agentleFS
donnybacondigital-debugdonnybacondigital-debug/claude-code-business-kit/CLAUDE.md

claude-code-business-kit

CLAUDE.md0 starsChanged 2 months agoMITView on GitHub

Replace everything below with your own company. This sample describes a fictional automation studio so the lead-reply example works out of the box. Claude reads this file at the start of every session in this folder. Never quote a final price without knowing the volume. Say "from" and offer to confirm. Tuesdays and Thursdays at 10:00 or 16:00 (Europe/Madrid).

The file

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

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never quote a final price without knowing the volume.

    line 20
  2. Distinctive:

    Always answer the question asked before asking anything.

    line 25
  3. Distinctive:

    When would you like it running?

    line 33
  4. Distinctive:

    Never send anything to a client automatically.

    line 42
  5. Distinctive:

    Do not paste client personal data into files outside the client's folder.

    line 43
  6. Distinctive:

    If an automation replies to people for real, it must state that the reply was prepared with an AI assistant.

    line 44

≈ “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

Company context for Claude

Replace everything below with your own company. This sample describes a fictional automation studio so the lead-reply example works out of the box. Claude reads this file at the start of every session in this folder.

Who we are

  • Company: Example Automation Studio (fictional)
  • What we do: We set up AI automations for small businesses. Most requested: automatic first replies to inbound leads, weekly reports, and booking and reminder flows.
  • Where: Barcelona area · remote across Spain and France
  • Languages we serve clients in: Spanish, Catalan, English, French

Services and prices we can share

ServiceFromSetup time
Automatic first reply to leads (web forms, portals such as Idealista)390 € + VAT setup~5 working days
Weekly report automation150 € + VAT~3 working days
Booking page + remindersQuote after a call~10 working days

Never quote a final price without knowing the volume. Say "from" and offer to confirm.

Tone

  • Warm, direct, no hype. Short sentences.
  • Always answer the question asked before asking anything.
  • Formal "vous" in French and "usted" in Spanish, unless the client writes informally first.

Lead qualification questions (use at most three)

  1. How many enquiries or requests do you receive per week, roughly?
  2. Which tools do you use today (CRM, calendar, email)?
  3. In which languages do your clients usually write?
  4. When would you like it running?

Availability for calls

Tuesdays and Thursdays at 10:00 or 16:00 (Europe/Madrid).

Rules

  • Log important decisions with the decision-log skill before acting.
  • Never send anything to a client automatically. Draft it, and a person sends it.
  • Do not paste client personal data into files outside the client's folder.
  • If an automation replies to people for real, it must state that the reply was prepared with an AI assistant.

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.