mcpField
R
review-loop

review-loop

github.com/lwlee2608Testing & quality169 installsUpdated 1d ago
Repository

About review-loop

review-loop is a coding review skill for teams that want fixes independently reviewed before they are committed. It defines a bounded review-and-fix cycle, repository checks, and an end-of-run report.

Key features

  1. 01Fresh subagent review each round
  2. 02Second opinion in the first round
  3. 03Fix selection by severity
  4. 04Repository checks after fixes
  5. 05Five-round cap and stop rules
  6. 06Commit and reporting guidance

Use cases

  1. 01Reviewing code changes and their fixes
  2. 02Running focused re-reviews of diffs
  3. 03Keeping review work within a round limit
  4. 04Reporting skipped and unresolved findings

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lwlee2608/agent-skills --skill review-loop

After installing, type/review-loopin Claude Code to confirm it loaded.

Details

From the project README

Review Loop

Review, fix, re-review until a round finds nothing worth fixing. Fixes are new code — they need their own review.

Rules

  1. Review in a fresh subagent every round. Invoke review-code with <target> --sub (default target diff). If review-code is missing, spawn a subagent to review for correctness, security, resource, and performance defects, rating each finding Yes / Judgment call / No for worth fixing. Never review your own fixes inline.

  2. Pass --second-opinion to round 1 only. Round 1 reviews the full change; later rounds review small fix diffs, where another agent adds cost but little coverage. Its Final Call reads code before any fixes exist, so it does not break rule 1.

  3. Use diff from round 2 for every target, including paths. GitHub does not see unpushed fixes, re-reviewing the whole codebase wastes context, and path-scoped reviews can miss fixes in related files. For pr <number>, check out the PR first.

  4. Fix every Yes; fix a Judgment call only if Trivial or Small. Skip No. When a round has a Final Call, act on it instead: Fix → fix, Optional → fix only if Trivial or Small, Skip → skip. Do not re-fix or re-argue a skipped item when a later round raises it again.

  5. Run the repo's checks after each round's fixes (make build / make test / make lint, else native commands). Fix breakage before the next review.

  6. Stop when a round has nothing new to fix. Cap at 5 rounds; round 5 is review-only, even if it finds actionable issues. Do not edit after that review — hand the open findings to the user. If a fixed finding comes back in any round, stop fixing and report the open findings.

  7. Commit each fix unless told otherwise. --commit each (default) — one commit per fixed finding. --commit end — one commit after the loop stops. Never push. On the default branch, branch before the first commit — otherwise diff anchors at HEAD and committed fixes drop out of the next review.

  8. Report at the end: rounds run and why it stopped, fixes (path:line — what changed), skipped findings with a reason each, open findings, and check results.

Comments

Markdown supported