julien777z/Code Review Action

Review pull requests with Claude or Cursor — inline severity-rated comments and an approval verdict.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit Jul 11, 2026
License
MIT

Pinned Snippet

workflow.ymlSHA-pinned
uses: julien777z/code-review-action@cd88357f145af4c31d6aff33384b8c1696f3fe88 # v0.3.2

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
github-tokenToken used to read the diff and post reviews and check runs.${{ github.token }}
resolve-tokenToken used to resolve the action's own review threads. The default GITHUB_TOKEN cannot resolve threads (GitHub rejects it with "Resource not accessible by integration"), so set this to a GitHub App installation token (or a fine-grained PAT) with pull-request write to enable auto-resolution. Empty falls back to github-token.no""
anthropic-api-keyAnthropic API key for the Claude backend and PR-summary generation.no""
cursor-api-keyCursor API key for the Cursor backend.no""
review-modelBackend to use — auto, claude, or cursor.auto
first-review-modelBackend for the PR's first review (opened/ready). Empty falls back to review-model.""
claude-modelAnthropic model id for Claude Managed Agents reviews and Claude PR-summary generation.claude-opus-4-8
cursor-modelCursor model id for the Cursor backend.composer-2.5
additional-contextExtra context injected into the review prompt.""
approval-includeComma-separated severities that, if open, request changes (otherwise comment only).critical
approval-disablePost review comments only and skip the approval verdict and check run.false
pr-review-summaryAppend an AI-generated summary (bullets, risk note, overview) to the PR description on open/ready events.true
enforce-project-rulesEnforce the repository's own coding rules as part of the review. Each backend loads the rule files it understands from the checked-out repo. No-op when the repository defines none.true
project-rules-severityFixed severity to report project-rule violations at (critical, high, medium, or low). Empty lets the review rate each violation itself.""
simplify-suggestAlso suggest code simplifications using the code-simplify skill, as optional suggestions.false
simplify-suggest-severitySeverity to report simplification suggestions at (critical, high, medium, or low). Empty defaults to low.""
simplify-nearby-codeExtend simplification suggestions to weigh nearby and related code as review criteria.false
min-severityLowest severity worth posting and counting — critical, high, medium, or low.low
low-findings-capMaximum number of low-severity findings to post per review; the runner selects the most important lows once the review stream ends.3
max-findingsOverall cap on inline comments per review (empty = uncapped).""
include-pathsComma/newline-separated globs to restrict the review to.""
exclude-pathsComma/newline-separated globs to skip (generated files, lockfiles, vendored code).""
trigger-phraseComment phrase that triggers a manual review.agent review
review-draftsReview draft pull requests.true
pr-numberPR number to review on a workflow_dispatch run.""
review-timeout-minutesOverall cap on the review agent's runtime in minutes. The agent streams findings incrementally, and a few minutes before the cap the runner interrupts it and asks it to immediately emit any findings it has identified but not yet reported, so a timed-out review still posts what was found. Set to 0 to disable.15

no outputs