weitzer-org/GSR Code Review

Multi-agent Gemini-powered code review that posts inline findings on a pull request.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
gemini-api-keyGemini API key used to run the review. Store as a repo/org secret.yes
github-tokenToken used to read the PR diff and post review comments.no${{ github.token }}
modeReview strategy: "subagent" runs the full swarm of specialized agents (Architecture, Logic, Security, TechDebt, Testing, ...) plus a deduplication pass and finds more issues but costs more tokens/time. "basic" runs a single general-purpose review pass, faster and cheaper. nosubagent
fail-on-severityFail the workflow if a finding at or above this severity is reported: one of "critical", "high", "medium", "low", or "none" to never fail. nonone
gemini-modelOverride the Gemini model used for review.no""
max-review-filesMaximum number of changed files to review before truncating.no300
agentsComma-separated list of subagent IDs to run (e.g. "logic,security"), or "all" to run every agent. Only applies when mode is "subagent"; ignored (with a warning) when mode is "basic". Defaults to "all". noall

no outputs