ai-coding-rules CLAUDE.md

Project instructions stored in a CLAUDE.md file, which gives Claude Code background about a repository and its working rules.

In plain words
What is it for?
It is for guiding work in the ai-coding-rules repository, including Markdown and Cursor rule files, pnpm commands, and instruction-sync scripts.
Why use it?
It helps the coding assistant understand the repository’s purpose, technologies, commands, structure, and instruction files without rediscovering them each session.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/luxvil/ai-coding-rules/claude-md
Clone the repo
git clone --depth 1 https://github.com/Luxvil/ai-coding-rules
Per session 1,894 This file is loaded in full into every session.
When invoked 1,894 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.01894 $0.01894
Opus 5 $0.00947 $0.00947
Sonnet 5 $0.00379 $0.00379
Haiku 4.5 $0.00189 $0.00189

Measured 2d ago against content hash eedbf8229aca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

ai-coding-rules CLAUDE.md scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"Bash(rm -rf *)",
Origin

This is a copy

100% identical to ai-coding-rules CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md – Project Memory

This file is automatically read by Claude Code at session start. It provides project-specific context to make Claude an effective coding partner.


🎯 Repository Purpose

This is the ai-coding-rules repository — a comprehensive framework for controlling AI-assisted coding across Cursor, GitHub Copilot, and Claude Code. It defines high-signal, low-noise rules that enable AI agents to operate as senior-level engineering partners.


🛠️ Tech Stack

Layer Technology
Documentation Markdown, MDC (Cursor rules format)
Package Manager pnpm

📦 Commands

Action Command
Sync instructions ./scripts/sync_instructions.ps1 (Windows) or ./scripts/sync_instructions.sh (Unix)

📁 Project Structure

ai-coding-rules/
├── CLAUDE.md                     # This file - Claude Code context
├── README.md                     # Project overview
├── CHANGELOG.md                  # Version history
│
├── docs/                         # 📚 Organized documentation
│   ├── core/                     # 🎯 Essential rules
│   │   ├── MASTER_RULES.md       # Central rules (Golden Rule, Three-Phase)
│   │   ├── global_rules.md       # Operating principles
│   │   ├── STRICT_MODE.md        # Non-negotiable rules
│   │   └── UNIVERSAL_RULE_FORMAT.md
│   │
│   ├── stacks/                   # 🔵 Technology guides
│   │   ├── stack_frontend.md     # React/Next.js/TypeScript
│   │   ├── stack_backend.md      # Node.js/Express/Nest
│   │   ├── stack_db.md           # SQL/ORM/Migrations
│   │   ├── stack_python.md       # Python
│   │   └── stack_rust.md         # Rust
│   │
│   ├── workflows/                # 🟡 Agent patterns
│   ├── operations/               # ⚪ Security & ops
│   ├── quality/                  # 🟢 Reviews & metrics
│   └── optimization/             # 💰 Token costs
│
├── .cursor/rules/                # Modular Cursor rules (19 .mdc files)
│
├── .claude/
│   ├── rules/                    # Path-specific rules
│   │   ├── security.md
│   │   ├── frontend.md
│   │   ├── backend.md
│   │   ├── testing.md
│   │   └── database.md
│   └── skills/                   # Structured output templates
│       ├── code-review.md
│       ├── security-audit.md
│       ├── refactor-plan.md
│       └── rigor-audit.md
│
├── .github/
│   ├── copilot-instructions.md
│   └── instructions/
│
├── .windsurf/                    # Windsurf/Cascade config
│
├── examples/rule-tests/          # Rule verification tests
│
└── scripts/                      # Automation scripts

Read the full file on GitHub · 272 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.

  1. 2d ago First seen · 272 lines · 1,894 tokens per session scan C eedbf8229aca

Subscribe to this mod's changes

ai-coding-rules CLAUDE.md is an instructions file published in the GitHub repository Luxvil/ai-coding-rules (3 stars, last pushed 3d ago), licensed MIT. It adds 1,894 tokens to every session, about $0.0095 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to ai-coding-rules CLAUDE.md, differing in 0 lines, and is treated as a copy.

Related

Other instructions, from other repositories