fi
+```
+
+If `OPEN_CHECKBOXES` > 0, print an informational warning (never block):
+"Note: Plan has N open checkbox(es) in `<plan filename>`. Run /plan-status to review what's REMAINING before the PR lands — or proceed if these items are intentionally deferred."
+
+If `PLAN_FILE` is none, skip silently.
+
 ---
 
 ## Step 2: Distribution Pipeline Check
diff --git a/test/fixtures/golden/claude-ship-SKILL.md b/test/fixtures/golden/claude-ship-SKILL.md
index 25119fb391..d592c26b14 100644
--- a/test/fixtures/golden/claude-ship-SKILL.md
+++ b/test/fixtures/golden/claude-ship-SKILL.md
@@ -920,6 +920,31 @@ For Design Review: run `source <(~/.claude/skills/gstack/bin/gstack-diff-scope <
 
 Continue to Step 2 — do NOT block or ask. Ship runs its own review in Step 9.
 
+5. Check for open plan items:
+
+```bash
+eval "$(~/.claude/skills/gstack/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
+_PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | \
+  grep -i "$(echo "$_BRANCH" | tr '/' '-')" 2>/dev/null | sort -r | head -1)
+if [ -z "$_PLAN_FILE" ]; then
+  _PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -1)
+fi
+if [ -n "$_PLAN_FILE" ]; then
+  _REMAINING=$(grep -c "- \[ \]" "$_PLAN_FILE" 2>/dev/null || echo "0")
+  echo "PLAN_FILE: $_PLAN_FILE"
+  echo "OPEN_CHECKBOXES: $_REMAINING"
+else
+  echo "PLAN_FILE: none"
+fi
+```
+
+If `OPEN_CHECKBOXES` > 0, print an informational warning (never block):
+"Note: Plan has N open checkbox(es) in `<plan filename>`. Run /plan-status to review what's REMAINING before the PR lands — or proceed if these items are intentionally deferred."
+
+If `PLAN_FILE` is none, skip silently.
+
 ---
 
 ## Step 2: Distribution Pipeline Check
diff --git a/test/fixtures/golden/codex-ship-SKILL.md b/test/fixtures/golden/codex-ship-SKILL.md
index 7770a8906e..d505ca6944 100644
--- a/test/fixtures/golden/codex-ship-SKILL.md
+++ b/test/fixtures/golden/codex-ship-SKILL.md
@@ -909,6 +909,31 @@ For Design Review: run `source <($GSTACK_ROOT/bin/gstack-diff-scope <base> 2>/de
 
 Continue to Step 2 — do NOT block or ask. Ship runs its own review in Step 9.
 
+5. Check for open plan items:
+
+```bash
+eval "$($GSTACK_ROOT/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
+_PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | \
+  grep -i "$(echo "$_BRANCH" | tr '/' '-')" 2>/dev/null | sort -r | head -1)
+if [ -z "$_PLAN_FILE" ]; then
+  _PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -1)
+fi
+if [ -n "$_PLAN_FILE" ]; then
+  _REMAINING=$(grep -c "- \[ \]" "$_PLAN_FILE" 2>/dev/null || echo "0")
+  echo "PLAN_FILE: $_PLAN_FILE"
+  echo "OPEN_CHECKBOXES: $_REMAINING"
+else
+  echo "PLAN_FILE: none"
+fi
+```
+
+If `OPEN_CHECKBOXES` > 0, print an informational warning (never block):
+"Note: Plan has N open checkbox(es) in `<plan filename>`. Run /plan-status to review what's REMAINING before the PR lands — or proceed if these items are intentionally deferred."
+
+If `PLAN_FILE` is none, skip silently.
+
 ---
 
 ## Step 2: Distribution Pipeline Check
diff --git a/test/fixtures/golden/factory-ship-SKILL.md b/test/fixtures/golden/factory-ship-SKILL.md
index baae7421d9..b16973198e 100644
--- a/test/fixtures/golden/factory-ship-SKILL.md
+++ b/test/fixtures/golden/factory-ship-SKILL.md
@@ -911,6 +911,31 @@ For Design Review: run `source <($GSTACK_ROOT/bin/gstack-diff-scope <base> 2>/de
 
 Continue to Step 2 — do NOT block or ask. Ship runs its own review in Step 9.
 
+5. Check for open plan items:
+
+```bash
+eval "$($GSTACK_ROOT/bin/gstack-slug 2>/dev/null)" 2>/dev/null || true
+_PLAN_DIR="${GSTACK_HOME:-$HOME/.gstack}/projects/${SLUG:-unknown}"
+_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
+_PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | \
+  grep -i "$(echo "$_BRANCH" | tr '/' '-')" 2>/dev/null | sort -r | head -1)
+if [ -z "$_PLAN_FILE" ]; then
+  _PLAN_FILE=$(find "$_PLAN_DIR" -name "*.md" 2>/dev/null | grep -E "ceo-plans|eng-plans" | sort -r | head -1)
+fi
+if [ -n "$_PLAN_FILE" ]; then
+  _REMAINING=$(grep -c "- \[ \]" "$_PLAN_FILE" 2>/dev/null || echo "0")
+  echo "PLAN_FILE: $_PLAN_FILE"
+  echo "OPEN_CHECKBOXES: $_REMAINING"
+else
+  echo "PLAN_FILE: none"
+fi
+```
+
+If `OPEN_CHECKBOXES` > 0, print an informational warning (never block):
+"Note: Plan has N open checkbox(es) in `<plan filename>`. Run /plan-status to review what's REMAINING before the PR lands — or proceed if these items are intentionally deferred."
+
+If `PLAN_FILE` is none, skip silently.
+
 ---
 
 ## Step 2: Distribution Pipeline Check
diff --git a/test/fixtures/plans/sample-ruby-llm-plan.md b/test/fixtures/plans/sample-ruby-llm-plan.md
new file mode 100644
index 0000000000..32c1541e08
--- /dev/null
+++ b/test/fixtures/plans/sample-ruby-llm-plan.md
@@ -0,0 +1,33 @@
+# CEO Plan: Implement ruby_llm integration
+**Branch:** add-ruby-llm | **Date:** 2026-04-01 | **Author:** example
+
+## Phase 0: Foundation
+
+Add the ruby_llm gem and configure the client. Create an initializer that loads the
+API key from the environment and sets the default model.
+
+**Files:**
+- `config/initializers/ruby_llm.rb` — new initializer
+- `app/services/llm_service.rb` — new service wrapping the client
+
+**Success criteria:**
+- [x] ruby_llm gem added to Gemfile and installed successfully
+- [x] config/initializers/ruby_llm.rb created with API key config
+- [ ] LlmService exposes a `complete(prompt)` method
+- [ ] LlmService handles API errors and returns a structured result
+
+## Phase 1: First Feature
+
+Build a summarization endpoint backed by ruby_llm. Add a model and controller to
+store requests and return streamed responses.
+
+**Files:**
+- `app/models/summary_request.rb` — new model
+- `app/controllers/summaries_controller.rb` — new controller
+
+**Gem:**
+- `ruby_llm` (already added in Phase 0)
+
+**Success criteria:**
+- app/models/summary_request.rb exists with validations
+- POST /summaries creates a SummaryRequest and enqueues a job
diff --git a/test/helpers/touchfiles.ts b/test/helpers/touchfiles.ts
index 5043884c32..6e6dc288cf 100644
--- a/test/helpers/touchfiles.ts
+++ b/test/helpers/touchfiles.ts
@@ -213,6 +213,9 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   // Learnings
   'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts'],
 
+  // Plan Status
+  'plan-status': ['plan-status/**', 'test/fixtures/plans/sample-ruby-llm-plan.md'],
+
   // Session Intelligence (timeline, context recovery, /context-save + /context-restore)
   'timeline-event-flow':            ['bin/gstack-timeline-log', 'bin/gstack-timeline-read'],
   'context-recovery-artifacts':     ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**'],
@@ -549,6 +552,9 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
   // Learnings — gate (functional guardrail: seeded learnings must appear)
   'learnings-show': 'gate',
 
+  // Plan Status — gate (deterministic, read-only, filesystem-only fixture, < $0.50/run)
+  'plan-status': 'gate',
+
   // Document-release — gate (CHANGELOG guardrail)
   'document-release': 'gate',
 
diff --git a/test/skill-e2e-plan-status.test.ts b/test/skill-e2e-plan-status.test.ts
new file mode 100644
index 0000000000..401288a553
--- /dev/null
+++ b/test/skill-e2e-plan-status.test.ts
@@ -0,0 +1,128 @@
+/**
+ * Gate-tier E2E for /plan-status.
+ *
+ * Verifies the skill can resolve a plan file, classify phase/criteria items,
+ * and produce a status report. Uses a filesystem-only fixture (no git commits
+ * that match plan deliverables) — the git evidence path is not exercised here.
+ *
+ * Gate tier: deterministic, read-only, filesystem-only fixture, < $0.50/run.
+ */
+
+import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
+import { runSkillTest } from './helpers/session-runner';
+import {
+  ROOT, runId,
+  describeIfSelected, testConcurrentIfSelected,
+  logCost, recordE2E,
+  createEvalCollector, finalizeEvalCollector,
+} from './helpers/e2e-helpers';
+import { spawnSync } from 'child_process';
+import * as fs from 'fs';
+import * as path from 'path';
+import * as os from 'os';
+
+const evalCollector = createEvalCollector('e2e-plan-status');
+
+describeIfSelected('Plan Status E2E', ['plan-status'], () => {
+  let workDir: string;
+  let gstackHome: string;
+
+  beforeAll(() => {
+    workDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-plan-status-'));
+    gstackHome = path.join(workDir, '.gstack-home');
+
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: workDir, stdio: 'pipe', timeout: 5000 });
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+    fs.writeFileSync(path.join(workDir, 'README.md'), '# Test project\n');
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial commit']);
+
+    // Install the plan-status skill
+    const skillDir = path.join(workDir, '.claude', 'skills', 'plan-status');
+    fs.mkdirSync(skillDir, { recursive: true });
+    fs.copyFileSync(path.join(ROOT, 'plan-status', 'SKILL.md'), path.join(skillDir, 'SKILL.md'));
+
+    // Copy bin scripts referenced by the preamble
+    const binDir = path.join(workDir, 'bin');
+    fs.mkdirSync(binDir, { recursive: true });
+    for (const script of ['gstack-update-check', 'gstack-slug', 'gstack-config', 'gstack-repo-mode']) {
+      const src = path.join(ROOT, 'bin', script);
+      if (fs.existsSync(src)) {
+        fs.copyFileSync(src, path.join(binDir, script));
+        fs.chmodSync(path.join(binDir, script), 0o755);
+      }
+    }
+
+    // Copy the fixture plan
+    fs.copyFileSync(
+      path.join(ROOT, 'test', 'fixtures', 'plans', 'sample-ruby-llm-plan.md'),
+      path.join(workDir, 'fixture-plan.md'),
+    );
+
+    // Create a minimal gstack analytics file (empty — no prior skill runs)
+    const analyticsDir = path.join(gstackHome, 'analytics');
+    fs.mkdirSync(analyticsDir, { recursive: true });
+    fs.writeFileSync(path.join(analyticsDir, 'skill-usage.jsonl'), '');
+
+    // Routing CLAUDE.md
+    fs.writeFileSync(path.join(workDir, 'CLAUDE.md'), `# Test project
+
+## Skill routing
+When the user invokes /plan-status, ALWAYS use the Skill tool first.
+
+Environment:
+- The plan-status skill is at ./.claude/skills/plan-status/SKILL.md
+- Bin scripts are at ./bin/ — replace ~/.claude/skills/gstack/bin/ with ./bin/
+- Use GSTACK_HOME="${gstackHome}" for all gstack bin scripts
+- The analytics file is at ${gstackHome}/analytics/skill-usage.jsonl
+`);
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(workDir, { recursive: true, force: true }); } catch {}
+    finalizeEvalCollector(evalCollector);
+  });
+
+  testConcurrentIfSelected('plan-status', async () => {
+    const result = await runSkillTest({
+      prompt: `Run /plan-status on the plan file at ./fixture-plan.md.
+
+IMPORTANT:
+- Use GSTACK_HOME="${gstackHome}" for all gstack bin scripts.
+- The bin scripts are at ./bin/ (replace ~/.claude/skills/gstack/bin/ with ./bin/ in any commands).
+- The plan file is ./fixture-plan.md — use it directly, do not search for other plans.
+- Do NOT use AskUserQuestion.
+- Do NOT make any file edits.
+- Produce the full status report and stop after Step 5.`,
+      workingDirectory: workDir,
+      maxTurns: 20,
+      allowedTools: ['Bash', 'Read', 'Glob', 'Grep'],
+      timeout: 180_000,
+      testName: 'plan-status',
+      runId,
+    });
+
+    logCost('/plan-status', result);
+
+    const output = result.output;
+
+    // Loose assertions: report header present + at least one status label
+    const hasHeader = /plan.?status/i.test(output);
+    const hasDone = /\bDONE\b/.test(output);
+    const hasRemaining = /\bREMAINING\b/.test(output);
+    const hasStatusLabel = hasDone || hasRemaining;
+
+    const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
+
+    recordE2E(evalCollector, '/plan-status', 'Plan status E2E', result, {
+      passed: exitOk && hasHeader && hasStatusLabel,
+    });
+
+    expect(exitOk).toBe(true);
+    expect(hasHeader).toBe(true);
+    expect(hasStatusLabel).toBe(true);
+  }, 240_000);
+});