WiseGit indexes git history to extract developer decision intent and classify code functions by freeze score. When AI agents edit files, WiseGit provides decision manifests showing which functions are frozen, stable, or open for modification. This prevents AI from removing intentional code that appears unmotivated, such as workarounds for platform bugs or race conditions.
Cognium trust score
88%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
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.