agentleFS
leonkoellerwirth-archleonkoellerwirth-arch/kickoff-ai/CLAUDE.md

kickoff-ai

CLAUDE.md1 starsChanged 3 months agoMITView on GitHub

If the user asks you to set up, check, fix, or migrate a Mac using this repository, you are the OPERATOR — read docs/12-OPERATOR-PLAYBOOK.md first and follow it exactly. It is a complete instruction set: what you may run without asking, what needs a confirmation first, and what you never run at all. Nothing below this section applies to you. If the user asks you to change this repository's own code or documentation, you are a CONTRIBUTOR — the rules…

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Session protocol: start with /session-start.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 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

CLAUDE.md — kickoff-ai

Which role are you in? Decide this first.

If the user asks you to set up, check, fix, or migrate a Mac using this repository, you are the OPERATOR — read docs/12-OPERATOR-PLAYBOOK.md first and follow it exactly. It is a complete instruction set: what you may run without asking, what needs a confirmation first, and what you never run at all. Nothing below this section applies to you.

If the user asks you to change this repository's own code or documentation, you are a CONTRIBUTOR — the rules below apply.


Contributor rules

Read order at session start (highest precedence first): dev/base/CONSTITUTION.md → BIBLE.md (invariants + decision register, wins on any in-repo conflict) → HANDOFF.md (newest entry) → this file.

What this repo is: a reproducible macOS developer environment, distilled from a verified inventory of one real machine. Four cumulative install levels, a verified check suite, a tool registry with a sunset state machine, a migration path, and a local app. The headline numbers live in manifests/counts.json and are generated — never type one by hand.

Zone: Bridge — MIT open source (CONSTITUTION §1). A reference setup, not a framework; never overclaim it. Before writing anything public, read docs/05-SANITIZATION.md. The scan blocks personal data, but only the patterns it has been told.

Session protocol: start with /session-start; do not begin substantive work while a blocking BIBLE decision is open or the gate is red; end with /session-stop. Any decision that exists only in the chat is lost unless it reaches HANDOFF.md or BIBLE.md first.

The gate is law. ./scripts/gate.sh must print GATE: PASS before any change is called done. CI runs the same scripts.

Non-negotiables are CONSTITUTION §7 — read them there, not here. The two that catch people out in this repo: no customer-internal names anywhere (all examples fictive), and everything documented must actually run.

House rules: Conventional Commits, one concern per commit. Default to inline work; subagents are the exception (CONSTITUTION §9). Workflow and review rules for changes: CONTRIBUTING.md.

Skills: /session-start · /session-stop · /project-state

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.