chore(cowork): adopt cowork-harness 0.16.0 (additive — H10 decider fix)

.claude-plugin/marketplace.json

@@ -1,6 +1,5 @@
 {
   "name": "lool-founder-skills",
-  "description": "Skills for startup founders by lool ventures",
   "owner": {"name": "lool ventures"},
   "plugins": [
     {

.github/ISSUE_TEMPLATE/bug_report.md

@@ -28,7 +28,10 @@ What you expected to happen instead.
 
 - [ ] Market Sizing
 - [ ] Deck Review
+- [ ] Financial Model Review
 - [ ] IC Simulation
+- [ ] Competitive Positioning
+- [ ] Cap Table
 - [ ] Other / not skill-specific
 
 ## Additional context

.github/workflows/ci.yml

@@ -29,6 +29,7 @@ jobs:
       - run: uv run mypy founder-skills/skills/ic-sim/scripts/
       - run: uv run mypy founder-skills/skills/financial-model-review/scripts/
       - run: uv run mypy founder-skills/skills/competitive-positioning/scripts/
+      - run: uv run mypy founder-skills/skills/cap-table/scripts/
       - run: uv run mypy founder-skills/tests/
 
   test:

.github/workflows/cowork-replay.yml

@@ -0,0 +1,80 @@
+name: cowork-replay
+
+# Token-free, agent-free PR gate for the fleet cowork-harness cassettes (cowork-harness >= 0.9.0):
+#   1. lint            — scenario no-silent-false-green invariants (CLI subcommand since 0.4.0)
+#   2. privacy gate    — HARD: PII/host-path scan (--skip-staleness). A finding fails the job.
+#   3. staleness gate  — WARN: --skip-privacy under continue-on-error. A skill edit re-stales the
+#                        affected cassette(s) and CI can't re-record, so this stays warn-not-fail.
+#                        0.9.0 makes the WARN *actionable*: `fileSigs` names the exact changed file
+#                        (e.g. "1 changed: skills/x/SKILL.md") instead of a coarse bucket — so a real
+#                        drift points right at the file. Re-record on a cadence (see cowork-tests/README.md).
+#   4. replay          — content + manifest-backed file_exists/artifact_json across the whole dir.
+# No model tokens, no Docker, no staged agent binary → runs on a stock GitHub-hosted runner.
+#
+# The LIVE lane (recording cassettes) needs the staged Cowork agent ELF (not redistributable, not on
+# hosted runners) → self-hosted/local only. See cowork-tests/README.md.
+
+on:
+  pull_request:
+    paths:
+      - 'founder-skills/skills/**'
+      - 'founder-skills/scripts/**'
+      - 'founder-skills/references/**'
+      - 'cowork-tests/**'
+      - '.github/workflows/cowork-replay.yml'
+
+jobs:
+  replay:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - run: npm i -g 'cowork-harness@0.16.0'   # EXACT pin (not a >= floor): pre-1.0 minors can break — a future cassette-format bump would replay-FAIL committed cassettes in CI, which cannot re-record. Bump deliberately after the ~30s token-free gate below (lint + privacy + replay) is green on the new version. This 0.15.0→0.16.0 bump was verified that way: lint + privacy + canary + replay all green on 0.16.0 against the committed cassettes. 0.13/0.14/0.15/0.16 carry NO breaking changes, cassette format stays **v6**, agent ELF stays 2.1.181, baseline stays 1.15200.0 → the bump is purely additive, no re-record forced. (Replay re-emits the RECORDED answers — it never runs the decider — so replay-green proves format compat, not decider behavior; 0.16's new scripted-`choose:` prefix-anchor tier is lowest-priority + fires only at RECORD time, so it cannot change a passing replay.) New since 0.12.0: `inspect <run>` (artifact digest, works on torn-down runs) + partial-run salvage on an unanswered gate + capability pre-flight `requires_capabilities`/exit-3 (0.13; `runs gc`→top-level `prune`, decider near-miss label tolerance); `replay --output-format json` exposes `staleness[]`/`skippedAssertions` + a `--fail-on-skill-drift` release gate (0.14); refined staleness diagnosis — a scoped skill now reports BOTH its own + shared-root drift, per-file detail on the replay lane (0.15); **H10 decider fix (0.16): `--decider-llm` replies by option NUMBER (no more option-echo whiff) + answers multiSelect; new `--decider-model <id>` override (live/authoring only — never reaches a committed cassette); scripted `choose:`/`--answer` prefix-anchor (boundary `startsWith`, fails loud on ambiguity — prefix-only); `docs/debugging.md` on-ramp**. DELIBERATELY NOT adopting `--fail-on-skill-drift` here: the cap-table skill is under active modification and the fleet shares roots (`scripts/`/`references/`/`agents/`), so it would red all 13 on every skill PR — keep the staleness gate WARN-only (continue-on-error) below; the baseline+skill staleness clears on the next release-cadence `rerecord.sh`. Carries forward: `record --concurrency` (0.11); bundled PyYAML + live-decider flags + `stalled` verdict (0.10); git-tracked staleness boundary + fileSigs (0.9); class-scoped allows (0.5) + `--skip-staleness`/`--skip-privacy` (0.6).
+
+      - name: Lint scenarios (no silent false-greens)
+        run: cowork-harness lint cowork-tests/scenarios/   # 0.9.0: lint accepts a directory
+
+      - name: Privacy gate (HARD)
+        # The PII guard that actually matters here is **synthetic-only recording**: every cassette's
+        # subject is a fictional company (Cadence / Acmecorp), so no real founder/company data exists to
+        # leak. Given that, the allowlist tunes the default scanner classes — using 0.5.0's CLASS-SCOPED
+        # flags so an allow can't bleed across classes (the 0.5.0 hardening):
+        #   * currency (`--allow`) — synthetic dollar figures the skills emit.
+        #   * DOMAIN class (`--allow-domain`) — allowed wholesale. The research/coaching skills
+        #     (market-sizing, comp-pos, deck-review) cite 150+ PUBLIC third-party domains: public, non-PII;
+        #     a real leak would surface a real NAME (caught by synthetic-only review) and a real EMAIL
+        #     (caught below), not merely a domain. An enumerated 150-domain list would be unmaintainable.
+        #     `--allow-domain` applies ONLY to domain findings — structurally it cannot clear an email
+        #     (0.5.0 replaced our earlier `^...$`-anchored generic `--allow`, which had to be hand-anchored
+        #     to avoid suppressing emails — see the F-2 footgun).
+        #   * email (`--allow-email`) — only the SYNTHETIC domains (acmecorp.com — fictional deck co;
+        #     example.com — RFC-2606 reserved, synthetic Carta stakeholders). Any OTHER email
+        #     (e.g. a real founder@realstartup.com) FAILS the gate — the live PII tripwire.
+        # The email tripwire is the one guard this posture leans on hardest. The SAME $ALLOW is reused for
+        # an email CANARY below: a purpose-built cassette carrying a non-synthetic email
+        # (analyst@realstartup.com) MUST trip. If it stops tripping, the tripwire is disabled → job fails.
+        # Defining $ALLOW once means the gate and the canary can never drift apart.
+        run: |
+          # Canonical allowlist — single source of truth shared with cowork-tests/rerecord.sh.
+          source cowork-tests/privacy-allowlist.sh
+          # Real gate: committed cassettes must be clean under the allowlist.
+          cowork-harness verify-cassettes cowork-tests/cassettes/ --skip-staleness "${ALLOW[@]}"
+          # Email canary: the SAME allowlist must still FLAG a non-synthetic email. If verify-cassettes
+          # exits 0 here, the email class is no longer catching real addresses → fail loudly.
+          if cowork-harness verify-cassettes cowork-tests/canary/email-canary.cassette.json --skip-staleness "${ALLOW[@]}"; then
+            echo "::error:: email canary did NOT trip — the email PII tripwire is disabled (a real email would pass). Check --allow-email is not over-broad and that no generic --allow matches an address."
+            exit 1
+          fi
+          echo "email canary tripped as expected — email tripwire is live."
+
+      - name: Staleness gate (WARN — does not fail the job; see header F8)
+        continue-on-error: true
+        run: cowork-harness verify-cassettes cowork-tests/cassettes/ --skip-privacy
+
+      - name: Replay content + artifact_json assertions (token-free)
+        run: cowork-harness replay cowork-tests/cassettes/ --output-format json

.github/workflows/version-check.yml

@@ -28,6 +28,12 @@ jobs:
               founder-skills/tests/*) return 1 ;;
               .github/*) return 1 ;;
               docs/*) return 1 ;;
+              # In-plugin content ships to users and DOES require a bump, even
+              # though it is Markdown — list these before the generic *.md rule.
+              # (Per VERSIONING.md: SKILL.md / agent / reference changes = PATCH.)
+              founder-skills/skills/*/SKILL.md) return 0 ;;
+              founder-skills/skills/*/references/*.md) return 0 ;;
+              founder-skills/agents/*.md) return 0 ;;
               *.md) return 1 ;;
               .gitignore|.editorconfig) return 1 ;;
               uv.lock) return 1 ;;

.gitignore

@@ -12,9 +12,11 @@ docs/internal/
 uv.lock
 .worktrees/
 artifacts/
+runs/
 cap-table-workspace/
 docs/plans/
 test-feedback-plugin/
 scripts/sync-test-repo.sh
 .superpowers/
 docs/superpowers/
+.playwright-mcp/