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.
npx agentmods add instructions/luxvil/ai-coding-rules/claude-mdgit clone --depth 1 https://github.com/Luxvil/ai-coding-rulesWhat 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 | $0.01894 | $0.01894 |
| Opus 5 | $0.00947 | $0.00947 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00189 | $0.00189 |
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 *)", 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.
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
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.
- 2d ago First seen · 272 lines · 1,894 tokens per session scan C eedbf8229aca
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.
Other instructions, from other repositories
agent-skills AGENTS.md
Instructions for rolandbrecht/agent-skills, covering agent instructions, 1. architectural changes & refactoring, 2. debugging & test failures, 3. structural code refactoring and 4. post-task reflection.
agent-skills CLAUDE.md
Instructions for rolandbrecht/agent-skills, covering agent instructions, 1. architectural changes & refactoring, 2. debugging & test failures, 3. structural code refactoring and 4. post-task reflection.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.
AI-System-Design-Consultant CLAUDE.md
Instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.