agentleFS
matteotittamatteotitta/repo-structure-agency/CLAUDE.md

repo-structure-agency

CLAUDE.md1 starsChanged 29 days agoMITView on GitHub

This is an agency or consultant workspace: your own business in my-agency/, each client in clients/. Read this file first. Every task belongs to one folder. If the user hasn't said which client, ask before you read or write anything. Never mix one client's context into another's work. For your own marketing, use my-agency/ the same way. Copy clients/_template/ to clients/active/<client-name>/, then run /company-context on their website.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Every task belongs to one folder.

    line 7
  2. Distinctive:

    If a context file you need is empty, say so and offer to run the skill that fills it.

    line 12
  3. Very specific:

    Write in the client's voice from their context/brand/.

    line 25
  4. Very specific:

    After meaningful work, add one line to the client's history.md and update their latest.md.

    line 26
  5. Very specific:

    When an engagement ends, move the folder to clients/previous/.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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

How to work in this repo

This is an agency or consultant workspace: your own business in my-agency/, each client in clients/. Read this file first.

Which client?

Every task belongs to one folder. If the user hasn't said which client, ask before you read or write anything. Never mix one client's context into another's work.

Before you write anything

  1. Open clients/active/<client>/latest.md, then the relevant files in that client's context/: at least icp/, positioning/ and messaging/, plus brand/ for anything public.
  2. If a context file you need is empty, say so and offer to run the skill that fills it. Don't invent the missing facts.
  3. Save work to clients/active/<client>/outputs/<lane>/<research|strategy|execution>/ and name files MMYY-topic.md.

For your own marketing, use my-agency/ the same way.

New client

Copy clients/_template/ to clients/active/<client-name>/, then run /company-context on their website.

House rules

  • Source every claim, and mark guesses as guesses. Never invent numbers, quotes or customers.
  • Client material stays in that client's folder. Treat transcripts and CRM exports as confidential (see .claude/rules/pii-redaction.md).
  • Write in the client's voice from their context/brand/.
  • After meaningful work, add one line to the client's history.md and update their latest.md.
  • When an engagement ends, move the folder to clients/previous/. Keep the docs, because you'll reuse what worked.

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.