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/londeren/claude-plugins/claude-mdgit clone --depth 1 https://github.com/Londeren/claude-pluginsWrote 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.
[](https://agentmods.dev/instructions/londeren/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/londeren/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/londeren/claude-plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01157 | $0.01157 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
claude-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Repository-wide guidance for Claude Code. Each plugin's own editing rules live in a separate file under docs/, imported below; read the one for a plugin before changing anything inside its directory.
@docs/prompt-writer-editing-rules.md @docs/book-to-skill-editing-rules.md
What this is
A plugin marketplace for Claude: .claude-plugin/marketplace.json at the root, one entry per plugin under plugins/<name>/. Markdown only, no build, no tests, no dependencies.
Only what lives inside a plugins/<name>/ directory ships to users. docs/, tmp/, this file and the root README never do.
Plugins in the repository:
plugins/prompt-writer/- a methodology for writing LLM prompts. Editing rules: docs/prompt-writer-editing-rules.md.plugins/book-to-skill/- turns a Markdown knowledge source into a generated Claude skill. Editing rules: docs/book-to-skill-editing-rules.md.
Adding a plugin
plugins/<name>/with.claude-plugin/plugin.json,skills/<skill>/SKILL.md,README.md,LICENSE.- An entry in the
plugins[]array of.claude-plugin/marketplace.json. docs/<name>-editing-rules.mdif the skill needs its own editing rules, imported from this file and listed above.- A row in the plugin table of the root README.
Do not create the directory before the skill has real content. The skills.sh CLI discovers skills by walking the repository for SKILL.md files, not by reading marketplace.json, so a placeholder shows up in the public listing the moment it is pushed.
Editing rules never live inside plugins/<name>/. Everything there ships, and the skills.sh route installs into .agents/skills/<name>/ inside the user's own project, where a stray CLAUDE.md would be loaded as their nested project instructions.
Skill layout inside a plugin
A skill lives in plugins/<plugin>/skills/<skill>/SKILL.md, never at the plugin root. Claude Code documents a fallback where a root SKILL.md is loaded as the plugin's single skill, and locally it works, but the claude.ai loader does not implement that fallback: it mounts /mnt/skills/plugins/<plugin>:<skill>/ and takes the skill name from the folder under skills/. With no skills/ directory the plugin installs, reports itself as installed, and exposes zero skills. claude plugin validate passes either way and will not catch this.
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.
- 5d ago First seen · 72 lines · 1,157 tokens per session scan A e060b8006a67
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository Londeren/claude-plugins (4 stars, last pushed 11d ago), licensed MIT. It adds 1,157 tokens to every session, about $0.0058 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
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.