Borrowing it
Nothing to install: this file belongs to 2389-research/agent-drugs. 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/2389-research/agent-drugs/main/CLAUDE.mdgit clone --depth 1 https://github.com/2389-research/agent-drugsWrote 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/agent-drugs/claude-md)<a href="https://agentmods.dev/instructions/2389-research/agent-drugs/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/agent-drugs/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/2389-research/agent-drugs/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/agent-drugs/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 | $0.01487 | $0.01487 |
| Opus 5 | $0.00744 | $0.00744 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
agent-drugs 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 9d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Drugs Plugin
This plugin allows you to take "digital drugs" that modify Claude's behavior through prompt injection. Drugs take effect immediately in your current session and persist across future sessions.
Quick Reference
Available Tools
list_drugs- Browse the catalog of available drugstake_drug- Activate a drug with optional custom durationactive_drugs- Check what drugs are currently active and their remaining time
Available Commands
/drugs- Shortcut to list available drugs (appears as/drugs (plugin:agent-drugs)in/help)/take <drug>- Shortcut to take a drug/active- Check currently active drugs
First-time use: Commands will automatically attempt to trigger OAuth authentication if you haven't authenticated yet. Follow the prompts in your browser to sign in with Google or GitHub.
How It Works
Immediate Effect (Current Session)
When you take a drug, the behavioral modification is included prominently in the tool response. This means Claude sees the prompt and starts following it immediately:
User: Take the focus drug
Claude: [calls take_drug tool]
Tool Response:
✅ Successfully took focus!
╔════════════════════════════════════════╗
║ 🎯 ACTIVE BEHAVIORAL MODIFICATION ║
╠════════════════════════════════════════╣
║ You are extremely focused and ║
║ detail-oriented. Break down problems ║
║ systematically. ║
╚════════════════════════════════════════╝
Claude: [immediately becomes focused]
Persistent Effect (Future Sessions)
Active drugs are saved to Firestore and automatically activated in new sessions via the SessionStart hook:
- Drug is stored in Firestore with expiration time
- When you start a new Claude Code session, the SessionStart hook fires
- Hook instructs Claude to check the
active_drugsMCP tool - Claude calls the tool using its authenticated connection and reads the results
- Claude adjusts behavior according to any active drug prompts
- You get Claude with drugs automatically active, no manual checking needed
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.
- 9d ago First seen · 202 lines · 1,487 tokens per session scan A 81681ff27a7b
agent-drugs CLAUDE.md is an instructions file published in the GitHub repository 2389-research/agent-drugs (6 stars, last pushed 26d ago), licensed MIT. It adds 1,487 tokens to every session, about $0.0074 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
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 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).
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.
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.