2,226 tools found
Create plugin-packaged specialist subagents with validated names, detailed personas, read-only defaults, and optional companion routing skills.
Transforms raw agent evaluation runs into decision-ready reports with explicit outcome populations, denominators, latency data, and experiment conditions
Deterministically inject sandbox/tool/worker/checkpoint faults into an agent workflow and produce a recovered/contained/unrecoverable verdict.
Authors and validates Agent QA tests, suites and hooks via MCP or CLI while preserving canonical IDs and schema contracts.
Skill for debugging and fixing failed Agent QA runs from MCP evidence: minimal patches, validated definitions, and a narrow verification rerun.
Triages failed Agent QA runs from MCP evidence into a fixed failure category with confidence, ownership and next action.
Plans safe recurring agent runs with cron, external schedulers, loops, or built-in clocks while avoiding tight LLM timers.
Coordinate a specialist development squad with deliberate routing, compressed briefings, versioned reports, and explicit user decisions.
Turn a Rex requirements report into an ordered implementation checklist with dependencies, milestones, risks, and binary definitions of done.
Produces system architecture blueprints covering data models, API contracts, module structure, design patterns, and security boundaries.
Prepare reviewed and tested applications for deployment with containers, gated CI/CD, environment configuration, and verification checklists.
Review code for concrete security, correctness, reliability, and blueprint-conformance defects before testing or deployment.
