A/B test AGENTS.md, Agent Skills, MCP setups, and coding-agent commands on your own repo with isolated worktrees and deterministic checks.

agent-evals agent-skills ai-agents automation coding-agents context-engineering developer-tools llm python testing
1 Open Issue Need Help Last updated: Aug 11, 2026

Open Issues Need Help

View All on GitHub
help wanted benchmark-case

A/B test AGENTS.md, Agent Skills, MCP setups, and coding-agent commands on your own repo with isolated worktrees and deterministic checks.

Python
#agent-evals#agent-skills#ai-agents#automation#coding-agents#context-engineering#developer-tools#llm#python#testing