This server bridges Claude Code with Kimi AI to provide structured code consultation through a challenge-loop protocol. Kimi serves as a read-only skeptic in four configurable roles — skeptic, architect, debugger, or judge — challenging proposals and offering alternative perspectives while Claude retains decision authority. The server supports manual consultation mode for on-demand requests and auto mode for proactive review, with a transparent evidence chain showing which files and searches informed each response.
Cognium trust score
64%
Tier
Scanned
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 2026-09-01.
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.