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.
Started Ready for Agents. While looking for worklore stories about breaking changes, I wondered which way of shipping docs coding agents actually use. 135 runs later: five lines in AGENTS.md beat the docs MCP, the skill and llms.txt. Now offering the same check to library teams: readyforagents.tech #readyforagents
Home
Search
Messages
Notifications
More

Are you sure?