Skip to content

v1.94.22.0 feat(skills): when-to-use descriptions, wider triggers and contract blocks for /investigate, /review, /qa, /verify (GST-1088 lane B) - #3909

Merged
capy-ai[bot] merged 13 commits into
mainfrom
capy/gst-1088-lane-b
Nov 3, 2026
Merged

capy-ai[bot] merged 13 commits into
mainfrom
capy/gst-1088-lane-b

Conversation

@garrytan

@garrytan garrytan commented Nov 3, 2026 •

Copy link
Copy Markdown
Owner
{
  "schema_version": 1,
  "pr": 3909,
  "head": "58aeee7c62383c41e3da7b7a7cb75b7f8f6f6100",
  "version": "1.94.15.0",
  "base": "main",
  "gate": {
    "targeted": {
      "pass": 1327,
      "fail": 0,
      "skip": 21
    }
  },
  "session_kind": "unattended",
  "head_tree": "69a8e0088463b901c0ba7e5f4da25d27989721ad",
  "product_patch_id": "4c0386b6ee36a71dc840368dba98c24533874e9a",
  "gstack_version": "1.94.15.0",
  "review_depth": {
    "depth": "full",
    "class": "code",
    "runtime_lines": 217,
    "rules": "19881e1ecf7ed1ad",
    "base": "bf2bcf14b08d774291613c8073674a0e90eb4f9f",
    "registry": "bf2bcf14b08d774291613c8073674a0e90eb4f9f",
    "gate_scan": {
      "tagged": 0,
      "head": "58aeee7c62383c41e3da7b7a7cb75b7f8f6f6100"
    },
    "reasons": [
      "risk:security",
      "runtime=217"
    ],
    "risk": [
      "security"
    ]
  },
  "pregate": "requires-remote cleared @69a8e0088463 (7 checks, current for 58aeee7c6238)",
  "requires_remote": [
    "free-tests.yml/macos-named-regressions: https://github.com/garrytan/gstack/actions/runs/41629884217/attempts/1",
    "windows-smoke.yml/windows-smoke: https://github.com/garrytan/gstack/actions/runs/41629884198/attempts/1",
    "pregate.json/remote_gate: remote-gate tree=69a8e0088463 tests=34869 skipped=112 runs=41629884217/1 profiles=ci-reuse/free-tests heads=58aeee7c6238 verified=2026-11-03T11:49:24.975Z"
  ],
  "issues": {
    "fixes": [],
    "refs": [],
    "flakes": []
  },
  "docs": {
    "status": "current",
    "scope": "README.md, AGENTS.md, CLAUDE.md, CONTRIBUTING.md, docs/ and gstack/llms.txt against the lane-B diff at 58aeee7"
  },
  "review_loop": {
    "passes": 2,
    "blocking_found": 1,
    "deferred": 0,
    "noted": 3,
    "fixed": 4,
    "scope": "frozen",
    "fix_checks": 3,
    "rounds": 5,
    "unrecorded": 1,
    "ledgers_read": 5,
    "dispatches": {
      "specialist": 6,
      "red-team": 2
    }
  }
}

What changed

/review now opens with a Done means list rendered from its contract: block, so the agent knows what must exist before it stops

/review now opens with a "Done means" list rendered from its contract: block, so the agent knows what must exist before it stops.

Before/after as text: /review now opens with a Done means list rendered from its contract: block, so the agent knows what must exist before it stops
--- Before · review/SKILL.md § Done means at 54606c5 · source text (section not present before)
+++ After · review/SKILL.md § Done means on this branch · source text
+## Done means
+Finish only when each of these exists (contract v1):
+
+- `specialists-dispatched`: the specialist selection printed (`Dispatching N specialists:` ...), then one Agent dispatch per specialist it names (none when a small diff skips them).
+- `adversarial-pass`: an Agent dispatch for the adversarial pass, its prompt including "Think like an attacker and a chaos engineer".
+- `review-report`: a `Pre-Landing Review` with Gate edits filled in (`none: <why>` where the skill's own stop rule leaves one empty).

Why

Untold, Opus 5.5 never opened /investigate in 252 trials (Run D, gstack-evals#140), and a when-to-use description raised GPT-6.1 Sol's open rate from 9.5% to 27.0% in the same run. Claude Code's catalog shows only a description's first sentence, so /investigate, /review, /qa and /verify now open with a "Use when ..." sentence. /investigate and /review also say up front what "done" means, so a run that skips the specialists, the adversarial pass or the report is visibly incomplete.

Blast radius

Every host render of these four skills changes, plus gstack/llms.txt, the Hermes trigger lead and router lines in lib/harness-register.ts. That is safe because the generator owns all of it: gen:skill-docs --dry-run reports 0 stale files, and the catalog, context, host-config, size-guard and parity tests pass at 981a3ce (script ran). The Done-means list drops any item whose step the host or the loadout removes, so no render asks for a step it doesn't contain (red-team read all 13 renders, file read).

Approvals

Approved: yes (record r-74843981c3d6). The full approval record stays private: this repository is public or its visibility is unknown.

APPROVALS_RENDER: redacted (repository visibility public); gstack-approvals list shows the full record

Summary

GST-1088 lane B (plan: GStack Minder drive renders/GSTA-256/plan-v2.md, approved by Garry with "do it" on gate rev 1). Agents weren't opening the right skill because the catalog line said what each skill is, not when to use it. This PR makes the first sentence a when-clause, widens the trigger lists people actually type, adds contract: blocks to /investigate and /review, and renders each block as a "Done means" list at the top of the skill.

Descriptions

Claude Code's catalog keeps only the first sentence (applyCatalogTrim), so the when-clause comes first. For the core skills /review and /qa, test/proactive-core-set.test.ts also requires that first sentence to carry one of the skill's own trigger phrases and the full description to carry every one. /review's "Proactively suggest before a merge." sits on its own line because skill-validation requires it.

Skill Claude catalog before Claude catalog after
/investigate Systematic debugging with root cause investigation. Use when a test fails, code errors or output is wrong: find the root cause, then fix it.
/review Review this PR's diff. Use when you review this PR's diff.
/qa Test the site, API or CLI and fix the bugs it finds. Use when you test the site, API or CLI and fix bugs.
/verify Build loop while coding: run the repo's checks and the tests /ship would pick, fix, repeat until green. Use when coding: run the checks and tests /ship picks until green.
Full descriptions (Codex, Gemini, Copilot, Hermes, OpenClaw and other full-description hosts)
  • /investigate before: Systematic debugging with root cause investigation. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". (gstack)
    after: Use when a test fails, code errors or output is wrong: find the root cause, then fix it. Systematic debugging; Iron Law: no fixes without root cause. Fits a failing build, test, script, service or config, an error message or stack trace, wrong or missing output, or broken data, before any edit that fixes it. (gstack)
  • /review before: Review this PR's diff. Checks it against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)
    after: Use when you review this PR's diff. Checks it for SQL safety, LLM trust boundaries, conditional side effects and bugs that pass CI and break production. Fits "look over my diff", "review my changes", "code review", "check my diff" or "pre-landing review". Proactively suggest before a merge. (gstack)
  • /qa: the first sentence becomes "Use when you test the site, API or CLI and fix bugs.", and the old "Use when asked to ..." sentence becomes "Fits ...". The rest is unchanged.
  • /verify before: Build loop while coding: run the repo's checks and the tests /ship would pick, fix, repeat until green. Never green when no test covers a change. Use when asked to "verify", "check my work", "run the checks", "make it green", or after each change before /ship. (gstack)
    after: Use when coding: run the checks and tests /ship picks until green. Build loop: run the repo's checks and the tests /ship would pick, fix, repeat. Never green when no test covers a change. Fits "verify", "check my work", "run the checks", "make it green", or after each change before /ship. (gstack)

Triggers

Skill Before After
/investigate debug this, fix this bug, why is this broken, root cause analysis, investigate this error debug this, fix this bug, test fails, failing test, why is this broken, this doesn't work, build is broken, stack trace, investigate this error, root cause analysis
/review review this pr, code review, check my diff, pre-landing review review this pr, look over my diff, code review, check my diff, review my changes, pre-landing review
/qa qa test this, find bugs on site, test the site unchanged: its parity cap had 9 bytes of room, so the parent ruled no cap raise for /qa
/verify verify my change, run the checks, make the tests pass, check my work before ship verify my change, run the checks, make the tests pass, make it green, is it green, check my work before ship

Where these reach (lib/skill-triggers.ts, scripts/gen-skill-docs.ts withTriggerLead, lib/harness-register.ts skillDirs):

  • Claude Code reads neither triggers: nor contract:. It sees only the new first sentence and the Done-means list.
  • Hermes (the only host with a descriptionLead) gets a 57-character Use for: <triggers> lead built from the trigger list. For example, /investigate's lead becomes "Use for: debug this, fix this bug, test fails." and /review's becomes "Use for: review this pr, look over my diff, code review.".
  • gbrain's host render keeps triggers: in its frontmatter.
  • Router lines in lib/harness-register.ts (dots, generic and OpenClaw router mode) now take the new "Use when ..." sentence. The Claude-trimmed description used to have no trigger sentence, so those lines used to fall back to the trigger list. The widened triggers therefore no longer reach router lines for these four skills.
  • Lane A's routing hook (separate PR, off by default) will read triggers:.

Contract blocks and "Done means"

The contract: blocks follow the frozen v1 schema ({ version: 1, items: [{ id, kind, ... }] }):

  • /investigate: report_labels (DEBUG REPORT with Symptom, Root cause, Fix, Evidence, Regression test and Status) and check_after_last_edit.
  • /review: selected_specialists_dispatched (marker Dispatching N specialists: from Step 4.5), agent_dispatch (Think like an attacker and a chaos engineer, from Step 4.8's adversarial prompt) and report_labels (Pre-Landing Review with Gate edits).

{{CONTRACT_DONE_MEANS}} (scripts/resolvers/contract-done-means.ts, registered in scripts/resolvers/index.ts) renders each block at the top of the body:

  • It leaves out an item when the host suppresses its backing resolver (REVIEW_ARMY, ADVERSARIAL_STEP) or the loadout excludes its section (section:review/review-army, section:review/adversarial).
  • The specialists item allows the small-diff skip ("none when a small diff skips them"), and report_labels items allow none: <why> where the skill's own stop rule leaves a label empty.
  • The sentence naming gstack-skill-contract check and waive follows an explicit CONTRACT_CHECKER_SHIPPED flag, and test/skill-descriptions.test.ts fails while the flag and the bin disagree. Main has shipped bin/gstack-skill-contract since v1.94.6.0 feat(hooks): opt-in skill routing and contract Stop hooks with gstack-skill-contract (GST-1088 lane A) #3912 (v1.94.6.0), so this PR merges main at bf2bcf1 (GStack Minder's rule 19 grant), sets the flag to true and renders the 240-character sentence under the list in /investigate and /review. The flag left at false is what turned train 102 red (runs 41625996288 and 41627137651).
  • It never offers the agent the skill_contracts off switch (gate rev 2 d5a). A placeholder without a block, invalid YAML or a schema break stops the render with CONTRACT_INVALID <file>: <problem>. Fix: edit <skill>/SKILL.md.tmpl, then bun run gen:skill-docs.

Raised caps

The growth comes from F1's "Done means" list and the contract: block, both from GST-1088's plan (renders/GSTA-256/plan-v3.md line 74, r2-d6 "Done-means list"). Garry said "do it" on gate rev 1 and on gate rev 2 (2026-11-03), which made F1 and D1 final. GStack Minder ruled that the PR making the checker flip re-pins /review by the measured amount with no slack. Lane C's diet is expected to bring /review back under the old caps. Every value below is measured on the merged tree at 981a3ce.

Entry Before this PR After the F1 list After the flip (this PR's head)
carve-guards review maxSkeletonBytes 59,073 59,774 60,014
carve-guards review maxSizeRatio 1.3180 1.3261 (143,907 / 108,523) 1.3283 (144,147 / 108,523 = 1.328262, rounded up)
allowlist agy/gstack-review 104,182 104,488 104,728
allowlist codex/gstack-review 103,705 104,011 104,251
allowlist copilot/gstack-review 103,763 104,069 104,309
allowlist cursor/gstack-review 122,053 122,541 122,781
allowlist factory/gstack-review 125,826 126,314 126,554
allowlist gemini/gstack-review 103,585 103,891 104,131
allowlist kiro/gstack-review 121,877 122,365 122,605
allowlist opencode/gstack-review 122,675 123,163 123,403
allowlist slate/gstack-review 121,965 122,453 122,693

No fixed cap moved: the 5,315-token ratchet, DRIVER.md's 12,288 bytes, the 61,420-byte global skeleton cap, the 800-line module size and PART_MAX 24,576 all pass (context-budget-ratchet, module-size-ratchet, ship-parts). The carve-guards comments now cite the flip and plan-v3 line 74.

Sibling PR #3837 also edits the allowlist (12 gstack-autoplan pins down by 17). A trial merge of this head with #3837's head 93bba94 conflicts only because the edited lines sit next to each other: the two PRs change disjoint keys (12 autoplan keys there, 9 review keys here, no overlap). Resolution: keep both sets. On the resolved tree, skill-md-size-guard, parity-suite and skill-descriptions pass (115 pass, 0 fail).
/qa gets no cap raise. Its trigger widening was dropped, and its opening sentence reads "... and fix bugs." rather than "... and fix its bugs.": main at 106fd39 already sits exactly at qa's cap (95,983 union bytes), so this PR adds no bytes to /qa. Merged with main, /qa measures 95,983, a ratio of 1.141989 against the 1.1420 cap.

Test change

test/harness-register.test.ts:251 changes from not.toMatch(/^Use /) to not.toMatch(/^Use for: /). The old check stood in for "OpenClaw doesn't get Hermes's trigger lead", and it relied on review's own description not starting with "Use". That description now starts with "Use when", so the check now tests for Hermes's Use for: lead directly.

Test Coverage

test/skill-descriptions.test.ts (new) was written first and failed 14 times before the frontmatter edits. It covers the when-clause openings within the catalog, lead and host caps, trigger length and overlap, ten sample prompts that each route to exactly one skill, the v1 schema and printed markers for every contract block, each renderer item kind, host and loadout filtering, the checker flag, and malformed blocks failing with the file and the fix.

Tests ran: targeted 1526 pass, 0 fail, 21 skip at 981a3ce (the 23 files below plus skill-contract, skill-contract-stop-hook, skill-route and the QA-only cross-host test); the preflight lane ran 1327 tests, exit 0. CI's Free Tests run 41628918123 is green at tree 07edccb5c6c2.

Pre-Landing Review

Pass 1 (full: batched testing, security and state-machines specialist, Red Team, native adversarial, outside voice openai/gpt-6.1-sol): 3 informational findings fixed (5255dd9) and 3 findings at the blocking floor fixed (93d0a20, 3d16d82): excluded loadout sections stayed required in the list, the list left no honest stop for an empty report label, and the rendered text depended on whether bin/gstack-skill-contract exists. Pass 2 (full on the fix range, as gstack-review-plan printed): clean, one informational note. After main moved, CI at d2f1e29 failed /qa's parity cap on the merge ref; GStack Minder granted one scoped fix-check ("Lane B #3909: grant fix-check qa trim.") for the 4-byte /qa trim in cc9b9b9, and that fix-check was clean (one informational note about this draft, fixed). After the rule 19 merge of main and the checker flip, GStack Minder granted one scoped fix-check on the flip hunk; it was clean with one informational note (below).

REVIEW_LOOP: passes=2 blocking_found=1 deferred=0 noted=3 fixed=4 scope=frozen unrecorded=1 ledgers_read=5 fix_checks=3 dispatches=8

Gate edits: 4 listed, 3 read, 0 findings — 0 kept, 0 restored, 0 open. The listed edits are the owner-approved re-pins above (test/helpers/carve-guards.ts review caps, test/fixtures/skill-md-size-allowlist.json gstack-review rows) and the test/harness-register.test.ts:251 assertion.

Outside review: completed (openai/gpt-6.1-sol), one finding, fixed.

Review notes

  • The Done-means list has no wording for whole-run early exits ("Nothing to review", BLOCKED, NEEDS_CONTEXT); a model obeying it on an empty diff may still dispatch the adversarial pass. Lane A's checker should treat a printed early-exit marker as satisfying the contract (pass 2 Red Team, informational).
  • The rendered sentence names gstack-skill-contract bare, and a standard install doesn't put that bin on PATH (other bins in these skills go through ~/.claude/skills/gstack/bin/). A waive run as written exits 127 and its waiver is dropped, so the Stop hook blocks once more. It fails no test and loses no data; rendering the host-resolved path changes the shared sentence and the pins, so it is left to lane A (flip fix-check, informational).
  • docs/skill-routing-and-contracts.md doesn't mention the Done-means list, and its /investigate example uses id repro-after-fix where the template uses check-after-last-edit (docs audit, optional).
  • On Codex the adversarial item still names an Agent dispatch; whether a host without delegation should suppress ADVERSARIAL_STEP is outside this lane (adversarial, low).
  • Trigger phrases overlap by substring across skills; matching is lane A's rule, and the ten sample prompts route to one skill each (adversarial, low).

Exploratory QA

Not run: no runnable surface changed; the change is skill text and its generator.

Design Review

No frontend files changed — design review skipped.

Eval Results

Not run in this lane. bun run eval:select selects 113 paid behavior probes plus 24 judges because scripts/resolvers/index.ts restores every gate case, which is past the $10 lane cap. The paid screen runs through gstack-ship-queue ready --screen (pre-approved), and the routing and contract evals belong to lane A's PR.

Review bot comments

No review bot comments.

TODOS

No TODO items completed in this PR.

Documentation

Scope. Read-only audit at head 58aeee7 on capy/gst-1088-lane-b against base bf2bcf1. The 16 committed changed files were checked: four skill descriptions and triggers, the contract: frontmatter on /investigate and /review, the new CONTRACT_DONE_MEANS resolver, gstack/llms.txt, the changelog fragment, and tests. Nothing is staged, unstaged or untracked. Three documents were read in full (changelog fragment, gstack/llms.txt, docs/skill-routing-and-contracts.md), and two more were checked by grep (docs/PROJECT_STRUCTURE.md, CLAUDE.md). The other candidate docs were grepped for the old and new description strings and for the contract and resolver names.

Result. The docs are current. gstack/llms.txt already carries the new when-clause descriptions for /investigate, /qa, /review and /verify. The changelog fragment accurately describes the change, including that the routing hook and contract check landed in lane A, and it points to docs/skill-routing-and-contracts.md. That doc's schema, item kinds and exit codes match what the templates declare. No other tracked doc quotes the old descriptions.

Debt. docs/skill-routing-and-contracts.md does not mention the {{CONTRACT_DONE_MEANS}} resolver or the "Done means" list rendered at the top of the skill. Its /investigate example uses the id repro-after-fix, while the template uses check-after-last-edit; the doc presents it as an example. No edits were made, because the mode is read-only.

Test plan

Also changed: gstack/llms.txt, regenerated by gen:skill-docs.

…locks for /investigate, /review, /qa, /verify (GST-1088 lane B)

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

trunk-io Bot commented Nov 3, 2026 •

Copy link
Copy Markdown

😎 This pull request was merged.

garrytan and others added 8 commits November 3, 2026 02:28
…s; bare gstack-skill-contract name until lane A ships it

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…llows the small-diff skip (review fix round)

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>
… stop rules (Step 11 voices)

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

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>
… qa parity cap

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

github-actions Bot commented Nov 3, 2026 •

Copy link
Copy Markdown
Contributor

E2E Evals: ✅ PASS

[test:paid] VERDICT GREEN — lane gate/pr, attempt 1
  rule 112/112 · behavior 1/1 · judge 24/24 · quarantined 0 (0 failing the lane)
  SKIPPED 0 · INFRA 0 · INCOMPLETE 0 · unattributed 0 · ACTION REQUIRED 0
  wall 7m56s · cost $37.73 known + 4 of 139 trial(s) cost unknown

125 executed, 0 reused rule/judge records | 0 manual accepted (unscored; no score-cache credit) | $33.52 rule/judge cost | reconcile exit: 0

Profile: pr / mode full-fallback; selected behaviors: 113, judges: 24. Deferred to scheduled/release coverage: 153 behaviors and 2 changed prompt files. Deferred checks did not run and receive no PR-pass credit.

Rule and judge shards
Shard Automated result Manual/unscored Executed Reused Status Cost
llm-judge/skill-llm-eval 24/24 0 24 0 ✅ $1.44
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-current 1/1 0 1 0 ✅ $0.93
e2e/skill-e2e-coverage-audit 2/2 0 2 0 ✅ $0.3
e2e-deploy/skill-e2e-deploy--setup-deploy-workflow 1/1 0 1 0 ✅ $0.13
e2e-qa-functional-fix/skill-e2e-qa-functional-fix 2/2 0 2 0 ✅ $0.93
e2e/skill-e2e-plan--plan-review-report 1/1 0 1 0 ✅ $1.56
e2e-qa-callers/skill-e2e-qa-callers--ship-exploratory-unavailable 1/1 0 1 0 ✅ $0.61
e2e-retro/skill-e2e-retro 1/1 0 1 0 ✅ $0.33
e2e/skill-e2e-shared-libs-paths--shared-libs-review-prior-coverage 1/1 0 1 0 ✅ $1
e2e-qa-workflow/skill-e2e-qa-workflow--qa-quick 1/1 0 1 0 ✅ $0.49
e2e-review-attribution/skill-e2e-review-attribution 3/3 0 3 0 ✅ $0.28
e2e/skill-e2e-ship-skip 1/1 0 1 0 ✅ $0.26
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-stale-before 1/1 0 1 0 ✅ $0.39
e2e/skill-e2e-shared-libs--shared-libs-review-lifecycle 1/1 0 1 0 ✅ $0.91
e2e-review-army/skill-e2e-review-army--review-army-migration-safety 1/1 0 1 0 ✅ $0.32
e2e-deploy/skill-e2e-deploy--land-and-deploy-first-run 1/1 0 1 0 ✅ $0.27
e2e/skill-e2e-shared-libs--shared-libs-read-only 1/1 0 1 0 ✅ $0.27
e2e-deploy/skill-e2e-deploy--land-and-deploy-review-gate 1/1 0 1 0 ✅ $0.2
e2e-docsync-spawned/skill-e2e-docsync-spawned 1/1 0 1 0 ✅ $0.73
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-stale-after 1/1 0 1 0 ✅ $0.41
e2e-safety-codex-consult/skill-e2e-safety-codex-consult 1/1 0 1 0 ✅ $0.27
e2e-deploy/skill-e2e-deploy--land-and-deploy-workflow 1/1 0 1 0 ✅ $0.56
e2e/skill-e2e-workflow 4/4 0 4 0 ✅ $0.8
e2e-review-army/skill-e2e-review-army--review-army-perf-n-plus-one 1/1 0 1 0 ✅ $0.24
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-late-result 1/1 0 1 0 ✅ $0.35
e2e/skill-e2e-shared-libs-paths--shared-libs-review-index-flags 1/1 0 1 0 ✅ $0.99
e2e-deploy/skill-e2e-deploy--benchmark-workflow 1/1 0 1 0 ✅ $0.24
e2e/skill-e2e-investigate-owned-completion 1/1 0 1 0 ✅ $0.07
e2e-qa-callers/skill-e2e-qa-callers--ship-exploratory-small-cli 1/1 0 1 0 ✅ $0.91
e2e-review-army/skill-e2e-review-army--review-army-json-findings 1/1 0 1 0 ✅ $0.07
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-store 1/1 0 1 0 ✅ $1.01
e2e-triage/skill-e2e-triage 1/1 0 1 0 ✅ $0.09
e2e-review-army/skill-e2e-review-army--review-army-delivery-audit 1/1 0 1 0 ✅ $0.15
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-timeout-unsettled 1/1 0 1 0 ✅ $0.2
e2e-design/skill-e2e-design--design-review-detector-shim 1/1 0 1 0 ✅ $0.13
e2e-session-intelligence/skill-e2e-session-intelligence 4/4 0 4 0 ✅ $0.29
e2e-safety-pair-agent/skill-e2e-safety-pair-agent 1/1 0 1 0 ✅ $0.1
e2e-plan-tune/skill-e2e-plan-tune 1/1 0 1 0 ✅ $0.12
e2e-qa-workflow/skill-e2e-qa-workflow--qa-bootstrap 1/1 0 1 0 ✅ $0.08
e2e-deploy/skill-e2e-deploy--canary-workflow 1/1 0 1 0 ✅ $0.11
e2e/skill-e2e-investigate-owned-termination 2/2 0 2 0 ✅ $0.18
e2e/skill-e2e-ship-hook-refresh 1/1 0 1 0 ✅ $0.1
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-launch-failure 1/1 0 1 0 ✅ $0.17
e2e-design/skill-e2e-design--plan-design-review-no-ui-scope 1/1 0 1 0 ✅ $0.08
e2e-third-party-actions/skill-e2e-third-party-actions 5/5 0 5 0 ✅ $0.46
e2e/skill-e2e-ship-hook-consent 2/2 0 2 0 ✅ $0.24
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-recovery 1/1 0 1 0 ✅ $0.4
e2e/skill-e2e-shared-libs--shared-libs-review-revalidation 1/1 0 1 0 ✅ $1.94
e2e-review/skill-e2e-review 2/2 0 2 0 ✅ $0.38
e2e-cso/skill-e2e-cso 1/1 0 1 0 ✅ $0.39
e2e-qa-functional/skill-e2e-qa-functional 2/2 0 2 0 ✅ $0.76
e2e-qa-callers/skill-e2e-qa-callers--ship-exploratory-late-input 1/1 0 1 0 ✅ $1.04
e2e-learnings/skill-e2e-learnings 1/1 0 1 0 ✅ $0.07
e2e-failure-routing/skill-e2e-failure-routing 4/4 0 4 0 ✅ $0.44
e2e-qa-workflow/skill-e2e-qa-workflow--qa-only-no-fix 1/1 0 1 0 ✅ $0.58
e2e-qa-callers/skill-e2e-qa-callers--review-exploratory-small-cli 1/1 0 1 0 ✅ $0.78
e2e-qa-callers/skill-e2e-qa-callers--ship-exploratory-plan-checks 1/1 0 1 0 ✅ $0.85
e2e/skill-e2e-test-value 3/3 0 3 0 ✅ $0.69
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-failure 1/1 0 1 0 ✅ $0.57
e2e-skillify/skill-e2e-skillify 3/3 0 3 0 ✅ $0.78
e2e/skill-e2e-shared-libs-paths--shared-libs-review-path-eligibility 1/1 0 1 0 ✅ $1.57
e2e-hermetic/skill-e2e-hermetic-canary 2/2 0 2 0 ✅ $0.06
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-completion 1/1 0 1 0 ✅ $0.96
e2e-design/skill-e2e-design--design-review-plugin-handoff 1/1 0 1 0 ✅ $0.14
e2e-review-army/skill-e2e-review-army--review-army-quality-score 1/1 0 1 0 ✅ $0.1
e2e-design/skill-e2e-design--design-review-detector-shim-dom 1/1 0 1 0 ✅ $0.23
e2e-safety-ship-evidence/skill-e2e-safety-ship-evidence 1/1 0 1 0 ✅ $0.11
e2e-browse/skill-e2e-bws 6/6 0 6 0 ✅ $0.29
e2e/skill-e2e-shared-libs--shared-libs-unsupported-git 1/1 0 1 0 ✅ $0.18
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-missing-asset 1/1 0 1 0 ✅ $0.26
e2e-ship-docsync/skill-e2e-ship-docsync--ship-docsync-missing-marker 1/1 0 1 0 ✅ $0.18
Fail-closed reconciliation
2e-plan-tune.test.ts
  slice 16  passed             21s  test/skill-e2e-triage.test.ts
  slice 16  passed             36s  test/skill-e2e-ship-docsync.test.ts#ship-docsync-timeout-unsettled
  slice 16  passed             35s  test/skill-e2e-ask-user-question-format-compliance.test.ts
  slice 16  passed             26s  test/skill-e2e-ship-docsync.test.ts#ship-docsync-launch-failure
  slice 16  passed             33s  test/skill-e2e-session-intelligence.test.ts
  slice 16  passed             39s  test/skill-e2e-ship-hook-consent.test.ts
  slice 16  passed             25s  test/skill-e2e-investigate-owned-termination.test.ts
  slice 16  passed             27s  test/skill-e2e-design.test.ts#design-review-detector-shim
  slice 16  passed             21s  test/skill-e2e-deploy.test.ts#canary-workflow
  slice 16  passed             30s  test/skill-e2e-ship-hook-refresh.test.ts
  slice 16  passed             14s  test/skill-e2e-design.test.ts#plan-design-review-no-ui-scope
  slice 16  passed             31s  test/skill-e2e-review-army.test.ts#review-army-delivery-audit
  slice 16  passed             29s  test/skill-e2e-safety-pair-agent.test.ts
  slice 16  passed             20s  test/skill-e2e-qa-workflow.test.ts#qa-bootstrap
  slice 17  passed             12s  test/skill-e2e-learnings.test.ts
  slice 17  passed             16s  test/skill-e2e-diagram.test.ts
[test:paid] collector final outcomes: 125 executed, 0 reused; 125 passed, 0 failed, 0 manual accepted (unscored; no score-cache credit) (125 attempt records from 71 collectors; every record counts)
[test:paid] deselected testcases, zero credit (316):
[test:paid]    302  sibling case of a case shard (its own shard runs it)
[test:paid]      8  periodic-tier case (this lane runs gate)
[test:paid]      6  Bun hook placeholder of a skipped describe block (not a test)
[test:paid] VERDICT GREEN — lane gate/pr, attempt 1
  rule 112/112 · behavior 1/1 · judge 24/24 · quarantined 0 (0 failing the lane)
  SKIPPED 0 · INFRA 0 · INCOMPLETE 0 · unattributed 0 · ACTION REQUIRED 0
  wall 7m56s · cost $37.73 known + 4 of 139 trial(s) cost unknown
[test:paid] exercised-path map (shadow, non-blocking): 10 MAP_GAP line(s) over 105 executed case(s) with recorded commands
  MAP_GAP document-release bin/gstack-banned-terms: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP plan-review-report bin/gstack-plan-reality: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP plan-review-report browse/dist/browse: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP plan-review-report design/dist/design: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP shared-libs-review-path-eligibility bin/gstack-approval-classes: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP ship-exploratory-late-input bin/gstack-review-plan: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP ship-exploratory-plan-checks bin/gstack-review-plan: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP ship-exploratory-small-cli bin/gstack-review-plan: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP test-audit-report-only design/dist/design: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
  MAP_GAP timeline-event-flow bin/gstack-skill-end: non-blocking for this PR; the next census refresh widens the map (docs/TESTING_INTERNALS.md#exercised-path-map)
[test:paid] report: every planned shard accounted and passed

Sliced lane: planner → duration-packed executors → fail-closed report. Behavior cases run a pre-registered 3-trial panel (PASS at 2/3 with no contract violation); a PASS 2/3 is shown with its failed trial, never as a clean pass. Reused results retain their original provenance and expiry.

Dispatched narrow screen (gstack-ship-queue ready --screen) of merge commit 3d06119ef789c0015fe0b29873c6b7b81ffc388f.

garrytan and others added 3 commits November 3, 2026 11:32
… ships, and re-pin /review by the measured 240 bytes

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

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
@github-actions github-actions Bot changed the title feat(skills): when-to-use descriptions, wider triggers and contract blocks for /investigate, /review, /qa, /verify (GST-1088 lane B) v1.94.22.0 feat(skills): when-to-use descriptions, wider triggers and contract blocks for /investigate, /review, /qa, /verify (GST-1088 lane B) Nov 3, 2026
@capy-ai
capy-ai Bot merged commit 592fa0c into main Nov 3, 2026
49 checks passed
garrytan added a commit that referenced this pull request Nov 3, 2026
Conflict: test/fixtures/skill-md-size-allowlist.json took main's file (with #3909's review pins and #3903); the 12 autoplan host pins are lowered to the guard's measured sizes (main minus 17 each, none raised).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
garrytan added a commit that referenced this pull request Nov 3, 2026
…al agent_dispatch marker in the contract resolver), cap comments cite gate rev 2, pins at the combined measurement

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
garrytan added a commit that referenced this pull request Nov 3, 2026
…r (match alone gates it), shared-preamble cut check, changelog at post-#3909 sizes, pins at measured (review 56,716, ratio 1.2979)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
capy-ai Bot added a commit that referenced this pull request Nov 3, 2026
…-resolved bin path (GST-1088 lane B follow-up) (#3957)

* feat(skills): when-to-use descriptions, wider triggers and contract blocks for /investigate, /review, /qa, /verify (GST-1088 lane B)

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

* fix(skills): keep core trigger phrases in /review and /qa descriptions; bare gstack-skill-contract name until lane A ships it

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

* fix(skills): Done-means list leaves out steps a host suppresses and allows the small-diff skip (review fix round)

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

* fix: pre-landing review fixes

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

* fix: Done-means honors loadout section exclusions and the skill's own stop rules (Step 11 voices)

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

* fix: the Done-means checker sentence follows an explicit CONTRACT_CHECKER_SHIPPED flag

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

* test: cite GST-1088 gate rev 2 for the /review cap raises

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

* Revert "test: cite GST-1088 gate rev 2 for the /review cap raises"

This reverts commit cc1539c.

* fix: trim /qa's opening sentence by 4 bytes so the branch fits main's qa parity cap

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

* fix: flip CONTRACT_CHECKER_SHIPPED now that bin/gstack-skill-contract ships, and re-pin /review by the measured 240 bytes

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

* docs: the changelog fragment says lane A's routing hook and contract check have landed

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

* fix(contracts): run gstack-skill-contract through the host-resolved bin path

The Done-means check/waive sentence named a bare gstack-skill-contract,
which a standard install does not put on PATH (fix-check finding on #3909
at 58aeee7). Render it through ctx.paths.binDir like every other gstack bin,
with a failing-first test across every host. Re-pin /review by the measured
+56 skeleton bytes and +24 chars per non-Claude host render.

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

* docs: changelog fragment wording for the bin-path fix

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>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant