claude-loop
Turns vague improvement goals into measured, anti-gaming loops with a deterministic stop.
- Stars
- 1
- Forks
- 0
- Updated
- Updated Jun 30, 2026
Turns vague improvement goals into measured, anti-gaming loops with a deterministic stop.
claude-loop converts “make it better” into a project-specific scorecard and a repeatable cycle: score real signals, triage the weakest link, fix one slice, verify independently, and score again. Its init, score, run, and status modes keep the rubric and checkpoint state in .loop/. The loop stops after the target score is reached twice, with 90 as the default, instead of running indefinitely.
Resource types
Use cases
Platforms
Review high-risk code through independent specialist agents and synthesis.
Audit a repository locally and turn cited findings into clear priorities.
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Review code with adjustable roast levels and actionable fixes.
Score and audit Claude SKILL.md files