cassianor/agentreview

Multi-agent AI code review powered by Anthropic Claude. Posts findings as PR review comments.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
anthropic-api-keyAnthropic API key (ANTHROPIC_API_KEY). Store as a repository secret.yes
openai-api-keyOpenAI API key. Required only when provider is "openai".no""
providerLLM provider to use: "anthropic" (default) or "openai".noanthropic
agentsComma-separated list of agents to run. Default: all agents.nosecurity,performance,style,tests,docs,dependency,accessibility,i18n
base-refGit ref to diff against. Defaults to the PR base branch.no""
modelClaude model to use (e.g. claude-sonnet-4-6, claude-opus-4-7).noclaude-sonnet-4-6
fail-onExit with code 1 if findings at or above this severity exist (critical|high|medium|low|never).nocritical
post-commentsPost findings as inline PR review comments (requires GITHUB_TOKEN).notrue
github-tokenGitHub token for posting PR comments. Defaults to the automatic GITHUB_TOKEN.no${{ github.token }}
namedescription
findings-countTotal number of unique findings after synthesis.
has-critical"true" if any critical findings were found, "false" otherwise.
report-jsonPath to the JSON report file written to the runner.