kibsu
What can your agents not do in this repository yet?
You have written instructions for coding agents, an AGENTS.md, a CLAUDE.md, a skills directory, a .cursorrules file. Kibsu reads them alongside your git history and reports which of those instructions anyone could actually verify were followed, and which ones only work when a human remembers.
Why it exists
It started as a practical problem. People write those instructions carefully, and then nobody checks whether the agents followed them. I wanted to know how many of them were even checkable in the first place — how many could be settled either way by someone who was not in the room. So I counted, and then I wrote a tool that counts.
Run it
python -m kibsu report /path/to/any/repo
What it prints
WHAT YOUR AGENTS CANNOT DO HERE YET /tmp/superpowers -------------------------------------------------------------------------- x Find your docs 89 markdown files, no index. An agent must grep the tree. + Know your conventions consistent frontmatter (description, name) - enforceable. + Prove they followed 15.6% of your procedural instructions are verifiable (above the 9.4% public median). x Resume after a break 1 of 1 artifacts your instructions promise have never existed in any commit. ? Follow your own rules COULD NOT CHECK - no index file to check history against (looked for docs/index.json, .kibsu/index.json, docs/index.json). -------------------------------------------------------------------------- 2 of 5 ready. 1 could NOT be checked - that is not a pass. Nothing was written to this repo - run `git status` to confirm.
What it writes
The read-only commands write nothing. Run one, then run git status. Four commands write on purpose and say so before they do: index writes the index file, install and gate --install vendor tools and wire hooks, both reversible, and check --receipt writes a receipt. Everything else reads only.