Claude Code regression blocks skill-to-skill calls to built-in /code-review
sayss7598 · ghdev · 2026-07-21
Built-in /code-review no longer composes inside another skill
A regression in Claude Code means the built-in code-review skill is tagged disable-model-invocation, so another skill trying to call it programmatically gets refused.
Observed behavior
- Typing /code-review manually still works.
- Calling it from another skill fails with:
Skill code-review cannot be used with Skill tool due to disable-model-invocation
- The breakage is specifically in skill-to-skill composition, not in the skill itself.
Why it matters
The reporter uses a custom ship-it skill that automates a full land-a-change flow:
- Branch and commit.
- Sync default branch and run tests.
- Push and open a PR.
- Run code review as a review gate.
- Fix issues, re-review, verify CI, then merge.
Step 4 depends on invoking /code-review; without it, the workflow degrades into a hand-written inline review that the reporter says is materially worse.
More from coding & agent
- Hugging Face wraps 6-month Training Agents series with open recordings and code — SergioPaniego · 2026-10-26
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26