synaptent/Aragora AI Code Review

Multi-agent AI red team code review for pull requests

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
agentsComma-separated list of agents (anthropic-api,openai-api)noanthropic-api,openai-api
roundsNumber of debate roundsno2
focusFocus areas (security,performance,quality)nosecurity,performance,quality
anthropic-api-keyAnthropic API key for Claudeno
openai-api-keyOpenAI API key for GPTno
openrouter-api-keyOpenRouter API key (fallback provider)no
post-commentPost review as PR commentnotrue
fail-on-criticalFail workflow if critical issues foundnofalse
max-diff-sizeMaximum diff size in bytesno50000
pr-numberPull request number override for manual/self-test runsno""
failure-thresholdFail workflow if total issues exceed this count (0 = disabled)no0
output-formatAdditional output format besides PR comment (sarif, json, none)nonone
sarif-uploadUpload SARIF to GitHub Security tabnofalse
emit-receiptEmit a portable, verifiable Open Decision Receipt (ODR) for the review and upload it as a build artifact. Runs a heterogeneous-model merge-quorum collection (dry-run, never posts) and bridges it to a signed-off-able receipt. Set to "true" to opt in; this performs a second model pass.nofalse
receipt-reviewersSpace-separated model families for the receipt quorum (keys must be provided)noclaude openai
use-secrets-managerLoad provider API keys from AWS Secrets Manager instead of inputs (the org's keyless pattern). Requires AWS credentials in the job env (e.g. via aws-actions/configure-aws-credentials with OIDC). When "true", the receipt quorum hydrates keys from Secrets Manager.nofalse
aws-regionAWS region for Secrets Manager (when use-secrets-manager is true)nous-east-2
namedescription
review-pathPath to the generated review file
review-generatedWhether a review comment was generated
review-json-pathPath to the generated JSON review file
review-log-pathPath to the review log file
unanimous-countNumber of unanimous issues found
critical-countNumber of critical issues found
high-countNumber of high severity issues found
medium-countNumber of medium severity issues found
low-countNumber of low severity issues found
total-countTotal number of severity-tagged issues (critical+high+medium+low)
risk-areas-countNumber of risk areas noted
split-opinions-countNumber of split-opinion items (agent disagreement)
agreement-scoreAgent agreement score (0-1)
sarif-pathPath to SARIF output file (if generated)
receipt-pathPath to the verifiable ODR decision receipt (if emitted)
receipt-verdictReceipt verdict (PASS / CHANGES_REQUESTED)
receipt-digestSHA-256 JCS content digest of the receipt
receipt-verifiedWhether the emitted receipt passed schema + digest verification