What is llm-code CLAUDE.md?

Instructions for a repository containing more than 40 reusable agent skills for coding tools such as Claude Code, GitHub Copilot, and Cursor. They describe the repository layout and commands for creating, checking, and packaging a skill.

Use them to understand the skill repository, scaffold a new skill, validate its structure, package it for distribution, and follow its folder conventions.

They give contributors a consistent way to add and validate skills in a documentation-focused project with no runtime build or test process. This avoids malformed skill folders and missing required files.

llm-code CLAUDE.md — Instructions file by itechmeat

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/itechmeat/llm-code/claude-md

Clone the repo

git clone --depth 1 https://github.com/itechmeat/llm-code

Per session 1,589 This file is loaded in full into every session.

When invoked 1,589 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01589	$0.01589
Opus 5	$0.00794	$0.00794
Sonnet 5	$0.00318	$0.00318
Haiku 4.5	$0.00159	$0.00159

Measured 2d ago against content hash 1ff6fb60b312, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llm-code 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 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.

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 · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 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.

What This Repo Is

A collection of 40+ Agent Skills for AI coding tools (Claude Code, GitHub Copilot, Cursor). Skills are installed into user projects via npx add-skill itechmeat/llm-code.

Key Commands

# Scaffold a new skill
python skills/skill-master/scripts/init_skill.py <skill-name>

# Validate a skill's structure
python skills/skill-master/scripts/quick_validate_skill.py skills/<skill-name>

# Package a skill for distribution
python skills/skill-master/scripts/package_skill.py skills/<skill-name>

There are no build or test commands — this is a documentation/skill collection with no runtime dependencies.

Repository Structure

skills/                     # Main skills directory
  <skill-name>/
    SKILL.md                # Required: frontmatter + agent instructions (must be human-readable too)
    references/             # Documentation for agents to read
    assets/                 # Templates/static files for agents to copy
    examples/               # Sample outputs showing expected format
    scripts/                # Executable utilities
agents/                     # Claude Code agent mode definitions
.github/
  skills/                   # GitHub Copilot-specific skill copies
  instructions/             # Copilot .instructions.md files
  agents/                   # Copilot agent definitions
  copilot-instructions.md   # Copilot repo-wide rules
.agents/skills/             # Agent-specific local skills (gitignored)
CHANGELOG.md                # Date-based versioning (Keep a Changelog)
SKILLS_VERSIONS.md          # Tracks product versions for each skill

Skill Authoring Rules

SKILL.md Frontmatter

---
name: skill-name # must match folder name; lowercase a-z0-9- only, no --
description: "..." # 80-150 chars; include trigger keywords for agent discovery
version: "1.2.3" # upstream product/library version being documented
release_date: "2026-01-01"
---

Read the full file on GitHub · 159 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.

2d ago First seen · 159 lines · 1,589 tokens per session scan A 1ff6fb60b312

Subscribe to this mod's changes

llm-code CLAUDE.md is an instructions file published in the GitHub repository itechmeat/llm-code (22 stars, last pushed 1mo ago), licensed MIT. It adds 1,589 tokens to every session, about $0.0079 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.

Data and AI

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 · 5,182 tokens

buildNext

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

llm-code CLAUDE.md