bai-os/Sentinel Review

AI code review with local agents (Claude Agent SDK): grounded findings (file + line) posted as a single PR review. Code goes only to the model provider you configure — no third-party review service.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
anthropic-api-keyAnthropic API key for the review agents. Store it as a repository or organization secret. Absent on fork PRs by design — the review is skipped with an explanatory job summary.no""
github-tokenToken used to read the PR and post the review.no${{ github.token }}
agentsComma-separated subset of reviewers to run (correctness|security|tests), overriding the repository policy. Leave empty to honor .sentinel.yml.no""
dry-runPrint the review into the job summary instead of posting to the PR.nofalse
base-urlGitHub API base URL override (GitHub Enterprise Server).no""

no outputs