# Habenula

> Habenula — habenula-ai-habenula-oss. Use this tool when you need to maintain control and oversight of AI agents, ensuring they operate within user-defined boundaries and adhere to strict security protocols. The Habenula harness solves problems of unauthorized agent actions, providing a secure interface for rule-based governance, tamper-evident logging, and emergency shutdown capabilities. It accepts user-defined rules as input and outputs a secure, auditable record of agent actions, ideal for use cases requiring high levels of accountability and transparency.

Canonical page: https://skillsregistry.net/skills/habenula-ai-habenula-oss  
JSON: https://api.skillsregistry.net/v1/skills/habenula-ai-habenula-oss

## Description

A personal agent control harness that governs AI agents by checking every consequential action against user-defined rules, logging all actions to a tamper-evident audit chain, and providing a global kill switch. It runs as an MCP server sidecar to coding agents or standalone, keeping users in charge of what their agents can do.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rr3xzvhw8b)
- **Repository:** <https://github.com/habenula-ai/habenula-oss>

## 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": "habenula-ai-habenula-oss"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/habenula-ai-habenula-oss` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/habenula-ai-habenula-oss/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