Borrowing it
Nothing to install: this file belongs to jtsternberg/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/jtsternberg/claude-plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/jtsternberg/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/jtsternberg/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/jtsternberg/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/jtsternberg/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/jtsternberg/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/jtsternberg/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 | $0.05684 | $0.05684 |
| Opus 5.5 | $0.02274 | $0.02274 |
| Sonnet 5.5 | $0.01137 | $0.01137 |
| Haiku 4.5 | $0.00568 | $0.00568 |
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 13d 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A collection of Claude Code plugins (skills, commands, hooks) for sharing and reuse. Each plugin lives in its own directory under plugins/.
Repository Structure
.claude-plugin/
├── plugin.json # Plugin metadata
└── marketplace.json # Marketplace registry of available plugins
plugins/
└── <plugin-name>/ # Each plugin in its own directory
├── .claude-plugin/
│ └── plugin.json # Plugin metadata (keep at the plugin root)
├── README.md # Plugin-level docs
├── skills/ # Skills live here (optional)
│ └── <skill-name>/ # One directory per skill
│ ├── SKILL.md # The skill definition — belongs at this path
│ └── scripts/ # Scripts the skill runs, bundled with it
├── commands/ # Slash command markdown files (optional)
└── hooks/ # Hook scripts (optional)
A directory under plugins/ without its own .claude-plugin/plugin.json is a
plugin group: each of its immediate subdirectories is a plugin of the normal
shape above (see plugins/pr-workflow/). A group typically also holds a
bundle/ plugin — a manifest with only name + dependencies — so one install
brings in every child. Tooling resolves a plugin root as the nearest directory
containing a plugin manifest; never assume plugins/<name> is a plugin root.
Each skill's SKILL.md belongs at plugins/<plugin-name>/skills/<skill-name>/SKILL.md. That path is what makes the skill discoverable in autocomplete. Claude Code invokes an installed plugin skill as /<plugin-name>:<frontmatter-name>; Codex invokes it as $<plugin-name>:<frontmatter-name>. Use the bare frontmatter name only when referring to the skill in prose. Keep .claude-plugin/plugin.json at the plugin root; everything a skill needs (its SKILL.md and any scripts/) sits together under its own skills/<skill-name>/ directory.
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.
- 13d ago Changed · +6 lines · +126 tokens per session 21e5ac02fdf4
- 20d ago Changed · +51 tokens per session 79949522eb61
- 23d ago Changed · +5 lines · +164 tokens per session ff67292fe188
- 26d ago Changed · +13 lines · +201 tokens per session dc690504a3cd
- 1mo ago Changed · +12 lines · +167 tokens per session b4081c9e4486
- 1mo ago First seen · 408 lines · 4,975 tokens per session scan A 49111fce42d6
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository jtsternberg/claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 5,684 tokens to every session, about $0.0227 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 2026-08-31.
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).
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.