Skills › gstack › ship › DRIVER.md

DRIVER.md

152 lines · ship/DRIVER.md at 3f79d81

Starts an agent Project instruction file

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1

2

3# /ship driver: run /ship from a parent agent

5Read this instead of `ship/SKILL.md` when a parent agent on any host runs /ship

6(`SESSION_KIND: unattended`). Commands live in `<root>/bin/` (`<root>` holds `ship/`); run each with

7the `GSTACK_LAUNCH` assignments your installer printed (`. <the GSTACK_LAUNCH_FILE it printed>`), never

8`export $(...)`, `env`, `printenv` or a bare `set` in a tool fence.

10**Rules.** Each phase below is one call: one program (Capy: an execute program; else a

11script) that runs the bins, reads, dispatches and waits, returning only result lines and reader

12outputs; print them verbatim. The model keeps only lead judgment, fixes, CHANGELOG and PR prose, the

13gates and the report. `STOP:` (exit 3) means nothing after it ran; `NEXT:` names

14the next act. Read a section only when a phase or the list at the end sends you, never

15up front. A STOP or decision this file does not cover: read `ship/SKILL.md` at that step, finish it

16there, come back. Unattended, a question with a recommended option takes it (log it); a gate

17disposition and every approval stay pending and end the run. Keep a private invocation record (the

18`--record` file): write its six headings at Phase 1, then fill each as its phase ends: **Checks**

19(Phases 2-4: lanes, pregate, evals, `Coverage:`, the plan checks, `Scope Check:`), **Decisions** (any

20phase: each answered or auto-taken question, in its words), **Reviews** (Phases 3-5: the plan line,

21start tokens, `Pre-Landing Review:`, `Gate edits:`, the reviewed tree), **Release** (Phases 5-7:

22version, CHANGELOG, commits), **Documentation** (Step 14.5) and **Next steps** (every phase: the next act).

24**Reviewers are the sections' own.** Every audit, specialist, Red Team, QA, fix-check, adversarial,

25outside-voice and documentation brief, its severity and confidence rules and its gates come from its

26section verbatim, with only its placeholders filled; this file

27never shortens a reviewer's brief. A blocking reader's prompt is its `gstack-review-dispatch render`

28file, unchanged; its findings reach `merged.jsonl` only via `collect`; `judge` refuses a drop or downgrade. Audit readers (Steps 7, 8, 9.2.1, 14.5) cannot block, so each runs on a

29small model at low effort; their findings go to the PR body.

31**Calls.** One pass with no fixes is 9 calls: Phases 1-8 and the report; at most 12 with a STOP's

32section read or a fix-check, plus a keep-alive per 200 s waited. A fix repeats Phases 3-4.

34**Budget: observe.** `gstack-ship-budget start --mode observe` records, never admits: each program ends

35with `gstack-ship-budget note --step <last step> --reading R --credits C --record <rec>`, R and C read in that program

36(Capy: your jam's `cost.tokens`, `cost.credits`). No check per step, no reservation, no meter-only

37call, no handoff; under `--token-cap` a note past the cap prints `verdict=stop`, the one stop check.

38A dispatching program takes `BEFORE` (R and C) as its readers start and passes

39`--dispatched-at <R> --dispatched-credits <C> --readers <n>` with the reading after the last settles.

41**Waits.** No call waits past 200 s: a program returns what still runs 200 s after its first line; the next

42call resumes the poll. Lanes, pregate and `finish` run in background. Never end the turn while

43readers run (each wakes it). A small waiting child saves nothing. Past 100 minutes, stop. Returns:

44≤32 KB per program; split longer reads at headings, each byte once, before first use.

46**One program per pass.** Each review pass, Step 11 and the Step 14.5 audit is one program, and the

47parent makes no other call while it runs: (1) `gstack-review-dispatch pass`: `gstack-review-plan --base <base>`

48with the pass's flags, then its staged manifest (Step 14.5 has one reader, `docs`); (2) `gstack-review-log --start

49<skill>` once per row the step logs (Step 14.5 takes none); (3) `BEFORE`; (4) `sent` (`BRIEF_MISMATCH` voids it), then one

50subagent per reader on its rendered file;

51(5) a poll until every reader settles (status `done` or `failed`, or a final summary; a fresh `idle`

52has not run); (6) `note` with the reading pair; a later batch (the Red Team,

53given the specialists' collected lines) repeats (3)-(6); (7) the collect: return only each reader's

54final output and status, via `collect`; it never walks the dispatch steps call by call.

/ship driver: run /ship from a parent agent

Read this instead of ship/SKILL.md when a parent agent on any host runs /ship (SESSION_KIND: unattended). Commands live in <root>/bin/ (<root> holds ship/); run each with the GSTACK_LAUNCH assignments your installer printed (. <the GSTACK_LAUNCH_FILE it printed>), never export $(...), env, printenv or a bare set in a tool fence.

Rules. Each phase below is one call: one program (Capy: an execute program; else a script) that runs the bins, reads, dispatches and waits, returning only result lines and reader outputs; print them verbatim. The model keeps only lead judgment, fixes, CHANGELOG and PR prose, the gates and the report. STOP: (exit 3) means nothing after it ran; NEXT: names the next act. Read a section only when a phase or the list at the end sends you, never up front. A STOP or decision this file does not cover: read ship/SKILL.md at that step, finish it there, come back. Unattended, a question with a recommended option takes it (log it); a gate disposition and every approval stay pending and end the run. Keep a private invocation record (the --record file): write its six headings at Phase 1, then fill each as its phase ends: Checks (Phases 2-4: lanes, pregate, evals, Coverage:, the plan checks, Scope Check:), Decisions (any phase: each answered or auto-taken question, in its words), Reviews (Phases 3-5: the plan line, start tokens, Pre-Landing Review:, Gate edits:, the reviewed tree), Release (Phases 5-7: version, CHANGELOG, commits), Documentation (Step 14.5) and Next steps (every phase: the next act).

Reviewers are the sections' own. Every audit, specialist, Red Team, QA, fix-check, adversarial, outside-voice and documentation brief, its severity and confidence rules and its gates come from its section verbatim, with only its placeholders filled; this file never shortens a reviewer's brief. A blocking reader's prompt is its gstack-review-dispatch render file, unchanged; its findings reach merged.jsonl only via collect; judge refuses a drop or downgrade. Audit readers (Steps 7, 8, 9.2.1, 14.5) cannot block, so each runs on a small model at low effort; their findings go to the PR body.

Calls. One pass with no fixes is 9 calls: Phases 1-8 and the report; at most 12 with a STOP's section read or a fix-check, plus a keep-alive per 200 s waited. A fix repeats Phases 3-4.

Budget: observe. gstack-ship-budget start --mode observe records, never admits: each program ends with gstack-ship-budget note --step <last step> --reading R --credits C --record <rec>, R and C read in that program (Capy: your jam's cost.tokens, cost.credits). No check per step, no reservation, no meter-only call, no handoff; under --token-cap a note past the cap prints verdict=stop, the one stop check. A dispatching program takes BEFORE (R and C) as its readers start and passes --dispatched-at <R> --dispatched-credits <C> --readers <n> with the reading after the last settles.

Waits. No call waits past 200 s: a program returns what still runs 200 s after its first line; the next call resumes the poll. Lanes, pregate and finish run in background. Never end the turn while readers run (each wakes it). A small waiting child saves nothing. Past 100 minutes, stop. Returns: ≤32 KB per program; split longer reads at headings, each byte once, before first use.

One program per pass. Each review pass, Step 11 and the Step 14.5 audit is one program, and the parent makes no other call while it runs: (1) gstack-review-dispatch pass: gstack-review-plan --base <base> with the pass's flags, then its staged manifest (Step 14.5 has one reader, docs); (2) gstack-review-log --start <skill> once per row the step logs (Step 14.5 takes none); (3) BEFORE; (4) sent (BRIEF_MISMATCH voids it), then one subagent per reader on its rendered file; (5) a poll until every reader settles (status done or failed, or a final summary; a fresh idle has not run); (6) note with the reading pair; a later batch (the Red Team, given the specialists' collected lines) repeats (3)-(6); (7) the collect: return only each reader's final output and status, via collect; it never walks the dispatch steps call by call.

Raw lines 1 to 55

Starts an agent dispatches :11

Starts an agent dispatch :27

Starts an agent dispatching :38

Starts an agent dispatched :39

Starts an agent subagent :50

56## 1. Load: Step 0

58The install check and this file.

1. Load: Step 0

The install check and this file.

Raw lines 56 to 59

60## 2. Preflight, tests, evals and reads: Steps 0.9, 1, 2, 3, 4, 5, 6, 6.5, 10

62`gstack-ship-budget start --record <rec> --mode observe [--token-cap <n>] --reading R --credits C`, then

63`gstack-ship-preflight --base <base> --lane <label>=<command>...` (the test commands AGENTS.md or

64CLAUDE.md names). `CARRY: carried` ends the run on its `GSTACK_RESULT:`

65line. A lane passes on `tests_ran: N` with exit 0; `tests_ran: 0` is ZERO-RUN, a failed lane; `unknown`

66is `count unavailable`. In-branch failures stop the ship; after a repair rerun with `--tests-only`.

67`requires-remote` needs `gstack-pregate clear` before Step 18. When prompts, templates, judges or eval

68harness changed, start the eval selector and pre-merge command (detached past 30 min); else

69record `evals: none affected`. Steps 6.5 and 10 run only if `gstack-greptile-early detect` finds

70Greptile. Then `gstack-ship-preflight --audit --base <base> --out <run dir>` writes the diff once

71(`CONTEXT:`) and the TODOS.md items naming touched paths (`TODOS:`), and prints the coverage map, the

72plan candidates and `READER: coverage=<needed|none> plan=<needed|none>`. Programs read

73`sections/review-army.md`, `sections/adversarial.md`, `sections/documentation.md`, the todos and commits

74files, and `sections/test-coverage.md` or `sections/plan-completion.md` only when its reader is `needed`.

75Never read TODOS.md or the full diff into the parent. A `PERSIST:` hint never replaces Step 9.

2. Preflight, tests, evals and reads: Steps 0.9, 1, 2, 3, 4, 5, 6, 6.5, 10

gstack-ship-budget start --record <rec> --mode observe [--token-cap <n>] --reading R --credits C, then gstack-ship-preflight --base <base> --lane <label>=<command>... (the test commands AGENTS.md or CLAUDE.md names). CARRY: carried ends the run on its GSTACK_RESULT: line. A lane passes on tests_ran: N with exit 0; tests_ran: 0 is ZERO-RUN, a failed lane; unknown is count unavailable. In-branch failures stop the ship; after a repair rerun with --tests-only. requires-remote needs gstack-pregate clear before Step 18. When prompts, templates, judges or eval harness changed, start the eval selector and pre-merge command (detached past 30 min); else record evals: none affected. Steps 6.5 and 10 run only if gstack-greptile-early detect finds Greptile. Then gstack-ship-preflight --audit --base <base> --out <run dir> writes the diff once (CONTEXT:) and the TODOS.md items naming touched paths (TODOS:), and prints the coverage map, the plan candidates and READER: coverage=<needed|none> plan=<needed|none>. Programs read sections/review-army.md, sections/adversarial.md, sections/documentation.md, the todos and commits files, and sections/test-coverage.md or sections/plan-completion.md only when its reader is needed. Never read TODOS.md or the full diff into the parent. A PERSIST: hint never replaces Step 9.

Raw lines 60 to 76

Project instruction file AGENTS.md :63

Project instruction file CLAUDE.md :64

77## 3. Audits and review: Steps 7, 8, 9, 9.1, 9.2, 9.2.1

79One program: the audit readers `READER:` names (Step 7 from `sections/test-coverage.md`, Step 8 from

80`sections/plan-completion.md`, each run as written; Step 7 may write tests, so it settles first), Step 9.2.1's QA reader (that step of

81`sections/review-army.md` as its brief) and the pass (above): Step 9's plan and start, Step 9.1's

82specialists and Step 9.2's Red Team as written. `Coverage:` and Step 8's line come from `--audit` when no

83reader ran.

3. Audits and review: Steps 7, 8, 9, 9.1, 9.2, 9.2.1

One program: the audit readers READER: names (Step 7 from sections/test-coverage.md, Step 8 from sections/plan-completion.md, each run as written; Step 7 may write tests, so it settles first), Step 9.2.1's QA reader (that step of sections/review-army.md as its brief) and the pass (above): Step 9's plan and start, Step 9.1's specialists and Step 9.2's Red Team as written. Coverage: and Step 8's line come from --audit when no reader ran.

Raw lines 77 to 84

85## 4. Judgment: Steps 8.1, 8.2, 9.3, 9.4 and Step 11

87Steps 8.1 and 8.2 (`Scope Check:`) on the todos and commits files, then the core checklist, Steps

889.3, 9.4 and the repeat decision as written (`gstack-review-plan` included;

89`JUDGMENT: ok` before any fix), fixes and persistence in

90one program. Prints `Pre-Landing Review:`, `Gate edits:`. `NEXT: stop` stops; `full` or

91`scoped`: one program runs the failing test, fix, `--tests-only` and Phase 3, each gated; `done`: the same program runs Step 11 from

92`sections/adversarial.md` as written (above), only the voices the last full-pass plan lists (neither

93prints `ADVERSARIAL: skipped (review plan)`).

4. Judgment: Steps 8.1, 8.2, 9.3, 9.4 and Step 11

Steps 8.1 and 8.2 (Scope Check:) on the todos and commits files, then the core checklist, Steps 9.3, 9.4 and the repeat decision as written (gstack-review-plan included; JUDGMENT: ok before any fix), fixes and persistence in one program. Prints Pre-Landing Review:, Gate edits:. NEXT: stop stops; full or scoped: one program runs the failing test, fix, --tests-only and Phase 3, each gated; done: the same program runs Step 11 from sections/adversarial.md as written (above), only the voices the last full-pass plan lists (neither prints ADVERSARIAL: skipped (review plan)).

Raw lines 85 to 94

95## 5. Voices, bind and version: Steps 11, 11.5, 12

97Judge the voices; missing outside coverage is `unavailable`, never clean; queued fixes rerun Phases

983-4. Then `gstack-review-dispatch verify` (`VERIFY: clean`) and `gstack-review-read`: the final Step 9 row and Step 11 native row (or `CURRENT` freshness

99after a planned skip) agree on `wtree`, `start_wtree`, `end_wtree`; save that reviewed tree. Then

100`gstack-ship-release version --base <base> [--bump micro|patch] --why '<line>'`; MINOR, MAJOR, `BUMP_ANSWER_REQUIRED`:

101approvals; `VERSION: skipped|kept`: no write.

102

5. Voices, bind and version: Steps 11, 11.5, 12

Judge the voices; missing outside coverage is unavailable, never clean; queued fixes rerun Phases 3-4. Then gstack-review-dispatch verify (VERIFY: clean) and gstack-review-read: the final Step 9 row and Step 11 native row (or CURRENT freshness after a planned skip) agree on wtree, start_wtree, end_wtree; save that reviewed tree. Then gstack-ship-release version --base <base> [--bump micro|patch] --why '<line>'; MINOR, MAJOR, BUMP_ANSWER_REQUIRED: approvals; VERSION: skipped|kept: no write.

Raw lines 95 to 102

Starts an agent dispatch :98

103## 6. Notes and documentation: Steps 13, 14, 14.5

104

105Step 13: one user-facing entry from the commits file, where `NEXT:` says;

106`gstack-prose-lint <it> --base origin/<base> --gate` until `PROSE_LINT: ok`. Step 14: TODOS.md deferrals and

107completions, edited from the todos file. Step 14.5, every ship: read `sections/documentation.md` and run its audit as written, as

108one program (above), then `gstack-ship-receipt docs-caps --base <base>`; print `Documentation:`.

109One re-audit at most.

110

6. Notes and documentation: Steps 13, 14, 14.5

Step 13: one user-facing entry from the commits file, where NEXT: says; gstack-prose-lint <it> --base origin/<base> --gate until PROSE_LINT: ok. Step 14: TODOS.md deferrals and completions, edited from the todos file. Step 14.5, every ship: read sections/documentation.md and run its audit as written, as one program (above), then gstack-ship-receipt docs-caps --base <base>; print Documentation:. One re-audit at most.

Raw lines 103 to 110

111## 7. Release: Steps 15, 16, 17

112

113Commit in bisectable chunks, then `gstack-ship-release finish --base <base> --reviewed-tree <t>

114--docs-post <post> --lane ... [--build <cmd>] --trailer '<t>'`: `ROUTE:`, `DOCS:`, `EVIDENCE:` (FRESH;

115STALE or MISSING reruns once), `PREGATE:`; print them, the last `Gate edits:` and each `tests_ran`. Then

116`gstack-ship-release push --branch <branch> [--gate-open <n>]`: `REDACT_PREPUSH:`, `SEALED:`, `PUSH:`

117(pushed or ALREADY_PUSHED). Unattended, push defers the pre-push offer; else its STOP runs Step 17's guard block (`HOOK_STATE:`, `HOOKS_IN_GIT_DIR:`, `PREPUSH_PROMPTED:`). Never force-push.

118

7. Release: Steps 15, 16, 17

Commit in bisectable chunks, then gstack-ship-release finish --base <base> --reviewed-tree <t> --docs-post <post> --lane ... [--build <cmd>] --trailer '<t>': ROUTE:, DOCS:, EVIDENCE: (FRESH; STALE or MISSING reruns once), PREGATE:; print them, the last Gate edits: and each tests_ran. Then gstack-ship-release push --branch <branch> [--gate-open <n>]: REDACT_PREPUSH:, SEALED:, PUSH: (pushed or ALREADY_PUSHED). Unattended, push defers the pre-push offer; else its STOP runs Step 17's guard block (HOOK_STATE:, HOOKS_IN_GIT_DIR:, PREPUSH_PROMPTED:). Never force-push.

Raw lines 111 to 118

119## 8. Publish: Steps 18, 19, 19-C, 20, 21, 22

120

121- Step 18: the open-PR lookup; a title file starting `v<NEW_VERSION> `. `UNATTENDED_SHIP:` with no open PR at HEAD takes Step 18-H.

122- Step 19 body: the receipt block, then the sections `sections/pr-body.md` lists (Pre-Landing Review: `REVIEW_LOOP:`, `Gate edits:`, deferred, notes), led under `CAPY_PR: on` (Step 19-C) by What changed, Why, Blast radius and Approvals (`gstack-approvals render`). `gstack-prose-lint <top> --sections 'Why,Summary,Blast radius' --gate`; `gstack-issue-links`; `gstack-review-scope summary --since "$REVIEW_SINCE" && gstack-ship-receipt write --pr <n> --base <base> --gate @<f> --pregate <f> --issues @<f> --review-loop @<f> --docs @<f> --body <body>`; `gstack-post pr-body` and `pr-title` (a new PR via the host's PR tool; a draft while a gate finding is `open`). `SHIP_RECEIPT:` opens your report.

123- Step 20: the ship metrics row via `gstack-review-log`.

124- Step 22: `gstack-ship-budget close --reading R --credits C` (`BUDGET_FINAL:` and `BUDGET_TIMELINE:` carry tokens and credits; put both in the report), then `gstack-ship-receipt result --pr <n>`: `GSTACK_RESULT: skill=ship status=complete run=<dir>`. Under a merge queue, `gstack-ship-queue ready --pr <n> [--screen|--no-screen]` at the pushed head; paste its output.

125

8. Publish: Steps 18, 19, 19-C, 20, 21, 22

Step 18: the open-PR lookup; a title file starting v<NEW_VERSION> . UNATTENDED_SHIP: with no open PR at HEAD takes Step 18-H.
Step 19 body: the receipt block, then the sections sections/pr-body.md lists (Pre-Landing Review: REVIEW_LOOP:, Gate edits:, deferred, notes), led under CAPY_PR: on (Step 19-C) by What changed, Why, Blast radius and Approvals (gstack-approvals render). gstack-prose-lint <top> --sections 'Why,Summary,Blast radius' --gate; gstack-issue-links; gstack-review-scope summary --since "$REVIEW_SINCE" && gstack-ship-receipt write --pr <n> --base <base> --gate @<f> --pregate <f> --issues @<f> --review-loop @<f> --docs @<f> --body <body>; gstack-post pr-body and pr-title (a new PR via the host's PR tool; a draft while a gate finding is open). SHIP_RECEIPT: opens your report.
Step 20: the ship metrics row via gstack-review-log.
Step 22: gstack-ship-budget close --reading R --credits C (BUDGET_FINAL: and BUDGET_TIMELINE: carry tokens and credits; put both in the report), then gstack-ship-receipt result --pr <n>: GSTACK_RESULT: skill=ship status=complete run=<dir>. Under a merge queue, gstack-ship-queue ready --pr <n> [--screen|--no-screen] at the pushed head; paste its output.

Raw lines 119 to 125

126## Where each STOP sends you (paths under `<root>/ship/`)

127

128- `merge conflicts`: `SKILL.md#step-3-merge-the-base-branch-before-tests`

129- `NEXT: carry route`: `SKILL.md#step-1-pre-flight`

130- `DISTRIBUTION: candidates=`: `SKILL.md#step-2-distribution-pipeline-check`

131- `APPLE:` with a store ask: `sections/apple-release.md#apple-app-store-release`

132- `pregate fail` or `incomplete`: `sections/tests.md#step-5-run-tests-on-merged-code`

133- a failed or zero-run lane: `sections/tests.md#test-failure-ownership-triage`

134- a red eval or a failed free-suite shard: `sections/measure.md#measure-then-fix-loop-a-red-paid-eval-or-a-failed-free-suite-shard`

135- Greptile found: `sections/greptile-early.md#step-65-early-greptile-pr-after-the-free-tests-pass`

136- coverage below target, a failed audit: `sections/test-coverage.md#step-7-test-coverage-audit`

137- plan items NOT DONE or UNVERIFIABLE: `sections/plan-completion.md#gate-logic`

138- `NEXT: stop`: `sections/review-army.md#decide-whether-to-repeat-step-9`

139- a `REVIEW_SCOPE_*` refusal, the review-log row: `sections/review-army.md#step-94-fix-first-and-persistence`

140- a required probe not passed: `sections/review-army.md#step-921-exploratory-qa-before-fix-first`

141- native adversarial incomplete, queued fixes: `sections/adversarial.md#finish-the-adversarial-phase`

142- Step 11.5 mismatch: `SKILL.md#step-115-bind-the-reviews`

143- a `version` STOP: `SKILL.md#step-12-version-bump-auto-decide`

144- `Documentation: blocked` or a `DOCS_CAP:` over: `sections/documentation.md#blocked-recovery`

145- finish: changed since review: `SKILL.md#2-choose-the-change-route`

146- finish: documentation inputs changed: `SKILL.md#3-resolve-documentation-freshness`

147- finish: build, lane or pregate STOP: `SKILL.md#4-verify-the-frozen-candidate`

148- a push STOP: `SKILL.md#step-17-push`

149- unattended, no open PR at HEAD: `sections/handoff.md#step-18-h-handoff-without-a-pr-automation-lanes`

150- a receipt write or `gstack-post` refusal: `sections/pr-body.md#compose-the-body-then-publish-through-gstack-post`

151- `verdict=stop` or `DELEGATE:`: `sections/budget-handoff.md#budget-and-context-handoff-read-when-a-cap-is-set-or-verdictdelegate-prints`

152- `QUEUE_RECEIPT_STALE`: `../docs/ship-policy.md#ship-before-ready`

Where each STOP sends you (paths under `<root>/ship/`)

merge conflicts: SKILL.md#step-3-merge-the-base-branch-before-tests
NEXT: carry route: SKILL.md#step-1-pre-flight
DISTRIBUTION: candidates=: SKILL.md#step-2-distribution-pipeline-check
APPLE: with a store ask: sections/apple-release.md#apple-app-store-release
pregate fail or incomplete: sections/tests.md#step-5-run-tests-on-merged-code
a failed or zero-run lane: sections/tests.md#test-failure-ownership-triage
a red eval or a failed free-suite shard: sections/measure.md#measure-then-fix-loop-a-red-paid-eval-or-a-failed-free-suite-shard
Greptile found: sections/greptile-early.md#step-65-early-greptile-pr-after-the-free-tests-pass
coverage below target, a failed audit: sections/test-coverage.md#step-7-test-coverage-audit
plan items NOT DONE or UNVERIFIABLE: sections/plan-completion.md#gate-logic
NEXT: stop: sections/review-army.md#decide-whether-to-repeat-step-9
a REVIEW_SCOPE_* refusal, the review-log row: sections/review-army.md#step-94-fix-first-and-persistence
a required probe not passed: sections/review-army.md#step-921-exploratory-qa-before-fix-first
native adversarial incomplete, queued fixes: sections/adversarial.md#finish-the-adversarial-phase
Step 11.5 mismatch: SKILL.md#step-115-bind-the-reviews
a version STOP: SKILL.md#step-12-version-bump-auto-decide
Documentation: blocked or a DOCS_CAP: over: sections/documentation.md#blocked-recovery
finish: changed since review: SKILL.md#2-choose-the-change-route
finish: documentation inputs changed: SKILL.md#3-resolve-documentation-freshness
finish: build, lane or pregate STOP: SKILL.md#4-verify-the-frozen-candidate
a push STOP: SKILL.md#step-17-push
unattended, no open PR at HEAD: sections/handoff.md#step-18-h-handoff-without-a-pr-automation-lanes
a receipt write or gstack-post refusal: sections/pr-body.md#compose-the-body-then-publish-through-gstack-post
verdict=stop or DELEGATE:: sections/budget-handoff.md#budget-and-context-handoff-read-when-a-cap-is-set-or-verdictdelegate-prints
QUEUE_RECEIPT_STALE: ../docs/ship-policy.md#ship-before-ready

Raw lines 126 to 152