Borrowing it
Nothing to install: this file belongs to l3a0/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/l3a0/claude-plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/l3a0/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/l3a0/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/l3a0/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/l3a0/claude-plugins/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.
<a href="https://agentmods.dev/instructions/l3a0/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/l3a0/claude-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04960 | $0.04960 |
| Opus 5.5 | $0.01984 | $0.01984 |
| Sonnet 5.5 | $0.00992 | $0.00992 |
| Haiku 4.5 | $0.00496 | $0.00496 |
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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — claude-plugins
claude-plugins is the owner's personal collection of Claude Code skills, published as one plugin under the l3a0 namespace. The repository is both the plugin and its own marketplace. .claude-plugin/plugin.json describes the plugin, and .claude-plugin/marketplace.json lists it. Each skill's SKILL.md lives under skills/<name>/ and carries the method. Two skills ship today.
kindle-highlights, whoseskills/kindle-highlights/scripts/folder carries the helpers it runs.ask-board, whose agents, hook and seat generator sit at the repository root rather than underskills/ask-board/. Its eleven board agents live inagents/, and a sitting launches only some of them. The hook inhooks/limits those agents to a short list of tools and folders, andscripts/gen_seats.pygenerates the ten seat files.
Every gotcha in kindle-highlights was earned on a real run. skills/kindle-highlights/SKILL.md names the five books it has run against and what each run recovered. PR #2, PR #3 and PR #13 each folded one run's lessons into the skill. PR #5 and PR #18 are the skill changes that did not come from a run. Both hardened the capture receiver. PR #5 followed a CodeQL alert, and PR #18 followed a review of PR #17 that found any web page open in the browser could write into the receiver's pages folder. The skill also runs against the user's own logged-in browser session and local app data, and is designed to keep that data on the user's machine. SECURITY.md states that scope. The capture receiver binds 127.0.0.1. It refuses a write outside its pages folder, the guard PR #5 added, and any request whose Origin is not https://read.amazon.com, the guard PR #18 added.
Status: the repo has no test suite, no design doc, no build plan and no milestones. README.md and each SKILL.md carry the reasoning. Two kinds of check run on every pull request:
- The Plugin Security Scan workflow in
.github/workflows/plugin-security-scan.yml, which also runs on every push. - CodeQL, through GitHub's default code-scanning setup.
Dependabot bumps the workflow's pinned actions weekly, per .github/dependabot.yml.
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.
- 11d ago Changed · +3 lines · +111 tokens per session 4afcc0614c2a
- 16d ago First seen · 138 lines · 4,849 tokens per session scan A 1fe60c9b78b0
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository l3a0/claude-plugins (19 stars, last pushed today), licensed MIT. It adds 4,960 tokens to every session, about $0.0198 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 2026-10-03.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.