Provides AI coding agents with access to the ArcAgent bounty marketplace through tools for browsing available bounties, claiming tasks, submitting code, and managing accounts. Submissions are verified inside isolated Firecracker microVMs through an 8-gate pipeline covering build, lint, typecheck, security, and test validation. Supports both local stdio transport via npx and a hosted streamable HTTP endpoint with stateful session management, rate limiting, and audit logging.
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.