maxi-tools/Maxi Review

Review pull requests with Maxi analyzer context and Jules feedback.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
jules_api_keyJules API key (create one at jules.google.com).yes
github_tokenGitHub token with pull-requests:write, statuses:write, issues:read (the review fetches linked-issue acceptance criteria), and checks:read (when ci_signal is enabled) for reviews, plus contents:write and issues:write for /maxi commands. Usually the default GITHUB_TOKEN secret.yes
fail_onWhen to fail the commit status check: never | blocking | any. Default blocking.noblocking
skip_draftsSkip review on draft PRs.notrue
skip_forksSkip review on PRs from forks (prompt-injection risk).notrue
bypass_labelLabel that, when applied to a PR, skips the review entirely.nomaxi-review-override
status_contextCommit status context name.nomaxi/review
extra_instructionsFree-form Markdown appended to the review prompt. Use to add project-specific rules, frameworks, or focus areas directly from the workflow.no""
rules_filePath (in the repo) to a Markdown file whose contents are injected into the prompt. Default .github/maxi-review-rules.md if it exists. Set to empty string to disable.no.github/maxi-review-rules.md
timeout_minutesHow long to wait for Jules to return a review before giving up. Default 30. Real reviews on non-trivial PRs often take 15-25 minutes; do not set below 20 or you will miss legitimate reviews.no30
analyzer_modeAnalyzer mode: auto runs Opengrep and PMD/CPD from PATH when no output files are configured; off skips analyzer execution and ingestion.noauto
opengrep_jsonOptional path to Opengrep/Semgrep-compatible JSON output to ingest.no""
opengrep_sarifOptional path to Opengrep/Semgrep-compatible SARIF output to ingest.no""
pmd_xmlOptional path to PMD XML output to ingest.no""
cpd_xmlOptional path to CPD XML output to ingest.no""
review_ignore_globsNewline- or comma-separated globs for generated/vendored paths to drop from the reviewed diff so the diff budget is spent on source (e.g. a bundled action's dist/). Empty uses a sensible default set (dist/**, *.map, lockfiles, **/generated/**); set to 'none' to disable filtering.no""
retrieval_modeAgentic retrieval loop. auto lets the reviewer request read_file, grep, and list_references at the PR head before the verdict; off disables it.nooff
dedupe_reviewersDedupe against other review bots. auto fetches active non-self inline review comments (CodeRabbit, Codacy, Codex, ...) and tells the model not to restate them; off disables it.nooff
ci_signalIngest CI evidence into the review. auto fetches the PR head check-runs (requires checks:read on github_token); off skips them. Supplied test_report/coverage_summary files are ingested regardless.nooff
test_reportOptional path to a test report file (e.g. a JUnit or text summary) to ingest as CI evidence for the review.no""
coverage_summaryOptional path to a coverage summary file (e.g. a coverage delta report) to ingest as CI evidence for the review.no""
commandMaxi review command to run for workflow_dispatch, for example /maxi apply-all or /maxi fix <finding-id>.no""
pr_numberPull request number for workflow_dispatch command runs.no""
namedescription
review_artifactsJSON array of harvested maxi.review.v1.review-artifact objects from /maxi harvest.