valani9/vstack agent-quality gate

Diagnose an AI-agent trace with 34 organizational-behavior patterns; fail the build on findings.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
tracePath to the agent trace JSON to diagnose.yes
fail-onMinimum finding severity that fails the build, one of: none | trace | low | moderate | medium | high | critical. Use 'none' to report without ever failing.nohigh
modeAnalysis depth: quick | standard | forensic.nostandard
recipeOptional named recipe bundle (see `vstack-recipes`).no""
clientLLM client for analyzers that need one: none | anthropic | openai | ollama. Defaults to 'none' (deterministic analyzers only, no API key needed). For full findings, set 'anthropic'/'openai' and provide the matching API key via env.nonone
shapeForce trace shape: individual | team | org (default: inferred).no""
sarifIf set to a path, also write a SARIF 2.1.0 report there (upload it with github/codeql-action/upload-sarif to surface findings in code scanning).no""
commentIf set to a path, write the findings summary (Markdown) there so you can post it as a sticky PR comment (e.g. marocchino/sticky-pull-request-comment).no""
versionvalanistack version to install (e.g. '0.45.0'). Empty = latest.no""
python-versionPython version to set up.no3.13
namedescription
max-severityHighest finding severity seen (or 'none').
findings-countTotal number of findings.
reportPath to the written JSON report.
sarifPath to the written SARIF report (empty unless `sarif` input set).
commentPath to the written Markdown comment (empty unless `comment` input set).