Cross-model audit gate with autonomous quality loop — AST hybrid scanning, fitness gate, blast radius, structured orchestration. 19 MCP tools, 743 tests. CLI + Claude Code plugin.
Agent
Accessibility Auditor — performs static code analysis for WCAG 2.1 AA compliance, aria attributes, semantic HTML, and keyboard support. Activated when accessibility domain is detected. NOTE — this is STATIC analysis only; runtime browser testing is handled by ui-reviewer.
Agent
Compatibility Reviewer — checks backward compatibility, migration safety, breaking API changes, and consumer impact. Activated when migration domain is detected (schema changes, API surface modifications).
Agent
Compliance Officer — checks license compatibility, PII handling, data retention, and regulatory patterns. Activated when compliance domain is detected (license files, personal data handling, GDPR/CCPA patterns).
Agent
Concurrency Verifier — analyzes async coordination, shared state access, race conditions, and deadlock potential. Activated when concurrency domain is detected (Promise.all, Workers, shared state, locks).
Agent
Documentation Steward — verifies doc-code consistency, API documentation completeness, and changelog coverage. Activated at T3 when documentation domain is detected.
Agent
Documentation Sync — extracts facts from code (hook counts, tool counts, test counts, module counts, versions) and fixes mismatches in all documentation files. Runs before squash commit.
Agent
Agent "i18n-checker" from berrzebb/quorum, covering i18n checker (claude code), claude code tool invocation, add missing key to both locale files at once, language-aware hardcoded string detection and domain-specific anti-patterns.
Agent
Headless worker for quorum — receives task + context, implements code, runs tests, submits evidence via auditsubmit tool, handles audit corrections. Use when the orchestrator needs to delegate a coding task to a worker agent.
Agent
Infrastructure Validator — checks Dockerfile security, CI/CD config, environment variable handling, and deployment safety. Activated when infrastructure domain is detected.
Agent
Observability Inspector — checks logging coverage, structured log format, error context, metric instrumentation, and trace propagation. Activated at T3 when observability domain is detected.
Agent
Performance Analyst — reviews changes for performance regressions, bundle size impact, query efficiency, and runtime complexity. Activated when performance domain is detected (DB queries, heavy computation, bundle config changes).
Agent
Read-only RTM generator — reads all track work-breakdowns, verifies each requirement against the actual codebase using deterministic tools, and produces 3 Requirements Traceability Matrices (Forward, Backward, Bidirectional). Use when the orchestrator needs to establish or update the RTM before distributing work.
Agent
Find UI issues that code-level analysis (scout, codemap, dependencygraph) cannot detect. Launches a real browser to check rendering, visual states, interactions, a11y, and runtime errors. Use after FE implementation to catch issues invisible to static analysis.