kanban-flow
AGENTS.md2 starsChanged 5 days agoMITView on GitHub
Conventions for AI coding agents working in this repository. Seeded by kf init; edit freely. Detect anything else by reading the repository, never by guessing.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Start a feature with one command: kanban <context> <feature> (bug: kanban <context> <name> --type bug).
- Very specific: line 22
Never use --force or --skip-hooks without explicit user approval.
- Very specific: line 23
Run kf autoconfig for the setup checklist and the review rules to apply as coding conventions.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
Conventions for AI coding agents working in this repository. Seeded by kf init; edit freely.
Commands
| Task | Command |
| Install | npm ci |
| Build | npm run build |
| Typecheck | npm run typecheck |
| Lint | npm run lint |
| Test | npm test |
Detect anything else by reading the repository, never by guessing.
Workflow (kanban-flow)
- Start a feature with one command:
kanban <context> <feature>(bug:kanban <context> <name> --type bug). - Human gates: confirm the requirement (Phase 1), approve the plan (Phase 2; approve starts the item,
--backlogdefers it), and merge the PR after a review PASS. Do not ask "continue?" between other phases. - Work item state lives in
.works/; move items only withkf stage/kf approve/kf archive;kf statuscloses an item whose PR merged. Never move folders by hand. - Never use
--forceor--skip-hookswithout explicit user approval; every bypass is recorded in the work item's metadata. - Run
kf autoconfigfor the setup checklist and the review rules to apply as coding conventions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

