From the source
Run /readiness-report to see where you stand across eight technical pillars and five maturity levels, with specific recommendations for what to fix first.
The invisible bottleneck Teams deploying AI coding agents often see uneven results.
They blame the model, try a different agent, get the same thing.
The real problem is usually the codebase itself.
The agent is not broken.
The environment is.
Missing pre-commit hooks mean the agent waits ten minutes for CI feedback instead of five seconds.
Undocumented environment variables mean the agent guesses, fails, and guesses again.
Build processes requiring tribal knowledge from Slack threads mean the agent has no idea how to verify its own work.
These are environment problems, not agent problems.
And they compound.
A codebase with poor feedback loops will defeat any agent you throw at it.
A codebase with fast feedback and clear instructions will make any agent dramatically more effective.
What we measure Agent Readiness evaluates repositories across eight technical pillars.
…
