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.
npx agentmods add instructions/mlz11/claude-code-plugins/claude-mdgit clone --depth 1 https://github.com/mlz11/claude-code-pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00479 | $0.00479 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
claude-code-plugins 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.
What it actually says
CLAUDE.md
This is a Claude Code plugin marketplace owned by mlz11.
Structure
.claude-plugin/marketplace.json # Marketplace catalog
plugins/<name>/ # Each plugin is a subdirectory
.claude-plugin/plugin.json # Plugin manifest
skills/<name>/SKILL.md # Skill definitions
README.md # Plugin-level docs
Style
- Never use em dashes (—). Use " - " (spaced hyphen) or parentheses instead.
Conventions
- Marketplace name:
mlz11-cc-marketplace - Commit messages: conventional commits (
feat:,fix:,docs:, etc.) enforced by.githooks/commit-msg - Plugin names: kebab-case
- License: MIT
- Each plugin must have its own
README.md,plugin.json, and at least one skill
Adding a Plugin
- Create
plugins/<plugin-name>/with the structure above - Add an entry to
.claude-plugin/marketplace.jsonin thepluginsarray - Include a
README.mdwith install instructions and usage examples
Versioning
- Source of truth:
plugin.jsonversionfield (semver:x.y.z) - Catalog mirror:
marketplace.jsonincludesversionfor discoverability butplugin.jsonis authoritative - Both must stay in sync - enforced by
.githooks/pre-push - Git tags:
<plugin-name>/v<semver>(e.g.swimlanes/v1.2.0)
Bumping a version
./scripts/bump.sh <plugin-name> <major|minor|patch|x.y.z>
This updates both plugin.json and marketplace.json, commits, and creates a git tag in one step.
Validation
./scripts/validate-versions.sh # all plugins
./scripts/validate-versions.sh swimlanes # one plugin
Runs automatically on git push via the pre-push hook.
Testing Locally
cc --plugin-dir ./plugins/<plugin-name>
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.
- 2d ago First seen · 62 lines · 479 tokens per session scan A ef659237663f
claude-code-plugins CLAUDE.md is an instructions file published in the GitHub repository mlz11/claude-code-plugins (2 stars, last pushed 6mo ago), licensed MIT. It adds 479 tokens to every session, about $0.0024 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.
Other instructions, from other repositories
ai-coding-tools AGENTS.md
AGENTS.md instructions for shopwareLabs/ai-coding-tools, covering shopware ai coding tools marketplace - technical reference, understanding skills, understanding slash commands, understanding developer documentation and marketplace architecture.
skills AGENTS.md
Instructions for artemnovichkov/skills, covering skills marketplace, repo structure, adding a new skill, installation and any agent (via skills.sh).
claude-code-marketplace CLAUDE.md
Claude Code instructions for NikiforovAll/claude-code-marketplace, covering project, commands, architecture, key concepts and linting.
claude-skills CLAUDE.md
Instructions for Sagargupta16/claude-skills, covering claude.md, what this is, architecture, component types and key format details.
awesome-claude-plugins CLAUDE.md
Claude Code instructions for Chat2AnyLLM/awesome-claude-plugins, covering awesome-claude-plugins development guidelines, active technologies, project structure, commands and code style.
claude-plugins CLAUDE.md
Instructions for tomoking2004/claude-plugins: Claude Code プラグインのマーケットプレイス.構成・導入・開発規約は README.md,美の基準は plugins/refine/BEAUTY.md を参照し,全ての成果物に適用する..