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/2389-research/claude-plugins/claude-mdgit clone --depth 1 https://github.com/2389-research/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/2389-research/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/2389-research/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/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 | $0.02620 | $0.02620 |
| Opus 5 | $0.01310 | $0.01310 |
| Sonnet 5 | $0.00524 | $0.00524 |
| Haiku 4.5 | $0.00262 | $0.00262 |
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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
2389 Research Claude Code Plugin Marketplace
Repository Purpose
This is a marketplace catalog for Claude Code plugins maintained by 2389 Research. It contains the plugin registry, site generator, and generated marketplace website. All plugins live in their own GitHub repos under 2389-research/.
Structure
claude-plugins/
├── .claude-plugin/
│ └── marketplace.json # Plugin registry (all entries)
├── scripts/
│ └── generate-site.js # Fetches READMEs from GitHub, builds site
├── docs/
│ ├── index.html # Generated marketplace site
│ └── style.css # Site styling
├── tests/ # Site generator tests
├── .github/
│ └── workflows/
│ └── generate-site.yml # CI: regenerates site on push + weekly
├── package.json
├── CLAUDE.md # This file
└── README.md
Available Plugins
Development
| Plugin | Repo | Description |
|---|---|---|
| css-development | 2389-research/css-development | CSS development workflows with Tailwind composition, semantic naming, and dark mode by default |
| firebase-development | 2389-research/firebase-development | Firebase project workflows including setup, features, debugging, and validation |
| landing-page-design | 2389-research/landing-page-design | High-converting landing pages with Vibe Discovery and anti-AI-slop principles |
| xtool | 2389-research/xtool | Xcode-free iOS development with xtool via SwiftPM |
| building-multiagent-systems | 2389-research/building-multiagent-systems | Architecture patterns for multi-agent systems |
| speed-run | 2389-research/speed-run | Token-efficient code generation with hosted LLM (Cerebras) |
| binary-re | 2389-research/binary-re | Agentic binary reverse engineering for ELF binaries |
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 · 240 lines · 2,620 tokens per session scan A deee1753512f
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository 2389-research/claude-plugins (93 stars, last pushed 2d ago), licensed MIT. It adds 2,620 tokens to every session, about $0.0131 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 2026-08-30.
Other instructions, from other repositories
qwen-code AGENTS.md
AGENTS.md instructions for QwenLM/qwen-code, covering agents.md, working principles, simplicity first, common commands and building.
qwen-code CLAUDE.md
Claude Code instructions for QwenLM/qwen-code: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Arcgentic CLAUDE.md
Claude Code instructions for Arch1eSUN/Arcgentic, covering arcgentic v0.2.0 — dev session handoff, 1. identity, 2. not-this (boundary), 3. where you are (state as of handoff) and files to be created (v0.2.0 p0 scope, per spec § 18).
agor CLAUDE.md
Claude Code instructions for preset-io/agor, a project described as: Agor - team command center for all things agentic.
agentic-tech-debt CLAUDE.md
Claude Code instructions for bcanfield/agentic-tech-debt, covering project rules, adapter parity — duplicated on purpose, what's duplicated (keep in sync), per-adapter deltas (do not sync away) and demo gifs.
agentic-tech-debt AGENTS.md
AGENTS.md instructions for bcanfield/agentic-tech-debt: The agent instructions for this repo live in CLAUDE.md — one source of truth for every coding agent. Read it and follow it as written; it applies to Codex exactly as it does to Claude Code.