A Claude Code skill that runs the /code-review skill's multi-agent review pipeline in a loop over a given code scope until no high-confidence (≥80) issues remain — committing after every productive iteration, running a post-loop Opus review, and finishing with a full test suite.
Renamed from
simplify-loop. Previously this skill dispatched three hard-coded review agents (reuse, quality, efficiency). It now uses the verbatim/code-review5-agent + confidence-scoring pipeline, with a hard 80-score cutoff before fixes are applied — fewer iterations but every fix is backed by a CLAUDE.md citation, a verified bug, or a historical precedent.
- Resolves scope from your argument (file, glob, git range, PR number, natural language, or whole repo)
- Per iteration, runs the
/code-review-style pipeline (see below) - Filters issues by confidence score
>= 80(verbatim from/code-review); below-threshold findings are dropped - Commits after every productive iteration with a structured message
- Exits when 2 consecutive iterations produce no changes (min 3 iterations, hard cap 10)
- Opus post-loop review — reviews all loop commits for correctness, safety, regressions, with a built-in hallucination self-check
- Runs tests — auto-detects
pytest/npm test/go test/ etc., fixes failures via subagent (cap 3 attempts) - Final report — iterations, commits, review verdict, test result
Clone into your Claude Code user skills directory:
git clone https://github.com/Poxagronka/code-review-loop ~/.claude/skills/code-review-loopOr copy SKILL.md manually:
mkdir -p ~/.claude/skills/code-review-loop
cp SKILL.md ~/.claude/skills/code-review-loop/SKILL.md/code-review-loop <scope>
| Command | What it does |
|---|---|
/code-review-loop services/creative_testing.py |
Single file |
/code-review-loop services/*.py |
Glob |
/code-review-loop main..HEAD |
Git range |
/code-review-loop 42 |
PR #42 (requires gh) |
/code-review-loop |
Current uncommitted changes |
/code-review-loop whole repo |
Entire tracked codebase |
/code-review-loop все питон файлы в services/ |
Natural language |
1. Haiku: collect relevant CLAUDE.md paths for the scope
2. Haiku: produce a short summary of what the scope does
3. Parallel x5 (Sonnet) — return issues, no fixes:
Agent 1: CLAUDE.md adherence audit
Agent 2: shallow bug scan
Agent 3: git blame / history context
Agent 4: comments on past PRs that touched these files
Agent 5: code-comment compliance (TODOs, WARNINGs, HACKs)
4. Parallel xN (Haiku) — score each issue 0/25/50/75/100 per verbatim rubric
5. Filter: drop any issue with score < 80
6. Sonnet fix agent — applies only the surviving high-confidence issues
After loop (Opus):
Reviews all commits, self-checks for hallucinations, fixes verified concerns
Final:
Auto-detected test runner → fix subagent if red (cap 3 attempts)
The /code-review slash-command is designed for one pass over a single GitHub pull request — it ends by gh pr comment-ing the surviving issues onto the PR. code-review-loop reuses the same agent prompts, scoring rubric, false-positive list, and 80-score cutoff verbatim, with two deliberate omissions:
- No eligibility check — there's no PR draft/closed/already-reviewed state to gate on; the loop runs against a local scope.
- No
gh pr commentstep — surviving issues are fed to a fix agent instead of posted as PR comments.
Everything else — the 5 review-agent prompts, the rubric, the filter threshold, the false-positive list — is preserved exactly as in the upstream skill.
The loop exits when 2 consecutive iterations produce no file changes on disk, with a minimum of 3 iterations. Hard cap at 10. Iterations where every raw issue is filtered out by the 80-score cutoff also count as "no changes" — so a clean scope is detected naturally without needing an LLM-reported "done" signal.
- Refuses to run on
main/masterbranch - Refuses to run with dirty working tree (unrelated uncommitted files)
- Never uses
git add -Aorgit add .— only adds specific changed files - Never amends commits — always creates new ones
- Never pushes — user decides when to push
- Confidence-score cutoff (
>= 80) prevents low-confidence findings from triggering edits - Post-loop Opus reviewer self-checks every concern against the live file before reporting
refactor(code-review-loop): iter N — <summary>
Scope: <scope description>
Files: N modified
Issues fixed: K
Co-Authored-By: Claude Code <noreply@anthropic.com>
- Claude Code
- Git repository
ghCLI (optional — Agent #4 degrades gracefully without it; required only for the#42PR scope form)- Test runner auto-detected:
pytest,npm test,go test ./...,cargo test,bundle exec rspec,make test
| Phase | Model | Why |
|---|---|---|
| CLAUDE.md path collection | Haiku | Trivial directory walk |
| Scope summary | Haiku | Short text generation |
| 5 review agents | Sonnet | Pattern-matching across files |
| Per-issue confidence scorer | Haiku | One small rubric eval per issue |
| Fix agent | Sonnet | Targeted edits |
| Post-loop code review | Opus | Safety-critical, hallucination resistance |
| Test fix | Sonnet | Debugging |
MIT