pstack: disable-model-invocation skills still have "Use only when user ..." agent instructions
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 8.2k
- Forks
- 751
- Avg merge
- 12h 1m
- Merged PRs (30d)
- 43
Description
The two things seem to clash: "Use only when user ..." and disable-model-invocation: true. I assume when you invoke e.g. /tdd, these tokens still land in the context window. Example: https://github.com/cursor/plugins/blob/main/pstack/skills/tdd/SKILL.md
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with pstack/skills/tdd/SKILL.md and compare the "Use only when user ..." instructions with disable-model-invocation: true. Check how invoking /tdd assembles the skill context, then confirm the related skills no longer present contradictory instructions or tokens when the change is complete.
Written by the indexing model from the issue text.
Assessment
- Domain
- tooling
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 64/100