AgentHub acts as a central nervous system for AI coding agents, enabling coordination between tools like Claude Code, Cursor, VS Code, and Gemini CLI. It implements soft-locking through intent-based coordination, allowing agents to declare file editing intentions before making changes. The system detects conflicts, facilitates real-time messaging between agents, and includes built-in code review workflows and expert escalation capabilities.
Cognium trust score
73%
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.