agentmods.dev

ClaudeMarketplace: Instructions file for Claude Code

CLAUDE.md

ClaudeMarketplace CLAUDE.md is an instructions file for Claude Code from RealDougEubanks/ClaudeMarketplace. It costs 4,376 tokens per session, scanned B, original, MIT.

A set of instructions for maintaining a repository of reusable Claude Code skills. Claude Code is a coding assistant, and a skill is a reusable set of instructions for it.

In plain words
What is it for?
It guides skill structure, naming, metadata, documentation, validation, and contribution checks in the marketplace repository.
Why use it?
It gives contributors consistent project rules and a required checklist, reducing invalid files and missed validation before commits.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions Claude Code.

This is RealDougEubanks/ClaudeMarketplace's own configuration. It tells Claude Code how to work on ClaudeMarketplace 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 ClaudeMarketplace configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 1repo 2mo ago B scan 4,376 tokens original MIT
View source ↗ RealDougEubanks/ClaudeMarketplace
Reuse

Borrowing it

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

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 ClaudeMarketplace CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/realdougeubanks/claudemarketplace/claude-md"><img src="https://agentmods.dev/badge/instructions/realdougeubanks/claudemarketplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,376 This file is loaded in full into every session.
When invoked 4,376 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.04376 $0.04376
Opus 5 $0.02188 $0.02188
Sonnet 5 $0.00875 $0.00875
Haiku 4.5 $0.00438 $0.00438

Measured 8d ago against content hash 7d60cdaeab39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

ClaudeMarketplace CLAUDE.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Skills are distributed via the Claude Code marketplace — there is no manual install script. Direct users to add this repo as a marketplace in `~/.claude/settings.json`.
CLAUDE.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Skills Marketplace — Project Context

This is the Claude Code Skills Marketplace repository. It is a collection of reusable prompt skills for Claude Code — each skill is a plugin directory under skills/ containing a SKILL.md instruction file at its root, metadata.json (machine-readable metadata), and README.md (human docs).

When working in this repo, your job is to help build, validate, and publish skills. Always follow the contribution conventions below.

Contribution Conventions

  • Skill directory names must be kebab-case (e.g. git-workflow, golden-rules).
  • Each skill directory has this structure: SKILL.md at the plugin root (with YAML frontmatter), metadata.json, README.md, .claude-plugin/plugin.json. There is NO commands/ directory (legacy layout, removed — see docs/decisions/0001-migrate-to-skill-md-layout.md). Multi-skill plugins (agent-based-development) use skills/<sub-skill>/SKILL.md instead of a root SKILL.md.
  • metadata.json must validate against schema/metadata.schema.json.
  • After creating or editing a skill, run ./scripts/validate.sh skills/<skill-name>.
  • After adding a skill directory, update skills/registry.json and run ./scripts/check-registry.sh.
  • Use ./scripts/new-skill.sh <name> to scaffold a new skill. It creates the full directory structure (including .claude-plugin/plugin.json) and registers the skill in registry.json and marketplace.json.
  • Skills are distributed via the Claude Code marketplace — there is no manual install script. Direct users to add this repo as a marketplace in ~/.claude/settings.json.
  • Do not modify skills/example-skill/ — it is the canonical reference for contributors.

Pre-Commit Checklist (MANDATORY — run before every commit)

Always run these checks before committing. CI will fail if any are skipped.

  1. Validate skill structure — ./scripts/validate.sh skills/<name> for each changed skill.
  2. Sync registry versions — skills/registry.json version must match metadata.json version for every skill. Update registry.json whenever you bump a skill version.
  3. Bump versions — Any skill whose SKILL.md, supporting files, metadata.json, or README.md changed must have its version incremented in all four places: metadata.json, skills/registry.json, .claude-plugin/marketplace.json, and skills/<name>/.claude-plugin/plugin.json. Use semver patch bumps for fixes, minor bumps for new features or layout changes.
  4. Run ShellCheck — shellcheck scripts/*.sh tests/*.sh. All scripts must pass with no errors.
  5. Run markdownlint — npx markdownlint-cli2 "skills/**/*.md" "*.md". No bare URLs — wrap emails and URLs in backticks or angle brackets.
  6. Check registration and version sync — ./scripts/check-registry.sh to confirm every skill directory is registered, and ./scripts/sync-versions.sh --check to confirm versions agree across metadata.json, registry.json, marketplace.json, and plugin.json.

Read the full file on GitHub · 212 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 · 212 lines · 4,376 tokens per session scan B 7d60cdaeab39

Subscribe to this mod's changes

ClaudeMarketplace CLAUDE.md is an instructions file published in the GitHub repository RealDougEubanks/ClaudeMarketplace (1 stars, last pushed 2mo ago), licensed MIT. It adds 4,376 tokens to every session, about $0.0219 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Codeclaudeclaude-aiclaude-code-pluginclaude-code-skillclaude-code-skills
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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens