What is claude-cat CLAUDE.md?

A session guide for Claude Cat, a coding project with defined Git branches and pull-request rules. It explains how contributors should work before changes reach released software.

Use it to choose the right branch type, keep work in an isolated branch, open pull requests to the correct target, and follow the repository's working loop.

It prevents direct changes to protected branches and makes the expected path from a topic branch through review to release clear.

How thingineeer/claude-cat configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thingineeer/claude-cat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/thingineeer/claude-cat/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/thingineeer/claude-cat

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/thingineeer/claude-cat/claude-md/github.svg)](https://agentmods.dev/instructions/thingineeer/claude-cat/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thingineeer/claude-cat/claude-md"><img src="https://agentmods.dev/badge/instructions/thingineeer/claude-cat/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/thingineeer/claude-cat/claude-md"><img src="https://agentmods.dev/badge/instructions/thingineeer/claude-cat/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,330 This file is loaded in full into every session.

When invoked 2,330 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02330	$0.02330
Opus 5	$0.01165	$0.01165
Sonnet 5	$0.00466	$0.00466
Haiku 4.5	$0.00233	$0.00233

Measured 8d ago against content hash 1ef0012bbcb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-cat CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — session playbook

This file is automatically loaded into Claude Code sessions started in this repo. It encodes the project's working rules so every session (and every contributor, AI-assisted or not) follows them without having to dig through CONTRIBUTING.md each time.

Branch model — read this first

  feat/*   ──PR──▶  dev   ──release PR──▶  main   ──tagged──▶  GitHub Release
  fix/*              │                      │
  chore/*            │                 (maintainer
  docs/*             │                  only decides
                     │                  when to cut)
        day-to-day integration         released versions

main is released software. Never commit or push to it directly. Only the maintainer opens dev → main PRs when a release is ready.
dev is where daily work integrates. Never commit or push to it directly either — open a PR from a feature branch.
feat/<topic> / fix/<topic> / chore/<topic> / docs/<topic> — short-lived, one-topic branches. PR base is always dev, unless the maintainer says otherwise.

The pre-commit and pre-push hooks reject direct work on main and dev locally. GitHub branch protection enforces the same rule server-side.

Worktree-only policy — hard rule

The primary checkout (~/Desktop/claude-cat) stays on dev and is read-only for humans and AI alike:

✅ git fetch origin
✅ git pull --ff-only origin dev (sync after PRs merge)
✅ git worktree add … / git worktree remove …
❌ editing files in the primary checkout
❌ git commit in the primary checkout
❌ git push of the primary checkout

All editing, committing, and pushing happens in side worktrees:

~/Desktop/claude-cat                          ← primary, dev, read-only
~/Desktop/claude-cat.feat-<topic-a>           ← side worktree for topic A
~/Desktop/claude-cat.fix-<topic-b>            ← side worktree for topic B
~/Desktop/claude-cat.chore-<topic-c>          ← another side worktree

Read the full file on GitHub · 214 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 214 lines · 2,330 tokens per session scan A 1ef0012bbcb4

Subscribe to this mod's changes

claude-cat CLAUDE.md is an instructions file published in the GitHub repository thingineeer/claude-cat (11 stars, last pushed 18d ago), licensed MIT. It adds 2,330 tokens to every session, about $0.0117 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflow

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-cat: Instructions file for Claude Code