Repository navigation
feat(advise): run by hand, on request, or as a subagent QA check - #26
Merged
Merged
Conversation
Add disable-model-invocation so Claude cannot start the advise skill on its own, since a run sends repository files to OpenAI. Replace the hardcoded model version in the description, body and README with generic wording. Closes #25 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Co55SexrgzuhD19cvKym1S
Drop disable-model-invocation, which also blocked subagents from preloading the skill. The skill now runs when the user types the command, asks for it (governed by Skill permission rules), or a subagent the user defined runs it before reporting back. Inside a subagent it runs Codex alone and hands disagreements to the parent. Closes #25 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Co55SexrgzuhD19cvKym1S
GauranshMathur
changed the title
GauranshMathur
marked this pull request as ready for review
October 4, 2026 10:55
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Requested by Arkhaya · project thread
Before: the advise skill could be started by the command or by asking Claude, there was no documented way to restrict that, it could not run as a QA step inside a subagent, and its description named a specific model version ("Fable 5.1").
After: the README documents three ways to run it. You can type
/codex-headless:advise. You can ask Claude for it, and you control that withSkill(codex-headless:advise)permission rules (askto confirm each time,denyto allow only the command). Or a subagent you define can preload it withskills:and run thedonecheckpoint before it reports back. The skill and README now call the second advisor "a Claude advisor subagent".disable-model-invocation: truewas tried first and dropped, because it also stops subagents from preloading the skill.How: the skill's "When to run it" section now counts the user's own configuration as asking. A new "Inside a subagent" section runs Codex alone, because a subagent cannot start another subagent or ask the user, and hands any disagreement back to the parent.
claude plugin validate . --strictpasses and all 50 tests pass.Closes #25
🤖 Generated with Claude Code
https://claude.ai/code/session_01Co55SexrgzuhD19cvKym1S