skills CLAUDE.md

skills CLAUDE.md is an instructions file for Claude Code, Codex from edloidas/skills. It costs 12,914 tokens per session, scanned A, original, MIT.

A repository instruction file for a collection of coding-agent skills. It explains how the repository is organized and how agents should load and name skills.

In plain words
What is it for?
Use it when adding or editing skills, checking the repository layout, following its loading conventions, or preparing changes for review.
Why use it?
It gives contributors one shared set of rules and helps prevent duplicated instructions, accidental commits, and inconsistent skill structure.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_SESSION_ID} variable, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is └── <skill-name> -> ../../<group>/skills/<skill-name>.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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 skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edloidas/skills/claude-md.svg)](https://agentmods.dev/instructions/edloidas/skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/edloidas/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/edloidas/skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 12,914 This file is loaded in full into every session.
When invoked 12,914 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 5.1 $0.12914 $0.12914
Opus 5 $0.06457 $0.06457
Sonnet 5 $0.02583 $0.02583
Haiku 4.5 $0.01291 $0.01291

Measured yesterday against content hash 5439e568bf87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 yesterday.

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 · 903 lines

How it starts

The opening of the file, as written. The whole thing — 903 lines — stays where its author put it; the contents beside it link to each section on GitHub.

edloidas/skills

A collection of Claude Code and other agents skills following the Agent Skills specification.

Never commit or push changes unless explicitly asked. Never commit directly to the main branch unless explicitly asked.

No AI footers: Do not add "Drafted with AI assistance", Claude Code session links, <sub> attribution lines, a trailing --- rule, or anything similar to commit messages, issue bodies, or PR bodies — including PRs created from the web. No Co-Authored-By trailer crediting an assistant either, and an existing one in git history is not licence to repeat it. Add attribution only when this file, the user's own instructions, or the user's prompt asks for it.

Canonical Repo Instructions

CLAUDE.md is the canonical repo instructions file. The repo root also contains an AGENTS.md symlink pointing to this file so Codex and other agents read the same instructions.

Edit CLAUDE.md directly. Do not replace the AGENTS.md symlink with a copied file.

Repository Structure

Skills are organized into plugin groups. Each group has a .claude-plugin/plugin.json for auto-discovery and contains related skills:

<group>/
├── .claude-plugin/
│   └── plugin.json               # Plugin metadata
└── skills/
    └── <skill-name>/             # Canonical skill location — a REAL directory
        ├── SKILL.md              # Required — frontmatter + instructions
        ├── scripts/              # Optional — executable code
        ├── references/           # Optional — docs loaded on demand
        └── assets/               # Optional — templates, images, data

<group>/skills/<skill-name>/ is the one canonical location for a skill, and it must be a real directory — never a symlink. Two independent constraints force this:

  1. Claude Code's plugin loader looks inside the plugin's skills/ directory, not the plugin root. A skill outside <group>/skills/ is invisible to the plugin even though SKILL.md, plugin.json, and the marketplace entry all exist.
  2. Agent skill CLIs (notably npx skills) discover skills with readdir(withFileTypes) + entry.isDirectory(), which is false for a symlink. A symlinked skill directory is invisible to them. They also hard-skip directories named node_modules, .git, dist, build, and __pycache__ — which is why the build/ group is only reachable through the <group>/skills/ path that the marketplace manifest points at.

Read the full file on GitHub · 903 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. yesterday Changed · +184 lines · +3,065 tokens per session 5439e568bf87
  2. 5d ago First seen · 719 lines · 9,849 tokens per session scan A 6270115c5060

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository edloidas/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 12,914 tokens to every session, about $0.0646 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.