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/raisedadead/claude-code-plugins/claude-mdgit clone --depth 1 https://github.com/raisedadead/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 | $0.00882 | $0.00882 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Read ARCHITECTURE.md before changing anything under plugins/. It carries the priorities, the tenets, the enforcement map and the testing standard. This file is only the handful of rails that are cheapest to violate.
Before proposing a change
Check RESEARCH.md §D first. Several obvious-looking improvements here were already made, deliberately, in the other direction. A gap you spot may be a decision you cannot see the reason for.
The standing example: the commit SHA is the version, so both plugin.json files ship without a version key and stay that way. See D1.
Then read §O. Work worth doing here is already listed there, with the reason it has not been done yet — starting from §O beats inventing a task, and re-filing something already tracked is the most common way a session wastes its first hour. Count what is live with grep -cE '^\| O[0-9]+ .*\| *(open|partial)' RESEARCH.md rather than trusting a number written in prose; O-rows flip state as work lands.
Priorities
Honesty > Recoverability > Leverage, in that order. Use it to settle conflicts rather than arguing them case by case.
Describe every gate as the thing it actually is. An opt-in gate, a default-off gate and an advisory nag each get named as such; a verdict parsed from a model is model-judgment, and computation is what a script returns. claim-check exits 1 on a sentence that claims enforcement while naming neither an exit code nor one of those labels.
blocks, enforces and gates are claims about runtime, and a doc cannot prove one. Run the thing and read the exit code before writing the verb. This rule was already on this page when the class recurred three times in one wave; all three shipped, each found by a reviewer and none by a test.
The shape to watch is right behaviour, wrong stated reason — a correct --cached read justified by a false claim about what git diff HEAD does. Nothing the claim predicted ever failed, so no test could catch it, and it read as authoritative through three reviews. When you write down why a thing is done, that sentence needs a probe too. See F25.
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 · 38 lines · 882 tokens per session scan A c1bd4be26185
claude-code-plugins CLAUDE.md is an instructions file published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 7d ago), licensed ISC. It adds 882 tokens to every session, about $0.0044 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
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.
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).
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.