Repository navigation
Codex picker prompts and docs name skills the way Codex lists them (GST-3196) - #4524
Merged
Merged
Conversation
…ST-3196) The nine codex_default_prompt templates said $gstack-<skill>, the folder name, which Codex 0.170 doesn't list, so the mention loaded nothing. They now say $<skill>, the SKILL.md name Codex lists (skill_prefix never changes it on Codex). The README's Codex row and docs/skills.md match. A test scans the Codex render and the docs for unlisted $gstack- mentions. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
😎 This pull request was merged. |
…hosts guide too (GST-3196) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…an named docs (GST-3196) The new mention test read docs/ by directory, which the docs lane's reader registry refuses; it now scans the five Codex-facing docs by name. docs/hosts.md and docs/skills.md say Codex lists the Claude second-opinion skill as claude-code. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…(GST-3196) The scan flagged #4522's $gstack-review example. Codex lists the skill as review, and codex exec '$review ...' injects it as a <skill> message (codex-cli 0.170 stub probe); only a folder-name mention is plain text. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Merged
capy-ai Bot
added a commit
that referenced
this pull request
Nov 19, 2026
- `gstack-artifact validate` no longer passes a run.json that gstack-autoplan never wrote. (#4494) - /ship's changed-number check no longer stops on tests that only share a word with the change (#4478). (#4496) - On Capy, /ship no longer edits or comments on pull requests as you. (#4518) - The destructive-command check stops asking about scratch deletes and catches the real damage it used to miss. (#4513) - The destructive-command check reads commands more carefully, closing gaps found after the last release. (#4525) - The Codex readiness check and the second-model review now pick the same model for a custom Codex provider (GST-3089). (#4491) - gstack's Codex hooks work when your Codex folder's path has a `(`, `&` or other shell character in it. (#4528) - Uninstalling gstack keeps your own Codex hooks trusted. (#4528) - Codex hook setup matches Codex more closely. (#4528) - On Windows, setup copies the Claude Code hook code that gstack's Codex hooks import (#4528) - /review's checklist on Codex reads shell commands more carefully. (#4528) - On Codex, gstack now suggests the right skill for a prompt and stops destructive commands before they run. (#4512) - On Codex, /review is now held once when it tries to finish without its adversarial pass or its report, as it already is on Claude Code. (#4522) - On Codex, gstack's skill suggestion now names the skill the way Codex lists it. (#4523) - On Codex, gstack's suggested prompts and docs now name skills the way Codex lists them. (#4524) - /review on Codex with gpt-6.1-sol is no longer held back for a second-model pass it already ran. (#4526) - On Codex, office-hours, plan-design-review and gstack-upgrade work again when you name them. (#4510) - gstack knows when Codex is running unattended. (#4510) - Codex reviewers start with a clean context. (#4510) - Docs no longer say Codex has no hook support. (#4510) - A command whose output was cut off no longer counts as a finished read. (#4492) - A folder marked as published data can no longer hide source code or agent files from /ship's review. (#4516) - Correction to the on-by-default helper hooks entry: the hook still routes only to /review, /qa and /verify, so skills you've installed yourself aren't suggested yet. With gstack's skills it routes 14 of 60 real bug reports (was 17), and long prompts are no longer skipped. (#4505) - /sync-gbrain's read check now works when the first page in your code source is over 64 KB. (#4497) - Free-suite CI no longer fails before any test runs when Ubuntu's package mirror is slow. (#4530) - Syncing a second repo no longer makes the first one ask for /sync-gbrain again. (#4532) - gstack's helper hooks are now on by default in Claude Code, OpenClaw and Hermes, and the prompt-routing hook fires on real bug reports. (#4503) - `gstack-pregate clear --receipt` accepts a remote gate run from before a merged release when the release only regenerated a declared release output. (#4483) - The second-model review now keeps the reviewer's own result, and reports a used-up budget as a budget stop. (#4515) - When the reviewer wrote its review to the result file it was asked for, Codex then replaced that file with its short closing message ("Done, I wrote the review"), so the review was thrown away and reported as missing its markers. (#4515) - When the provider refuses the call with HTTP 402 Payment Required (usually a metering proxy that hit its allowance, or an account out of credits or quota), gstack used to record only "exit 1". (#4515) - The pre-commit /verify check now fails a check that times out, and its checks share one time budget (GST-3201). (#4527) - /ship's review collector no longer reads a reviewer's own scope list or list of passed checks as findings (GST-3201). (#4527) - Merge-queue stack tests fail when git cannot list a PR's added test files (GST-3201). (#4527) - /ship can now review results PRs that publish raw session data. (#4511) - /ship's review pass works when the checkout you ship isn't the project's default checkout. (#4507) - A second review round no longer reports done when nothing was reviewed. (#4520) - The prompt-routing hook now suggests skills you install yourself, and no longer sends ordinary bug reports to /qa (GST-3123). (#4506) - gstack's script runner and merge-queue checks now also refuse cut-off output. (#4502) - A failed second-model review reports the cause that actually stopped it, and the runner never deletes its own prompt. (#4519) - `gstack-ship-queue ready` now fills in the trial merges and the second-model trail read instead of printing lines to fill. (#4529) - Five small ship-tool fixes. (#4529) - A ruling the owner gives while a `/ship` run is open can be relayed. (#4529) - /ship no longer kills a working test run as stalled when the test command starts its workers in their own session. (#4533) - /ship no longer stops a review because the state-machine reader started its reply the way its instructions say. (#4504) - When Claude Code runs /verify right before a commit, it now gets a quick check instead of the full fix loop (GST-3150). (#4508) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
On Codex, the suggested prompts for nine gstack skills and the README now say
$office-hours,$reviewand so on, which load the skill;$gstack-office-hoursloaded nothing.Why: Codex lists each skill by the
name:in its SKILL.md, not thegstack-folder, and skill_prefix never changes that name on Codex.Nothing to do: the next
./setup --host codexpicks it up.What changed
codex_default_promptin autoplan, land-and-deploy, modernize, office-hours, qa, review, runaway-stopper, ship and write-skill:$gstack-<skill>becomes$<skill>. Only the Codexagents/openai.yamlreads this key, so every tracked Claude SKILL.md is byte-identical.$office-hours.$claude-code.codex exec '$review ...'injects the skill; only a folder-name mention is plain text (the example Codex now holds /review to its checklist before a session can end (GST-3173) #4522 added).$gstack-mentions that are not a listed skill name, and checks the README Codex row. It fails at be83949 (nine openai.yaml files, and the README row on its own).How it was checked
Use $office-hours ...injects one skill block (office-hours, the rendered SKILL.md);Use $gstack-office-hours ...injects none../setup --host codex --prefixinto a throwaway HOME: skill_prefix=true, and Codex's office-hours SKILL.md still saysname: office-hours.Agent notes
Issues
Refs #4522
Documentation exception: accepted by Captain GStack Minder (GSTA-36) 2026-11-19 via Captain agent message to GSTA-649, 2026-11-19: GStack Minder accepts docs/skill-routing-and-contracts.md:98 without a third docs audit: one sentence, corrected to match a codex-cli 0.170 stub probe, and checked against lib/codex-rollout.ts:141-143 by the fix-check reader.
Review-loop exception: accepted by Captain GStack Minder (GSTA-36) 2026-11-19 via lane GSTA-649 relay: Captain GStack Minder (GSTA-36): rule-19 grant, merge origin/main plus one scan fix; one advisory scoped fix-check (fix-check at d70dd69, 0 findings)
Open notes, not changed here: the generic fallback prompt
Use gstack-<x> for this task.(scripts/gen-skill-docs.ts, Codex render code) still names the folder; Gemini, Cursor, Factory and Kiro README rows still saygstack-office-hours(not Codex, not measured); lib/skill-route.ts:375 comment is stale. Decision trail: captain drive reports/GSTA-649-decisions.tsv.