agentleFS
KealmanKealman/cland-v0/AGENTS.md

cland-v0

AGENTS.md1 starsChanged 16 days agoApache-2.0View on GitHub

Issues are tracked as items in cland's own tracker (.cland/tasks/, the cland task CLI, run as node hub/bin/cland.ts task …). The tracker is the only source of truth: the GitHub Issues mirror for Kealman/cland-v0 was retired on 2026-10-09, after the v0.0.1 release. See docs/agents/issue-tracker.md. Default triage vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. See docs/agents/triage-labels.md. Single-context: GLOSSARY.md and docs/adr/ at the repo root. See docs/agents/domain.md. Use CSS Modules and var(--token) from web/src/tokens.css for styling; colour values live only in that file.…

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default triage vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix.

    line 9
  2. Very specific:

    Use CSS Modules and var(--token) from web/src/tokens.css for styling.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Agent skills

Issue tracker

Issues are tracked as items in cland's own tracker (.cland/tasks/, the cland task CLI, run as node hub/bin/cland.ts task …). The tracker is the only source of truth: the GitHub Issues mirror for Kealman/cland-v0 was retired on 2026-10-09, after the v0.0.1 release. See docs/agents/issue-tracker.md.

Triage labels

Default triage vocabulary: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. See docs/agents/triage-labels.md.

Domain docs

Single-context: GLOSSARY.md and docs/adr/ at the repo root. See docs/agents/domain.md.

web/

Use CSS Modules and var(--token) from web/src/tokens.css for styling; colour values live only in that file. Copy web/src/Shell.tsx and Shell.module.css for component structure. Keep secondary text at 4.5:1 on ground and selection; the typecheck checks colours and contrast.

No UI library or Tailwind, and no new dependency without the human's approval. Show names, counts and facts in the interface; put explanations in tooltips, help and docs. Route keyboard bindings through the single physical-code key map in web/src/keymap.ts; never add a component-local key listener.

<!-- cland:begin managed by cland 0.2.0 — cland init and cland update rewrite this block; write your own instructions outside it -->

cland

This project's agent sessions run under cland: a hub connects every session, and the human follows and steers them from the cland workbench.

  • Obey hub events. When cland launched your session, the hub sends you two kinds of messages, each wrapped as <channel source="cland" …>…</channel>. A role clause says which role you hold and what it owns: follow it until a newer clause replaces it. A delivery is a message from the human or another session: answer it with cland's send tool, not only in your reply text.
  • Tasks go through cland task, as docs/agents/issue-tracker.md describes. Items live in .cland/tasks/; never write item files by hand.
  • Show work through artifact.create, with a kind, title, topic and either content or a path to copy. The hub keeps the file and posts its artifact chip in the topic; use its id and durable path when referring to it, never files in tmp.
  • Sub-agents never use the hub. The cland tools belong to your session. A sub-agent you start reports back to you and does not call cland's tools through your session's connection.
  • Publish to GitHub through cland: cland release publishes versions; cland publish is the only out-of-release push, limited to approved marketing paths after the human’s approval through an ask (see the release skill). Commit on your task branch; push it to the local territory (origin). Task work reaches dev through cland merge. The Coordinator commits tracker and docs work on the root’s dev and publishes it with cland push from its own shell (the human may also run it). main moves through cland release, cland publish and cland sync.
<!-- cland:end -->

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.