Review Fix Loop — Development skill for Claude Code
Run a review, fix the findings, and review again until no blocker or major findings remain.
How to install Review Fix Loop
Installs to ~/.claude/commands/mschabow-agentic-sdlc-review-fix-loop.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/mschabow/agentic-sdlc/HEAD/.claude/commands/review-fix-loop.md -o ~/.claude/commands/mschabow-agentic-sdlc-review-fix-loop.md Restart Claude Code, or start a new session, for it to be picked up.
What Review Fix Loop does
name: review-fix-loop version: 1.0.0 description: Run a review, fix the findings, and review again until no blocker or major findings remain. Use when the user says "fix these and re-run the review", "address all issues", or hands over review findings from prism-review, /code-review, or a pasted review file. changelog:
- "1.0.0 (2026-10-03): Added to the sdlc-workflow plugin so it ships to every account from one source."
Review-fix loop
The user reviews code, fixes what the review
Alternatives in Development
- Ralphy — My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & 2.8k ★
- Overnight PRs — Autonomous overnight loop — verify issues against the codebase, close stale ones, ship PRs through /ship (bug 324 ★
- Iterate Feature — Iterate on the feature "$ARGUMENTS" to fix issues and address feedback 180 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Gap Loop
Loop post-implementation gap analysis until 2 consecutive clean rounds (bounded at 6, per-finding 2-fix limit,
Sdlc Loop
Run the SDLC orchestration loop — auto-dispatch eligible tasks until a gate, blocker, circuit-breaker, or comp
Sdlc Review Fix
Fix blocking issues to get APPROVED. Use when addressing review feedback. Triggers: fix issues, address review
Cpv Batch Scope Diagnose And Fix
Same-turn diagnose + fix across a fleet of project folders. One cpv-doctor-agent per project scans the request
M Review Again
Review Again: Multi-Round Review & Fix Loop
Evil Mode
EVIL mode — adversarial sweep with scored findings, adversarial verification, and loop-until-dry. The upgrade
Related Agents
Game Tester
QA tester for EOB1 ScummVM CHT fan translation. Drives scummvm headlessly in WSL Xvfb (no window appears on Wi
Aiskills Code Reviewer
Reviews diffs and pull requests with visible per-dimension passes and severity-classified findings (Blocker/Ma
Jarvis Validator
Adversarial, read-only audit of a built Jarvis folder against its jarvis-spec.md and knowledge/security-checkl