PMAT (Pragmatic Multi-language Agent Toolkit) provides zero-configuration AI context generation for any codebase. Analyzes code complexity, grades technical debt (A+ through F), runs mutation testing with 85%+ kill rate validation, and provides repository health scoring. Supports 17+ programming languages through CLI, MCP, or HTTP interfaces. Offers 19 MCP tools for deterministic code analysis including tdg_analyze_with_storage, quality_gate, and refactor_start.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.