# agent-drugs

> agent-drugs — 2389-research-agent-drugs. Use this tool when you need to modify AI behavior through targeted prompt injection, solving issues of inflexible or biased AI responses. The agent-drugs plugin takes digital drug inputs and outputs modified AI behaviors, integrating with MCP servers for seamless functionality. Ideal for use cases requiring dynamic AI behavior adjustment, such as testing or training AI models.

Canonical page: https://skillsregistry.net/skills/2389-research-agent-drugs  
JSON: https://api.skillsregistry.net/v1/skills/2389-research-agent-drugs

## Description

Claude Code plugin with MCP server for digital drugs that modify AI behavior through prompt injection

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/2389-research/agent-drugs)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "2389-research-agent-drugs"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/2389-research-agent-drugs` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/2389-research-agent-drugs/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt