storkme/PR Second Opinion

Independent, agentic, OpenRouter-backed second-opinion review on a PR.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
openrouter-api-keyOpenRouter API key (https://openrouter.ai/keys).yes
github-tokenToken with pull-requests:write. Default: the workflow token.no${{ github.token }}
pr-numberPR number to review. Default: the PR from the triggering event.no${{ github.event.pull_request.number }}
modelOpenRouter model id for the review passes.noz-ai/glm-5.2
kAgentic passes to union. K=1 (default) skips the merge.no1
merge-modelOpenRouter model for the K>1 merge. Default: same as model.no""
projectProject name used in the review prompt.no${{ github.event.repository.name }}
guidance-filePath (in the repo) to this project's review checklist / 'memory'.no""
exclude-globsComma-separated globs to drop from the diff. Default: sensible set.no""
max-diff-charsCap on the diff size sent to the model.no60000
pass-timeout-secondsPer-pass timeout.no900
toolsAgent tool grant. 'read,bash' (default) greps for callers/tests; set 'read' to drop shell access on repos with untrusted PR authors. See README Security.noread,bash
reasoningWhether the model is a reasoning model. Default true (the default z-ai/glm-5.2 is). Set false for a non-reasoning model so pi omits reasoning params.notrue
fail-on-degradedFail the check (exit 2) when a pass degrades — times out, exits non-zero, or produces no review — and no review was posted. Surfaces reviewer malfunction, not review findings (a posted review always passes). Set 'false' for the old always-green behavior.notrue

no outputs