← Back to Docs
Detectors

Nine architectural agents, seven hygiene layers

What are VibeCop's nine architectural detector agents?

VibeCop runs nine architectural detector agents against every pull request — three LLM-powered, two embedding-powered, three graph-powered, and one history-powered. Each agent is calibrated to your codebase's Stack Profile, and every finding it produces carries an entropy weight that feeds the Architecture Integrity Index across four axes.

What does each detector agent catch?

AgentCatchesAxis
Hallucinated AbstractionsLayers, wrappers, interfaces adding indirection without valueSimplicity
Semantic DuplicationLogic re-implemented in parallel paths instead of sharedReuse
Over-EngineeringPremature generalization, unused flexibility, config-for-config's-sakeSimplicity
Pattern DriftSame problem solved differently across the codebaseConsistency
Reinvented UtilitiesHand-rolled logic duplicating an existing library or internal utilityReuse
StructureDependency-graph cycles, high coupling, and excessive fan-outStructure
Layer ViolationsImports that cross a declared architectural layer boundaryStructure
Orphaned ModulesFiles with zero in-edges and zero out-edges in the code graphStructure
Reintroduced BugsFindings matching a previously resolved issue — a regression against review historyConsistency

Dependency Health used to sit on the Structure axis. It is now a hygiene layer alongside its sibling dependency-CVE check: it carries no axis, so it no longer moves the index. Architectural Complexity is the three graph agents above.

What hygiene checks run before deep analysis touches any code?

Seven deterministic hygiene layers run first, fast and free of false positives from hallucinated rules: dependency CVE scanning against the live osv.dev database with EPSS and CISA KEV enrichment, dependency-health checks, secret detection (23 patterns), static application security testing (SAST) across 18 CWE- and OWASP-tagged rules, infrastructure-as-code checks (22 rules), vendored-drift detection, and magic-number detection.

Do hygiene findings affect the Architecture Integrity Index?

No — hygiene findings carry no axis. They matter for security and compliance, but only findings from the nine architectural detector agents carry an entropy weight that affects the index; see the Architecture Integrity Index doc for the full scoring formula.

Related docs