agent-skills CLAUDE.md

Repository instructions for building and checking agent skills in the agent-skills project. They describe the folder layout, required information, writing rules, and audit commands.

In plain words
What is it for?
Use them when adding or reviewing skills, checking required metadata, running the project-wide audit, or installing a skill locally for Claude Code.
Why use it?
They give contributors a shared standard for keeping skills consistent, short, portable across AI tools, and free of references to unavailable platform commands.

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/builderced/agent-skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/BuilderCed/agent-skills
Per session 264 This file is loaded in full into every session.
When invoked 264 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.

ModelPer sessionOnce invoked
Fable 5 $0.00264 $0.00264
Opus 5 $0.00132 $0.00132
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 8b38aea6e0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-skills 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 · 36 lines

What it actually says

CLAUDE.md — agent-skills

Cross-platform AI agent skills repo. 31 skills across 15 categories.

Structure

  • Skills in skills/{category}/{skill-name}/SKILL.md
  • References in skills/{category}/{skill-name}/references/
  • Audit script: bash scripts/audit-all.sh

Conventions

  • SKILL.md must have YAML frontmatter (name, description, version, last-updated, platforms, dependencies, update_sources, license)
  • Max 3K tokens per skill (SKILL.md + references/)
  • Natural language instructions only (no platform-specific tools like Read, Write, Bash)
  • Disclaimer required on regulatory/legal/financial skills
  • French for FR-only skills, English for global skills

Commands

# Audit all skills
bash scripts/audit-all.sh

# Install a skill locally
npx skills add . --skill eu-ai-act-compliance -a claude-code

Do NOT

  • Add platform-specific tool references (Read, Write, Edit, Bash) in SKILL.md core
  • Include copyrighted content (AFNOR, proprietary norms)
  • Exceed 3K tokens per skill
  • Skip disclaimers on regulatory skills
  • Reference skills that don't exist in the repo
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 · 36 lines · 264 tokens per session scan A 8b38aea6e0ec

Subscribe to this mod's changes

agent-skills CLAUDE.md is an instructions file published in the GitHub repository BuilderCed/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 264 tokens to every session, about $0.0013 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 2026-08-31.