What is ai-project-guard CLAUDE.md?

A local-first command-line tool that creates project guidance files for AI coding agents. These files record architecture, lessons learned, risky modules, workflows, commands, and agent roles.

It helps initialize governance files for existing or older projects, currently focusing on Claude Code and planned support for other agents.

It gives an agent project-specific boundaries and context without uploading the code or directly changing the project's business code.

How zhangguangzhi001-bot/ai-project-guard configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zhangguangzhi001-bot/ai-project-guard. 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/zhangguangzhi001-bot/ai-project-guard/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zhangguangzhi001-bot/ai-project-guard

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/zhangguangzhi001-bot/ai-project-guard/claude-md/github.svg)](https://agentmods.dev/instructions/zhangguangzhi001-bot/ai-project-guard/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zhangguangzhi001-bot/ai-project-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/zhangguangzhi001-bot/ai-project-guard/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/zhangguangzhi001-bot/ai-project-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/zhangguangzhi001-bot/ai-project-guard/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,721 This file is loaded in full into every session.

When invoked 1,721 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	$0.01721	$0.01721
Opus 5.5	$0.00688	$0.00688
Sonnet 5.5	$0.00344	$0.00344
Haiku 4.5	$0.00172	$0.00172

Measured 2mo ago against content hash 39083e8563b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-project-guard 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 · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository status

This repository contains a product requirements document (ai-project-guard-prd.md) and a v0.1 TypeScript/Node CLI implementation for the planned AI Project Guard open source tool. There are no Cursor rules or Copilot instructions.

Product purpose

AI Project Guard is planned as a local-first CLI that initializes AI coding governance files for existing/legacy projects. Its primary output is not business code changes, but project-specific guard rails such as CLAUDE.md, architecture context, lessons learned, dangerous module lists, workflows, commands, and agents.

Core product constraints from the PRD:

Default to local scanning; do not upload code for analysis.
Do not directly modify target project business code.
Do not write real secret values into generated files.
Do not silently overwrite existing governance files.
MVP focuses on Claude Code output before expanding to Cursor, Copilot, Gemini, and generic agents.

Common commands

Development commands from package.json:

npm install
npm run build
npm run dev -- init --profile claude-code --dry-run
npm run typecheck
npm run lint
npm run format
npm test
npm run test:watch

Run one test file:

npm test -- tests/generators/claude-generator.test.ts

Current implemented CLI surface:

ai-project-guard init
ai-project-guard init --profile claude-code
ai-project-guard init --profile claude-code --dry-run
ai-project-guard init --profile claude-code --output ./target-project
ai-project-guard init --profile claude-code --output ./target-project --force
ai-project-guard init --profile claude-code --no-scan

Planned later commands from the PRD: scan, validate, doctor, local, template list, and template eject.

Planned implementation architecture

The PRD proposes a TypeScript-style CLI organized around these major areas:

Read the full file on GitHub · 176 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.

2mo ago First seen · 176 lines · 1,721 tokens per session scan A 39083e8563b6

Subscribe to this mod's changes

ai-project-guard CLAUDE.md is an instructions file published in the GitHub repository zhangguangzhi001-bot/ai-project-guard (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,721 tokens to every session, about $0.0069 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 2026-08-31.

Building agents Memory and context

ai-project-guard CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-project-guard CLAUDE.mdzhangguangzhi001-bot/ai-project-guard	Instructions file	5	3mo ago	MIT	A	1,721	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ai-project-guard: Instructions file for Claude Code