claude-auto-patch: Instructions file for Claude Code

CLAUDE.md

claude-auto-patch CLAUDE.md is an instructions file for Claude Code from Cedriccmh/claude-auto-patch. It costs 239 tokens per session, scanned A, original, MIT.

A configurable system that changes Claude Code before it starts by applying binary patches. Binary patches modify compiled program files at the byte level.

In plain words
What is it for?
Use it to define, enable, disable, install, and apply patches, with platform-specific handling for Windows and macOS.
Why use it?
It automates repeatable changes to Claude Code while checking whether each patch is already applied or in an unknown state.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is Cedriccmh/claude-auto-patch's own configuration. It tells Claude Code how to work on claude-auto-patch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-auto-patch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Cedriccmh/claude-auto-patch. 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/Cedriccmh/claude-auto-patch/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Cedriccmh/claude-auto-patch

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.

agentmods badge for claude-auto-patch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cedriccmh/claude-auto-patch/claude-md/github.svg)](https://agentmods.dev/instructions/cedriccmh/claude-auto-patch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cedriccmh/claude-auto-patch/claude-md"><img src="https://agentmods.dev/badge/instructions/cedriccmh/claude-auto-patch/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.

agentmods 80×15 button for claude-auto-patch CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cedriccmh/claude-auto-patch/claude-md"><img src="https://agentmods.dev/badge/instructions/cedriccmh/claude-auto-patch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 239 This file is loaded in full into every session.
When invoked 239 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00239 $0.00239
Opus 5.5 $0.00096 $0.00096
Sonnet 5.5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 2mo ago against content hash 50963e353fcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-auto-patch 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 2mo 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 · 25 lines

What it actually says

claude-auto-patch

Configurable auto-patch system for Claude Code. Applies binary patches before Claude starts via a shell wrapper.

Project Structure

install.py              - Shell wrapper installer/uninstaller
auto_patch.py           - Patch engine (called by shell wrapper)
auto-patch-config.json  - Toggle individual patches on/off
skills/
  create-patch/         - Skill for creating new patch definitions
    SKILL.md            - Skill instructions
    scripts/            - Helper scripts for code analysis
    references/         - Patching best practices guide

Key Concepts

  • Shell wrapper: install.py injects a claude() function into shell profiles that runs patches before launching claude
  • Equal-length replacement: Patches must be exactly the same byte length as original code
  • Three-state detection: Each patch has target_re (unpatched), patched_re (patched), and implicit "unknown"
  • Cache mechanism: Uses file mtime to skip re-scanning unchanged binaries
  • Platform handling: Windows rename-swap for running exe, macOS codesign
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.

  1. 2mo ago First seen · 25 lines · 239 tokens per session scan A 50963e353fcd

Subscribe to this mod's changes

claude-auto-patch CLAUDE.md is an instructions file published in the GitHub repository Cedriccmh/claude-auto-patch (10 stars, last pushed 7mo ago), licensed MIT. It adds 239 tokens to every session, about $0.0010 per session on Opus 5.5. 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.

Related

claude-auto-patch CLAUDE.md compared with instructions from other repositories

claude-auto-patch CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-auto-patch CLAUDE.mdCedriccmh/claude-auto-patchInstructions file107mo agoMITA239Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode