xdg-claude: Instructions file for Claude Code

CLAUDE.md

xdg-claude CLAUDE.md is an instructions file for Claude Code from xdg/xdg-claude. It costs 487 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a marketplace that contains Claude Code add-ons, with one self-contained folder for each add-on. They describe where the marketplace list lives and where the full add-on authoring guide can be found.

In plain words
What is it for?
Use them when creating or revising add-ons, following repository conventions, and keeping each add-on’s version aligned with the marketplace listing.
Why use it?
They keep shared repository rules in one place and direct contributors to the detailed authoring manual when they need it.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions Claude Code.

This is xdg/xdg-claude's own configuration. It tells Claude Code how to work on xdg-claude 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 xdg-claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xdg/xdg-claude. 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/xdg/xdg-claude/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/xdg/xdg-claude

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 xdg-claude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xdg/xdg-claude/claude-md/github.svg)](https://agentmods.dev/instructions/xdg/xdg-claude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xdg/xdg-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/xdg/xdg-claude/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.

agentmods 80×15 button for xdg-claude CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xdg/xdg-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/xdg/xdg-claude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 487 This file is loaded in full into every session.
When invoked 487 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 $0.00487 $0.00487
Opus 5.5 $0.00195 $0.00195
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 2mo ago against content hash 92f9846fd866, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xdg-claude 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 2mo 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

xdg-claude — plugin marketplace repository

This repository is a Claude Code plugin marketplace. Each top-level directory (e.g. coding-best-practices/, git-commit-agent/, plugin-authoring/) is a self-contained plugin. The marketplace manifest lives at .claude-plugin/marketplace.json.

Authoring or revising a plugin

The full authoring manual — component types, the three skill patterns, SKILL.md / agent / hook / manifest reference, and worked examples — lives in the authoring-plugins skill, not here. It loads on demand instead of consuming context every session.

  • If the plugin-authoring plugin is installed, invoke the authoring-plugins skill (or just start the task; its description triggers it).
  • If it is not installed, read the skill directly: plugin-authoring/skills/authoring-plugins/SKILL.md and its reference/ files.

Repository conventions (apply to every change here)

These rules govern work in this repo regardless of which plugin you touch:

  1. Version bumps are paired. When you change a plugin, bump its semver in BOTH <plugin>/.claude-plugin/plugin.json and the matching entry in .claude-plugin/marketplace.json. The two must never disagree.

  2. New plugins get registered in two places. Add an entry to .claude-plugin/marketplace.json AND a row to the appropriate table under "List of Plugins" in README.md (Essential / Rule / Hook / Skill). Pick the category matching the plugin's primary surface.

  3. Each plugin needs its own README.md following the style of the existing ones (what it does, installation, marketplace prerequisite).

  4. One plugin, one responsibility. Skill plugins are each exactly one pattern from the taxonomy in the authoring-plugins skill.

  5. Keep plugin READMEs in sync with changes. When a change adds, removes, or alters a plugin's skills, agents, hooks, or behavior, update that plugin's own README.md in the same pass. Treat the README as part of the change, not a follow-up.

Read the full file on GitHub · 43 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. 2mo ago First seen · 43 lines · 487 tokens per session scan A 92f9846fd866

Subscribe to this mod's changes

xdg-claude CLAUDE.md is an instructions file published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 487 tokens to every session, about $0.0019 per session on Opus 5.5. 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

xdg-claude CLAUDE.md compared with instructions from other repositories

xdg-claude CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
xdg-claude CLAUDE.mdxdg/xdg-claudeInstructions file206d agoApache-2.0A487Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode