garrytanandcapy-ai[bot] 049b4693a7 Count an outside review as clean only from its last VERDICT line ...

Every outside-review prompt now asks the reviewer to end with exactly
VERDICT: CLEAN or VERDICT: FINDINGS, and the parser reads a pass only from
that line. Prose no-findings sentences are no longer evidence for clean.
Codex's structured review and /codex review run through codex exec, since
codex review --base takes no prompt and could never give the line.

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

2026-11-07 20:18:01 +00:00

..

adversarial.md

Count an outside review as clean only from its last VERDICT line

2026-11-07 20:18:01 +00:00

adversarial.md.tmpl

fix(ship): make the five judge-flagged workflow spots match the code (GST-1346) (#4004)

2026-11-04 23:50:18 +00:00

apple-release.md

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

apple-release.md.tmpl

v1.91.15.0 v1.91.15.0: Opus 5.5 prompt cleanup, behavior-level skill tests, transcript consent (#3017)

2026-10-03 01:19:03 -07:00

budget-handoff.md

feat: /runaway-stopper — detect, stop and prevent runaway threads and subagents (GST-1279) (#3975)

2026-11-04 02:59:50 +00:00

budget-handoff.md.tmpl

feat: /runaway-stopper — detect, stop and prevent runaway threads and subagents (GST-1279) (#3975)

2026-11-04 02:59:50 +00:00

capy-pr.md

feat: the plan check works on public repos: a machine-local plan_record and a record-keyed Plan line (GST-1774) (#4133)

2026-11-07 18:02:40 +00:00

capy-pr.md.tmpl

feat: the plan check works on public repos: a machine-local plan_record and a record-keyed Plan line (GST-1774) (#4133)

2026-11-07 18:02:40 +00:00

changelog.md

v1.91.353.0 fix(ship): Step 12 keeps VERSION on --keep-current, adds bump never, and waits for the owner's answer before an unattended bump (GST-380) (#3666)

2026-10-31 06:07:36 +00:00

changelog.md.tmpl

v1.91.353.0 fix(ship): Step 12 keeps VERSION on --keep-current, adds bump never, and waits for the owner's answer before an unattended bump (GST-380) (#3666)

2026-10-31 06:07:36 +00:00

documentation.md

ship-receipt write: every docs audit in one /ship run binds the reviewed digest (GST-1616) (#4071)

2026-11-06 15:04:30 +00:00

documentation.md.tmpl

ship-receipt write: every docs audit in one /ship run binds the reviewed digest (GST-1616) (#4071)

2026-11-06 15:04:30 +00:00

greptile-early.md

fix(ship): make the five judge-flagged workflow spots match the code (GST-1346) (#4004)

2026-11-04 23:50:18 +00:00

greptile-early.md.tmpl

fix(ship): make the five judge-flagged workflow spots match the code (GST-1346) (#4004)

2026-11-04 23:50:18 +00:00

greptile.md

v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)

2026-11-03 01:40:07 +00:00

greptile.md.tmpl

v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)

2026-11-03 01:40:07 +00:00

handoff.md

v1.93.22.0 fix(ship): targeted record binds to the commit it read; write/carry run the targeted verdict; fix-check ledgers count (GST-986) (#3887)

2026-11-02 21:53:30 +00:00

handoff.md.tmpl

v1.93.22.0 fix(ship): targeted record binds to the commit it read; write/carry run the targeted verdict; fix-check ledgers count (GST-986) (#3887)

2026-11-02 21:53:30 +00:00

manifest.json

v1.93.33.0 wave(review): #3705 #3744 #3745 #3764 #3765 #3795 (#3852)

2026-11-03 01:40:07 +00:00

measure.md

v1.91.159.0 security: gstack's Bun entry points ignore the audited repo's .env and bunfig.toml (S1) (#3312)

2026-10-20 00:24:28 +00:00

measure.md.tmpl

v1.91.159.0 security: gstack's Bun entry points ignore the audited repo's .env and bunfig.toml (S1) (#3312)

2026-10-20 00:24:28 +00:00

plan-completion.md

feat: crew PRs carry their brief's Plan line; ship-queue ready and land check it (GST-1751) (#4118)

2026-11-07 09:53:38 +00:00

plan-completion.md.tmpl

v1.91.331.0 revert(review): restore pre-#3621 reviewer briefs (no-loss round 3) (#3638)

2026-10-30 10:40:19 +00:00

pr-body.md

feat: retire /investigate after a no-gain eval (GST-1717) (#4110)

2026-11-07 06:52:04 +00:00

pr-body.md.tmpl

feat: retire /investigate after a no-gain eval (GST-1717) (#4110)

2026-11-07 06:52:04 +00:00

preamble.md

v1.91.276.0 feat(preamble): tier 2+ skills load the shared preamble once per session (GSTA-96) (#3434)

2026-10-27 13:28:18 +00:00

review-army.md

Count an outside review as clean only from its last VERDICT line

2026-11-07 20:18:01 +00:00

review-army.md.tmpl

v1.94.41.0 fix(ship): receipt counts bind by finding id, scoped re-check, lighter READY, head= on the result line (GSTA-258 L4) (#3926)

2026-11-03 22:35:15 +00:00

shared-code-reuse.md

v1.91.302.0 fix: repair three flaky gate cases from the 2026-10-28 flaky pass (index flags, exploratory QA, cookie auth) (#3553)

2026-10-29 01:58:13 +00:00

shared-code-reuse.md.tmpl

v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

2026-09-29 06:07:35 -07:00

test-coverage.md

v1.91.331.0 revert(review): restore pre-#3621 reviewer briefs (no-loss round 3) (#3638)

2026-10-30 10:40:19 +00:00

test-coverage.md.tmpl

v1.91.331.0 revert(review): restore pre-#3621 reviewer briefs (no-loss round 3) (#3638)

2026-10-30 10:40:19 +00:00

tests.md

feat: retire /investigate after a no-gain eval (GST-1717) (#4110)

2026-11-07 06:52:04 +00:00

tests.md.tmpl

fix(ship): make the five judge-flagged workflow spots match the code (GST-1346) (#4004)

2026-11-04 23:50:18 +00:00