Skill-Lab: Instructions file for Claude Code

CLAUDE.md

Skill-Lab CLAUDE.md is an instructions file for Claude Code from 8ddieHu0314/Skill-Lab. It costs 3,027 tokens per session, scanned A, original, Apache-2.0.

A set of project instructions for Skill-Lab, a Python command-line tool that evaluates agent skills such as SKILL.md files. It defines the project's naming, documentation, attribution, and command conventions.

In plain words
What is it for?
Use it when developing, documenting, evaluating, or releasing Skill-Lab changes, especially around skill scoring, security checks, and project documentation.
Why use it?
It prevents contributors from using inconsistent names, missing required documentation, or adding prohibited attribution to project output. It also explains the tool's evaluation areas and expected repository practices.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is 8ddieHu0314/Skill-Lab's own configuration. It tells Claude Code how to work on Skill-Lab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Skill-Lab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 8ddieHu0314/Skill-Lab. 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/8ddieHu0314/Skill-Lab/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/8ddieHu0314/Skill-Lab

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.

agentmods badge for Skill-Lab CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/8ddiehu0314/skill-lab/claude-md.svg)](https://agentmods.dev/instructions/8ddiehu0314/skill-lab/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/8ddiehu0314/skill-lab/claude-md"><img src="https://agentmods.dev/badge/instructions/8ddiehu0314/skill-lab/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,027 This file is loaded in full into every session.
When invoked 3,027 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03027 $0.03027
Opus 5 $0.01514 $0.01514
Sonnet 5 $0.00605 $0.00605
Haiku 4.5 $0.00303 $0.00303

Measured 8d ago against content hash 6beddc0df319, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Skill-Lab 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 8d 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 · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 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.

Python CLI tool (v0.7.0) that evaluates agent skills (SKILL.md files) via static analysis, LLM-as-judge quality review, trigger testing, and LLM-based test generation. Produces a 0-100 static score across 37 checks (structure:13, naming:3, description:3, content:13, security:5) / 5 dimensions, plus a 0-100 LLM judge score across 9 criteria / 2 axes (Activation Quality + Instruction Quality).

Attribution

NEVER include Co-Authored-By lines, "Generated with Claude Code", or any AI co-authorship attribution in commit messages, PR descriptions, PR reviews, or any other output.

Naming

Name Usage
Skill-Lab GitHub repo / project name
skill-lab PyPI package (pip install skill-lab)
sklab CLI command (sklab evaluate ./my-skill)

Docs

Document Contents
docs/ARCHITECTURE.md Tech stack, data flow, CLI commands, check systems, design patterns
docs/IMPLEMENTATION_PLAN.md Vision, roadmap, design decisions
docs/SECURITY.md 5-layer security scan details
docs/PRIVACY.md Telemetry & privacy policy
docs/DEV_STATS.md Telemetry flow, SQLite schema, event types, CI detection
docs/versions/ Per-version specs (v0.1.0–v1.0.0)

After code changes: update ARCHITECTURE.md (modules/CLI) and the relevant docs/versions/vX.X.X.md.

ALWAYS READ THE DOCS BEFORE ACTIONING

Commands

pip install -e ".[dev]"       # install with dev deps
sklab                         # auto-scan repo + getting started guide (no subcommand)
sklab evaluate ./my-skill     # static analysis + LLM quality review (--optimize to chain into optimizer)
sklab evaluate --all          # evaluate every skill in CWD (also: --repo for git root)
sklab check                   # quick pass/fail (exit 0/1, good for CI)
sklab info ./my-skill         # metadata + token estimates
sklab prompt ./skill-a        # export skill as XML prompt
sklab trigger                 # run trigger tests (requires Claude CLI, --provider local|docker)
sklab generate                # generate trigger tests via LLM (multi-provider)
sklab optimize ./my-skill     # LLM-powered SKILL.md optimization (multi-provider)
sklab stats                   # usage statistics
sklab setup                   # configure hooks for Claude Code/Cursor
sklab scan ./my-skill         # security scan (BLOCK/SUS/ALLOW)
sklab list-checks             # browse all checks (--spec-only, --suggestions-only)
pytest tests/ -v                            # run all tests
pytest tests/test_checks.py -v              # run single test file
pytest tests/test_checks.py -k "keyword" -v # filter by keyword
mypy src/                     # type check
ruff check src/ && ruff format src/
/verify                       # runs all of the above (pytest, mypy, ruff check, ruff format)

Read the full file on GitHub · 157 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. 8d ago First seen · 157 lines · 3,027 tokens per session scan A 6beddc0df319

Subscribe to this mod's changes

Skill-Lab CLAUDE.md is an instructions file published in the GitHub repository 8ddieHu0314/Skill-Lab (56 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 3,027 tokens to every session, about $0.0151 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.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens