Back
Ready for Agents
Ready for Agents
#readyforagents
Ready for Agents tests how coding agents use your library. We run Claude Code, Codex and Gemini on real tasks with your package, with your llms.txt, skill, docs MCP and AGENTS.md switched on one at a time. The report shows which version the agents picked, whether the code passed hidden tests, which docs channel they opened, and what each run cost.
It grew out of worklore research: 135 graded agent runs on three libraries. Early access now.
It grew out of worklore research: 135 graded agent runs on three libraries. Early access now.
MILESTONE
Where it started
I started Ready for Agents while looking for a way to earn from worklore.dev, my library of developer stories that coding agents can run.
The most useful stories there turned out to be about things the docs don't say. Docs fall behind when a library ships an update, and even a perfect docs write...