Garry Tanandcapy-ai[bot] e2d9c798b2 v1.92.57.0 fix(hermes): plain skill-start fence that Tirith can resolve, so Hermes can start gstack skills (GST-882) (#3825) ...

* fix: plain skill-start fence that a static resolver can follow (GST-882)

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

* fix: checked-in renders keep the lookup as plain lines; regenerate goldens, lower size pins (GST-882)

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

* test: Codex preamble expectation follows the plain start lookup (GST-882)

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

* fix: pre-landing review fixes (runtime-root header documents the plain skill-start fence, GST-882)

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

* fix: Step 11 review fixes: troubleshooting names the skill-start exception; parity test pins the start lookup to the later-fence root (GST-882)

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

* fix: type the parity test's env so the test typecheck ratchet stays clean (GST-882)

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

* docs: changelog fragment for GST-882

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

* test: writing-style Codex fence expectation follows the plain start lookup (GST-882)

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>

2026-11-02 05:02:04 +00:00

..

generate-ask-user-format.ts

v1.91.277.0 feat(preamble): office-hours stops copying the shared AskUserQuestion subsections (GSTA-96) (#3453)

2026-10-27 13:47:00 +00:00

generate-brain-health-instruction.ts

feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040)

2026-04-19 17:50:31 +08:00

generate-brain-sync-block.ts

v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)

2026-10-07 23:29:05 +00:00

generate-completeness-section.ts

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

generate-completion-status.ts

v1.91.158.0 feat(config): plan_mode_preamble=off drops the plan-mode preamble from installed skills (port of #3213) (#3308)

2026-10-19 23:31:59 +00:00

generate-confusion-protocol.ts

v1.46.0.0 feat: gstack v2 foundation — catalog tokens drop 56%, eval-first floor covers all 51 skills (#1712)

2026-05-26 16:50:03 -07:00

generate-context-health.ts

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

generate-context-recovery.ts

v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)

2026-10-03 07:54:09 -07:00

generate-evidence-directive.ts

v1.91.247.0 fix(plan-eng-review): define the three references its judged text left dangling (GSTA-91) (#3421)

2026-10-26 13:36:43 +00:00

generate-preamble-bash.ts

v1.92.57.0 fix(hermes): plain skill-start fence that Tirith can resolve, so Hermes can start gstack skills (GST-882) (#3825)

2026-11-02 05:02:04 +00:00

generate-repo-mode-section.ts

feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040)

2026-04-19 17:50:31 +08:00

generate-search-before-building.ts

v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)

2026-10-03 07:54:09 -07:00

generate-test-failure-triage.ts

v1.91.203.0 feat(router): verified cause → fix, bounded triage for unknown causes (#3157, #3158) (#3395)

2026-10-25 10:09:02 +00:00

generate-upgrade-check.ts

v1.91.240.0 feat(proactive): default to the four core skills (core | all | off), with docs, prompt and tests (GSTA-99) (#3432)

2026-10-26 10:05:57 +00:00

generate-voice-directive.ts

v1.91.309.0 fix(flaky): one rule each in the judged review and Eng prose; a cancelled judge names what it was waiting on (GSTA-139 S3) (#3544)

2026-10-29 05:50:41 +00:00

generate-writing-style.ts

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