MCP servers and skills: search, filter by where they run, and compare.
Is this SWE-bench-style task fair to grade an agent on? Agentic screening with verified evidence, measured against human annotations. Also an agent skill: /fairtask
SkillMITFew starsNo key
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.
PythonMIT★ 154No key
Best-of-N for coding agents with a same-model verifier, run your task N times in isolated git worktrees and apply the verified winner. A /ultra command for opencode, plus a standalone CLI.
SkillMIT★ 4Few starsNo key
Spec-to-task lifecycle manager for AI coding agents. Decomposes specs into atomic, dependency-ordered tasks. Agents execute with 2 tool calls instead of hundreds.
SkillMIT★ 8No key
An open-source, cost-efficient (<zsh.50/task), and extensible Agentic Software Development Life Cycle (AIDLC) framework
SkillApache-2.0Few starsNo key
Claude Code skill: route subagent workers by task profile. Frontier reasoning for planning, judging and synthesis; commodity pricing for execution. Based on Anthropic's benchmarked Fable-orchestrator/
SkillApache-2.0★ 1Few starsNo key
Who stands behind it
