agentleFS
jahalajahala/umbel/.claude/CLAUDE.md

umbel

CLAUDE.md7 starsChanged 5 months agoMITView on GitHub

tend tracks planned work across sessions. If it's not updated, the next session starts blind. When you need it: /tend discover (map an existing codebase into features) · /tend change (requirement changes) · /tend narrate (write the article body) For reads of a single feature, use the polyglot: bash docs/tend/<id>.tend.html data | jq.

The file

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

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    When you need it: /tend discover (map an existing codebase into features) · /tend change (requirement changes) · /tend narrate (write the …

    line 12
  2. Very specific:

    No plan? → /tend plan creates implementation steps

    line 17
  3. Very specific:

    All done? → /tend audit verifies code matches checks

    line 19
  4. Distinctive:

    When asked to implement multi-file changes, check tend first:

    line 22
  5. Very specific:

    No match → /tend brainstorm to create one (minimal draft is fine)

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.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
CLAUDE.md

tend — Feature Map

tend tracks planned work across sessions. If it's not updated, the next session starts blind.

Start here

  1. /tend position — define who you're building for (personas + jobs)
  2. /tend brainstorm — shape your first feature into slots + checks
  3. /tend plan — break it into testable steps
  4. /tend run — build it
  5. /tend audit — verify it with real evidence

When you need it: /tend discover (map an existing codebase into features) · /tend change (requirement changes) · /tend narrate (write the article body)

Daily loop

  1. /tend — see status + what's unblocked
  2. Pick the suggested feature or choose from the list
  3. No plan? → /tend plan creates implementation steps
  4. Implement steps — tend_update_feature with steps[] (by-id merge) as you complete each
  5. All done? → /tend audit verifies code matches checks

Before you build

When asked to implement multi-file changes, check tend first:

  1. ls docs/tend/features/ (or tend_get_unblocked) — does this work map to a feature?
  2. No match → /tend brainstorm to create one (minimal draft is fine)
  3. Match → tend_update_feature with the touched step's status as you complete each

MCP tools

  • tend_get_context — full feature context in one call
  • tend_get_unblocked — what to work on next
  • tend_update_feature — single write surface; step status is one of many fields
  • tend_get_gaps — what needs attention; each gap names the closing skill
  • npx tend-cli ui — generate web dashboard and open in browser

For reads of a single feature, use the polyglot: bash docs/tend/<id>.tend.html data | jq.

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.