What is llm-skill CLAUDE.md?

A CLAUDE.md startup file for the llm-skill project. It tells Claude Code to read AGENT.md first and use it to route tasks to the appropriate skills.

Load the llm-skill project in Claude Code, connect it to an existing project, and choose skills based on the central AGENT.md file.

It gives Claude Code a clear entry point instead of requiring it to read every skill file. It also defines how the project separates task execution, skill maintenance, and routing changes.

How hanyuancheung/llm-skill configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hanyuancheung/llm-skill. 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/hanyuancheung/llm-skill/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hanyuancheung/llm-skill

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/hanyuancheung/llm-skill/claude-md/github.svg)](https://agentmods.dev/instructions/hanyuancheung/llm-skill/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hanyuancheung/llm-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/hanyuancheung/llm-skill/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/hanyuancheung/llm-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/hanyuancheung/llm-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 591 This file is loaded in full into every session.

When invoked 591 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	$0.00591	$0.00591
Opus 5	$0.00296	$0.00296
Sonnet 5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 9d ago against content hash b6b508d27e68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-skill 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 9d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Code entrypoint

This is the Claude Code runtime boot file for the llm-skill project. It is a thin shell. All routing, contract, and lifecycle rules live in AGENT.md. Do not add domain knowledge here.

What Claude Code should do on load

Treat AGENT.md as the single source of truth. Read it first; do not read the whole skills/ tree.
Route via AGENT.md §2 Skill Registry. Pick ≤ 3 candidate skills by triggers, then lazy-load.
Respect the Execute → Distill → Guide loop (AGENT.md §1). Claude Code does NOT edit skills while executing; writes go through distill, routing edits go through guide.
Language: default SKILL.md is English. If the user writes in Chinese, prefer SKILL_zh.md when it exists.
Proactive distill: at task end, if reusable signals were observed, surface a short proposal to invoke distill.

Install (Claude Code)

Claude Code auto-loads CLAUDE.md from the workspace root.

# Option A: use this repo as the project root
git clone <this-repo-url> .

# Option B: mount into an existing project
git clone <this-repo-url> .claude-skills
ln -s .claude-skills/AGENT.md  ./AGENT.md
ln -s .claude-skills/CLAUDE.md ./CLAUDE.md
ln -s .claude-skills/skills    ./skills

Validate:

bash install.sh
python3 scripts/validate.py

Minimal contract

Read: AGENT.md, chosen skills/<name>/SKILL.md (lazy).
Write: skills only via distill; AGENT.md only via guide.
Never: dump domain knowledge into this file.

Tips for Claude Code specifically

Prefer parallel tool calls when loading multiple skills chosen by the routing step.
When reporting "done", include: (a) deliverable, (b) whether a distill proposal is attached.
If a skill's How conflicts with user intent, user wins; the conflict must be logged as a distill candidate.

Pointers

Schema and routing → AGENT.md
Meta-skills → skills/execute/, skills/distill/, skills/guide/
New skill scaffold → skills/_template/
Changelog → CHANGELOG.md

Read the full file on GitHub · 55 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.

9d ago First seen · 55 lines · 591 tokens per session scan A b6b508d27e68

Subscribe to this mod's changes

llm-skill CLAUDE.md is an instructions file published in the GitHub repository hanyuancheung/llm-skill (22 stars, last pushed 4mo ago), licensed MIT. It adds 591 tokens to every session, about $0.0030 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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 · 5,153 tokens

vscode buildNext.instructions.md

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-skill: Instructions file for Claude Code