- ▸Listing the files
- ▸Reading the instructions
- ▸Checking the build tools
- ▸Finding the tests
- ▸Reading the folder layout
- ▸Adding up the score
honojs/hono
Needs work
The overall score is the average of these six
Open a category to see every check
Can an agent quickly find the code that matters?
Biggest wins first
No AGENTS.md was found. An agent starting work in this repository has to infer the package manager, the test command, and the layout of 116 directories from the file tree alone.
Create AGENTS.md at the repository root covering:
GoodRepo found 1 routes and 116 directories with no document describing how they relate. Agents spend context searching for the right implementation path before making a one-line change.
Add an Architecture section to AGENTS.md describing:
Not available yet
An AI reads the code to settle the 3 checks a quick scan cannot. Takes about a minute and is free with a GitHub sign-in.
Are agent-facing instructions present and complete?
Can an agent verify its own changes?
Does the codebase repeat the same patterns?
Is setup, build, lint and test behavior obvious?
How much must an agent read to make one change?
No typecheck script exists, so an agent cannot verify a change compiles without running a full build.
Add to package.json:
138 test files exist but nothing documents how to run just one. Agents run the whole suite for every iteration, which is slow and expensive.
Add the single-test command to AGENTS.md, for example:
No template lists the environment variables this project needs, so an agent cannot tell which ones a feature depends on.
Commit a .env.example that lists every variable with a comment describing it.