Skip to content

feat!: review locally with the other vendor's model (quest review, /quest-review) - #271

Merged
kixelated merged 12 commits into
mainfrom
quest/m0/local-review
Oct 28, 2026
Merged

kixelated merged 12 commits into
mainfrom
quest/m0/local-review

Conversation

@kixelated

@kixelated kixelated commented Oct 28, 2026 •

Copy link
Copy Markdown
Collaborator

Closes the local review quest, as planned in kixelated/quest#267 with trial findings from kixelated/quest#270.

Summary

Before a PR goes up for review, the authoring session now has the other vendor's model review the committed branch read-only on this machine, fixes or refutes each finding, and only then pushes and marks the PR ready. GitHub's online reviewers become optional input that merge addresses but never waits for.

  • quest review (new CLI, src/cli/review.ts): it detects the running harness (CLAUDECODE / CODEX_THREAD_ID) and runs the other one. --harness overrides that; an unknown or ambiguous harness, or a missing or logged-out CLI, is an error. It pins each reviewer's model and effort in one MODELS table: claude-opus-5-5 or gpt-6.1-sol at medium effort, and with --deep, for a high-stakes change, claude-fable-5-1 or gpt-6-astra; --model/--effort override them. Round 1 runs the vendor's own review (codex exec review --base or claude -p with /code-review <effort> <base>...HEAD), then resumes that session for one turn that applies the base's REVIEW.md and returns findings in one JSON schema (--output-schema / --json-schema). Later rounds resume the same session with the new head and --responses. A refutation stands only with evidence the reviewer cannot rebut. Session state is kept per branch in the clone's common Git dir.
  • Read-only: Codex runs in its read-only sandbox with approval_policy="never", --ignore-rules, and --ignore-user-config (the user config's project trust would load the head's .codex/config.toml and start its MCP servers). Claude runs in dontAsk mode with --tools Read,Grep,Glob,Bash,Agent, --strict-mcp-config, and no settings files (--setting-sources ""), so only Bash that Claude Code itself classifies read-only runs.
  • Base-only instructions: the reviewer never loads the checkout's AGENTS.md/CLAUDE.md. Claude loads no settings sources; Codex gets -c project_doc_max_bytes=0. Instead, the base's AGENTS.md/CLAUDE.md from the root and each directory holding a changed path arrive via --append-system-prompt / -c developer_instructions. Neither CLI refreshes those on resume, so a change to the applicable files starts a new session, which still weighs --responses. The base's REVIEW.md, read with git show <base>:REVIEW.md, goes into each round's user turn and is revoked if the base drops it.
  • Cache: Claude gets CLAUDE_CODE_PROMPT_CACHE_TTL=1h; Codex keeps its default 30-minute retention (the Plan's 24h request is dropped, see Decisions). Every turn passes identical flags. Each turn's usage prints as a usage line.
  • /quest-review replaces /quest-ready. It runs the checks and the review loop (with --deep only for a high-stakes change such as security, a wire format or public API, or a risk of data loss; or records a trivial skip), rewrites ## Review, pushes, and marks the PR ready with the existing quest ready hold, then offers /quest-merge. /quest-start, /quest-iterate, /quest-complete, /quest-spawn, /quest-afk, /quest-merge, the README, and docs/getting-started.md now call it.
  • Guide Reviews section (reviews run against the PR's base with --base; the ## Review record names the reviewer's model and effort), /quest-merge's waits, and CONTRIBUTING.md's review policy were rewritten: the ## Review record naming the head satisfies the required review (counted only on a PR whose author has write access; anyone else's head is reviewed by the merger, running no code from it, with checks left to CI and a quest the PR cannot modify), online findings are addressed at merge and never waited for or requested, and the every-fourth-round design checkpoint counts quest review rounds (--new restarts the count after a design change). Land only reviewed heads now names the ## Review record as kixelated/quest's policy example.
  • The finished quest file and its links are deleted. Prose mentions in codex-cloud-off.md and helpers/review-rules.md were updated.

Impact

  • New command quest review (plain and --json output, each naming the reviewer's model and effort; --deep for the stronger tier; exit 0, 2, or 1).
  • Breaking: the quest-ready skill is renamed quest-review. Migrate by running quest init to add the quest-review stub and deleting the old .claude/skills/quest-ready and .agents/skills/quest-ready stubs, which now fail with "no skill named ready". Its precedent, takeover→iterate, did the same. This repository's stubs are renamed here.
  • The quest ready CLI hold command is unchanged. No wire or data format changes.

Validation

  • just check and just test pass (618 + 426 tests). test/review.test.ts adds 14 tests using fake claude/codex CLIs. They cover harness detection, unknown harness, missing and logged-out CLIs, dirty or detached checkouts, read-only flags, and base-only instructions (head canary absent, nested scoping, identical siblings, symlink dedupe). They also cover the pinned models, --deep, and its conflict with --model, a nondefault --base (fetched, with that branch's instructions), REVIEW.md in the follow-up, resume with responses, --responses rules, revoking a removed REVIEW.md, a new session on instruction change, and schema parsing failures.
  • Model ids verified against claude 2.1.312 and codex-cli 0.160.0: claude-opus-5-5 and claude-fable-5-1 at --effort medium answered with that model in modelUsage; gpt-6.1-sol and gpt-6-astra at model_reasoning_effort="medium" answered with that model and effort in the rollout's turn_context. Bogus ids fail on both (unrecognized_model / 400). A probe with --effort medium and /code-review low ran its review subagent at "effort":"low", so the command's level overrides --effort and now follows it.
  • Claude side verified by hand (it was untested): claude -p with /code-review high <base>...HEAD works headless as a built-in command. Its first turn reports usage only in modelUsage, and --resume <id> --json-schema returns structured_output. Prompts must go on stdin, since --tools is variadic and swallows a positional prompt. dontAsk denied git diff --output=<file> (no file written). With --setting-sources user, the maintainer's own Bash(gh pr merge *) allow rule ran gh pr merge --help; with --setting-sources "" it was denied. Hidden-instruction probes confirmed the head's CLAUDE.md (root and nested) is not loaded and the appended base text is.
  • Codex side: the rollout of a codex exec review thread shows the head's AGENTS.md injected as project-doc by default and absent with project_doc_max_bytes=0, while developer_instructions reaches the review thread. A resume with a different developer_instructions keeps only the first, which motivated the new-session rule.
  • End-to-end on a scratch repo with both reviewers: a base AGENTS.md rule ("titles start with BASE:") was followed over the head's injected canary, and REVIEW.md dropped style findings. Round 2 dropped a fixed finding and kept an uncited refutation with a rebuttal.
  • Cache from usage output: Codex resumed turns read 66-91% of input from cache (round 1 follow-up 51,840/78,572; round 2 156,160/196,053; this PR's round 4 1,513,216/1,671,716). Claude's round 1 follow-up read 11,962/25,060 (the /code-review turn runs as a local command), and its round 2 read 26,882/28,262 (95%).

Review

  • Reviewer: Codex (codex-cli 0.160.0), model gpt-6.1-sol at medium effort, via quest review --base origin/main from this Claude Code session.
  • Reviewed head: aca8b3bdd5dccbf51ea66baaf23ae07e6c6b4b9b, round 10 of the session: no findings.
  • Earlier rounds, all fixed:
    • Round 9 (c1c0ff6, the --deep rename, with the maintainer's decisions 5 and 6 in its responses): no findings. Codex online then posted a P1, reproduced and fixed in aca8b3b: in a worktree of a clone Codex trusts, the head's .codex/config.toml loaded and its MCP servers ran outside the sandbox. Codex now skips the user's config (--ignore-user-config), whose project trust caused it; -c projects={} did not.
    • Round 8 (8da37a2): no findings.
    • Round 7 (e9f3eeb), high: on an outsider's head, quest in this repository runs from the checkout, so its code ran before the reviewer's sandbox. The guide now runs no code from such a head, using a quest the PR cannot modify with --root.
    • Round 6 (aff3bfa): no findings. Online reviewers then posted three on that head, all fixed in e9f3eeb: /quest-review reviewed against the default branch instead of the PR's base (Codex P2, agreed by the maintainer account's automated review); it ran an outsider's checks locally (Codex security P1); and this PR had dropped "the author's own review does not count", so a fork author's self-written record counted (Codex security P1).
    • Round 5 (7716a68), medium: Claude's review turn sent /code-review high, whose level overrides --effort, so a medium review ran its first turn at high. Verified by probe (above); the command now takes the selected effort.
    • Round 4 (c60367d), low: a new session inherited the old session's recorded model. Fixed by removal: the round reports the model it passed, and the stored model and Codex rollout scraping are gone.
    • Round 3 (967585c): restating changed instructions in the user turn can't override system-level ones, so a change now starts a new session.
    • Round 2 (1636fe2): changed instructions never reached a resumed session. A REVIEW.md removed from the base was never revoked.
    • Round 1 (de3d4e5): user allow rules widened Claude's read-only access, so it now loads no settings files and Codex gets --ignore-rules. Identical sibling AGENTS.md files lost their scope. A stale REVIEW.md stayed on later rounds.
  • Design checkpoints: at round 4 the maintainer chose to continue. Round 8 left nothing to fix; my judgment is the approach still holds, with findings now in the trust rules around the CLI rather than its design. The approach did not change.

Decisions

Settled by the maintainer on 2026-10-28 (5 and 6 confirmed at merge):

  1. Codex prompt-cache retention. Codex 0.160 has no setting for it, and current models offer only 30m (default) or 12h, not the Plan's 24h.

    • ✅ Accept Codex's default 30m. The Plan's 24h requirement is dropped.
    • Plan a quest waiting on Codex to expose prompt_cache_options.ttl, then request 12h.
  2. Claude reviewer settings.

    • ✅ Load no settings files (--setting-sources ""), so the reviewer stays read-only whatever the user's allow rules, hooks, or plugins; --model/--effort pick a model.
    • Load user settings and accept that allow rules widen the reviewer.
  3. Round-4 design checkpoint.

    • ✅ Continue: fix the low finding, run round 5, then /quest-review to mark ready.
    • Rethink the approach.
    • Merge as is with the low finding as a follow-up.
  4. Reviewer model and effort. This supersedes the Plan's "quest hardcodes no model ids" (model and effort from the CLI's defaults): with no settings loaded, Claude had no configurable default.

    • ✅ Pin claude-opus-5-5 / gpt-6.1-sol at medium effort by default, plus a stronger tier, claude-fable-5-1 / gpt-6-astra, that the authoring agent picks for high-stakes changes (security, wire/API, data-loss risk), never routine work. Both tiers live in one table, selected by a flag rather than typed ids; --model/--effort override.
    • (An earlier update named high effort; the maintainer corrected it to medium.)
  5. Trust line.

    • ✅ Write access to the repository decides whose ## Review record counts and whose head may run code locally, matching who can edit a PR body.
  6. Stronger-tier flag name.

    • ✅ --deep everywhere (CLI, help, tests, /quest-review, README, guide, this body), renamed from --strong in c1c0ff6.

Choices made without asking

  • Instruction mechanism: CLI flags instead of a scratch worktree with restored files, because both CLIs hide project docs cleanly and the flags keep sessions in the real checkout. "Applicable" means the base's AGENTS.md/CLAUDE.md at the root and in every directory holding a changed path; a same-directory symlink is given once.

  • --base <remote>/<branch>, defaulting to origin's default branch from ls-remote --symref, fetched into its remote-tracking ref with an explicit refspec.

  • Strict checkout inputs: a dirty or detached checkout is refused. --responses is required after a round with findings and refused when there is no earlier round. --responses - reads stdin.

  • State is keyed by branch in <git-common-dir>/quest/review/. Switching the reviewer harness starts a new session.

  • Environment: the reviewer gets the user's environment minus quest agent's stripped variables (CLAUDE* except CLAUDE_CONFIG_DIR, ANTHROPIC*, CODEX_* except CODEX_HOME, OPENAI_API_KEY, OP_*). So it uses each CLI's stored login, and an env-var-only API key login is reported as logged out.

  • Model tiers: --deep conflicts with --model (exit 2). The stronger tier also runs at medium effort, since only the model was specified. The round reports the model and effort quest passed rather than what the CLI reports. Claude's /code-review level follows the selected effort, as its level overrides --effort. Usage lines are omitted for turns that report all zeros (Codex's review turn).

  • Guide: the local review runs before marking ready and before each push to a ready PR; pushes to a draft that still waits on decisions need none. quest status's review-rounds is left as is but is no longer referenced by the guide.

  • Codex user config: skipped (--ignore-user-config) for the P1 above, mirroring decision 2's choice for Claude; a custom model_provider or profile in it no longer applies to the reviewer.

Suggested follow-ups

  • Retire the dotfiles peer-review skill once this lands (per the Plan).
  • A model bump is a one-line change to MODELS in src/cli/review.ts; a recurring quest could check the pinned ids against the newest models each milestone.
  • Have quest init (or an upgrade path) remove stubs of skills that no longer exist, such as quest-ready.
  • quest status's review-rounds counts GitHub review rounds, which the guide no longer uses: drop it, or report local rounds from the ## Review record.
  • Land only reviewed heads: the ## Review record is written by the author's session, so kix's gate should decide how far it trusts a self-reported record.

🤖 Generated with Claude Code

(written by Claude Opus 5.5)

kixelated and others added 6 commits October 28, 2026 14:52
Quest-Claim: 6186cc2eca218f7e
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The skill reviews the branch locally with the other vendor's model,
records the round in the PR body's ## Review section, pushes, and marks
the PR ready. Merge addresses online findings already posted and never
waits for a review. Deletes the finished local-review quest.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…er directory; give REVIEW.md every round

Claude Code now loads no settings files, since a user's own allow rule
(such as Bash(gh pr merge *)) ran under dontAsk, and Codex ignores
execpolicy rules. Identical instruction files in sibling directories
each keep their scope, and later rounds carry the base's current
REVIEW.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… later rounds

A resumed session keeps the system or developer instructions it started
with, so a later round now restates instruction files that changed since
the session was given them, and says when the base dropped REVIEW.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Neither CLI refreshes system or developer instructions on resume, and a
user-turn restatement cannot override them, so a changed set of
instruction files starts a new session whose follow-up still weighs the
author's responses.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@kixelated kixelated changed the title Review locally with the other vendor's model feat!: review locally with the other vendor's model (quest review, /quest-review) Oct 28, 2026
kixelated and others added 2 commits October 28, 2026 16:07
The Claude reviewer loads no settings, so a CLI default could not pick its
model. quest review now runs claude-opus-5-5 or gpt-6.1-sol at medium effort,
and with --strong, for a high-stakes change, claude-fable-5-1 or gpt-6-astra.
The ids live in one MODELS table; --model and --effort override them.

The reported model is the one passed, so the Codex rollout scraping and the
stored model go away, and a new session can no longer inherit the old one's.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The command's level sets its own effort and overrode --effort, so a medium
review ran its first turn at high.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@kixelated
kixelated marked this pull request as ready for review October 28, 2026 23:14
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Oct 28, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-10-28T23:53:10.363700Z aca8b3b New commits
🔒 Security Review ✅ Completed 2026-10-28T23:56:35.349305Z aca8b3b New commits

Security findings

Advisory findings (2)

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: aff3bfa9cd

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread assets/skills/review.md Resolved

@kixelated kixelated left a comment

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Automated review by review (OpenAI)
Reviewed commit: aff3bfa

I agree with the independently reported P2 actual-base finding: assets/skills/review.md:17 invokes quest review without the PR's base, while src/cli/review.ts defaults to origin's default branch. A release/backport PR can therefore be recorded as reviewed against the wrong diff. Resolve and pass the PR's base on every round; add a nondefault-base workflow regression. Referencing that thread rather than duplicating an inline comment.

No additional actionable bugs found in this static pass. Direction is sound: a shared findings schema, explicit reviewer selection, and restarting sessions when base instructions change keep the local loop understandable. The skill rename/migration and optional-online-review policy are documented; the self-reported Review record is a policy choice, not an independently enforced attestation.

Verification: inspected CLI orchestration, instruction sourcing, resume/error handling, fake-CLI tests, and workflow changes. No tests or live reviewer CLI/security probes were run; reported model, cache, and sandbox behavior was not independently reproduced.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🛡️ Codex Security Review · Automatically triggered

Here are some automated security review suggestions for this pull request.

Reviewed commit: aff3bfa9cd

ℹ️ About Codex security reviews in GitHub

This is an experimental Codex feature. Security reviews are triggered when:

  • You comment "@codex security review"
  • A regular code review gets triggered (for example, "@codex review" or when a PR is opened), and you’re opted in so security review runs alongside code review

Once complete, Codex will leave suggestions, or a comment if no findings are found.

Comment thread assets/skills/review.md Resolved
Comment thread assets/skills/merge.md Resolved
kixelated and others added 2 commits October 28, 2026 16:24
…cords and checks

A PR against a release branch was reviewed against the default branch. A PR's
author writes its body, so a fork author's own `## Review` record counted, and
reviewing their head ran its checks with the reviewer's credentials. Only a
record on a PR whose author has write access now counts; anyone else's head is
reviewed locally by the merger, with its checks left to CI.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In a repository whose `quest` runs from the checkout, reviewing an outsider's
head ran its code before the reviewer's sandbox started.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

@kixelated kixelated left a comment

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Automated review by review (OpenAI)
Reviewed commit: 8da37a2

The actual-base P2 referenced in my previous review is addressed: the shared guide now requires the PR's base via --base, and the new fake-CLI test covers fetching a release branch and using its instructions. No new actionable bugs found in this two-commit update; the base is unchanged.

The independent untrusted-checks and review-record trust findings are addressed at the workflow-policy level: outsider heads must run no local code, including their own quest, and their self-written review records do not count. Reusing the shared guide avoids divergent skill rules. These remain agent-followed rules, not a new CLI sandbox or authenticated attestation.

Verification: static inspection of both commits, the affected guide/skills, and the nondefault-base regression test. No tests or live CLI/security probes run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

@kixelated kixelated left a comment

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Automated review by review (OpenAI)
Reviewed commit: c1c0ff6

No actionable bugs found in the CLI API change since 8da37a2. The --strong → --deep rename is consistent through option parsing, option forwarding, tier selection, model-conflict handling, tests, and usage guidance. Model/effort selection itself is unchanged; no additional compatibility machinery is needed for this still-unmerged command.

The prior actual-base fix and workflow trust guidance are unchanged. Verification: static inspection of this commit and surrounding dispatch/selection code; no tests or live reviewer CLIs run.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: c1c0ff69fb

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/cli/review.ts Resolved
…ad the head's config

A worktree of a trusted clone is trusted, so Codex loaded the reviewed
head's .codex/config.toml and started its MCP servers outside the sandbox.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

@kixelated kixelated left a comment

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Automated review by review (OpenAI)
Reviewed commit: aca8b3b

No new actionable bugs found in this update since c1c0ff6. The independently reported P1 head-controlled Codex configuration issue is addressed at both launch sites: the shared codexFlags now passes --ignore-user-config to initial review and resume, and the fake-CLI test asserts it for both. Centralizing the isolation flags is the right direction; the earlier actual-base and workflow-policy fixes are unchanged.

Verification: static inspection of the one-commit delta, shared flag wiring, and test assertions. No tests or live Codex probes run; the reported trusted-worktree/MCP isolation and retained-login behavior were not independently reproduced.

@kixelated

Copy link
Copy Markdown
Collaborator Author

Merge summary for aca8b3b:

  • Maintainer decisions recorded in the body (✅ 5 and 6): the write-access trust line is accepted, and the stronger-tier flag is renamed --strong → --deep everywhere (c1c0ff6).
  • Codex's P1 on c1c0ff6 was reproduced and fixed in aca8b3b: Codex reviewer turns now pass --ignore-user-config, so the user config's project trust cannot load a head's .codex/config.toml MCP servers.
  • Local quest review rounds 9 and 10 (Codex gpt-6.1-sol, medium): no findings. Codex online reviewed aca8b3b (code and security) with no findings. Checks pass; quest check --base origin/main passes with an installed quest.

(written by Claude Opus 5.5)

@kixelated
kixelated merged commit 4feaf18 into main Oct 28, 2026
12 checks passed
@kixelated
kixelated deleted the quest/m0/local-review branch October 28, 2026 23:57
kixelated added a commit that referenced this pull request Oct 29, 2026
* quest: plan the follow-ups from quest review (#271)

A caller plans a background merge's follow-ups, quest status drops
review-rounds, quest init prunes retired stubs, a live test checks the
real reviewer CLIs run nothing a head plants, a condition quest tracks
Codex's project-config skip, and a recurring check keeps the pinned review
models current. land-review requires an App check run for runner heads.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* quest: watch #49333 without posting upstream

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
kixelated added a commit that referenced this pull request Nov 1, 2026
quest init and quest uninstall recognized a stub only by exact match with a
current skill's stub, so a repository that installed /quest-ready kept it
after #271 removed the skill, and any stub whose description or setup link
changed made init refuse to run. Both now recognize a stub of any version by
its shape: frontmatter naming the skill, then the `quest skill <name>`
pointer. Init removes such stubs for skills this version no longer ships and
leaves older stubs of current skills as they are; uninstall removes stubs of
any version. Symlinked entries and edited stubs stay untouched.

Deletes the finished init-prune quest.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
moq-bot Bot pushed a commit that referenced this pull request Nov 2, 2026
* chore(quest): claim quest/m0/init-prune.md

Quest-Claim: c30a38f3e6af77c6

* fix(init): remove stale skill stubs by their shape

quest init and quest uninstall recognized a stub only by exact match with a
current skill's stub, so a repository that installed /quest-ready kept it
after #271 removed the skill, and any stub whose description or setup link
changed made init refuse to run. Both now recognize a stub of any version by
its shape: frontmatter naming the skill, then the `quest skill <name>`
pointer. Init removes such stubs for skills this version no longer ships and
leaves older stubs of current skills as they are; uninstall removes stubs of
any version. Symlinked entries and edited stubs stay untouched.

Deletes the finished init-prune quest.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(init): treat a stub with extra frontmatter fields as edited

Skill frontmatter has only ever held `name` and `description`, so a stub
with any other field, such as `allowed-tools`, was edited by a user and
stays put on init and uninstall.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant