tushardhole/Safe PR Review Agent

Provider-agnostic AI PR reviews with schema-safe output normalization, diff-anchor filtering, and inline fallback safety.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github_tokenGitHub token for reading PR data and posting review comments.yes
openai_api_keyAPI key for the OpenAI-compatible provider.yes
openai_base_urlBase URL for OpenAI-compatible API endpoint.no
modelModel name to use for code review.no
exclude_patternsComma-separated glob patterns for files to exclude.no
max_filesMaximum number of changed files to review.no
review_levelReview depth. One of quick, thorough, security-focused.no
extra_promptExtra instructions appended to the system prompt.no
max_context_roundsMaximum file-reading tool call rounds for context gathering.no

no outputs