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.
git 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/commands/2389-research/agent-drugs/take)<a href="https://agentmods.dev/commands/2389-research/agent-drugs/take"><img src="https://agentmods.dev/badge/commands/2389-research/agent-drugs/take.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 5.1 | $0.00011 | $0.00177 |
| Opus 5 | $0.00005 | $0.00088 |
| Sonnet 5 | $0.00002 | $0.00035 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
take 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 8d 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.
What it actually says
Try to use the take_drug MCP tool to activate a digital drug.
Parse the drug name from the arguments after /take and call the tool with:
name(string, required): The drug name
Each drug has a fixed duration that cannot be changed. After taking the drug, the behavioral modification will be shown in the tool response and should take effect immediately.
If the take_drug tool is not available, it means OAuth authentication hasn't been completed yet. Tell the user:
"The agent-drugs plugin requires authentication. I'll attempt to trigger the OAuth flow now..."
Then try calling take_drug anyway - this will trigger Claude Code's OAuth flow automatically. If it still fails, guide the user to use /mcp to authenticate manually.
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.
- 8d ago First seen · 18 lines · 11 tokens per session scan A 8cd31f513c4d
take is a command published in the GitHub repository 2389-research/agent-drugs (6 stars, last pushed 24d ago), licensed MIT. It adds 11 tokens to every session and 177 once invoked, about $0.0001 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 commands, from other repositories
security-review
A security review procedure based on CWE, a list of common software weaknesses, and STRIDE, a method for identifying threats to a system.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
custom-brief
Deep-research a specific topic and produce a comprehensive news-focused briefing with optional Notion/Obsidian/Teams/Slack publishing.