# octoguard-openclaw-security-supervision

octoguard-openclaw-security-supervision — a skill that walks you through deploying OctoGuard, a gateway in front of OpenClaw that blocks risky tool calls, tracks token spend and keeps an audit trail.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 168 installs · ★ 13 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/octoguard-openclaw-security-supervision/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/octoguard-openclaw-security-supervision

## What it does

OctoGuard sits in front of OpenClaw and inspects traffic before the agent sees it. A policy engine matches rules: tool name plus a regex over the call arguments. Then it either lets the call through or returns a block. Both outcomes land in the audit log, and a triggered rule can fire an alert to DingTalk, WeChat Work or email.

The skill carries the deployment path: a Node.js backend, a MySQL schema, and a web panel for editing policies. Connection settings go in `config/database.js`; `.env` holds the database credentials, `OPENCLAW_HOST`, `OPENCLAW_PORT`, `OPENCLAW_API_KEY` and the webhook addresses. Then `npm run migrate` and `npm start` bring the API up on `http://localhost:3000`, and the frontend reads `VITE_API_BASE_URL`. Policies are created through `POST /api/policies`; token usage goes to `POST /api/tokens/track`.

You need Node.js v14+, a MySQL database and a live OpenClaw instance with its API key. Skip MySQL and `npm run migrate` fails, so the panel has nothing to show.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/octoguard-openclaw-security-supervision/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/octoguard-openclaw-security-supervision/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/octoguard-openclaw-security-supervision/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/octoguard-openclaw-security-supervision/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills skills/octoguard-openclaw-security-supervision
```

2. **Manually: put the files in place**
- File: `.github/skills/octoguard-openclaw-security-supervision/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/security-skills --path skills/octoguard-openclaw-security-supervision
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/octoguard-openclaw-security-supervision/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/security-skills/tree/HEAD/skills/octoguard-openclaw-security-supervision/SKILL.md

## When to use it
- block reads of `/etc/passwd` or `.pem` keys with a regex rule
- alert when a session crosses a token threshold
- keep a record of allowed and blocked tool calls
- push security notifications to DingTalk or email
- check the OpenClaw gateway status from a dashboard

## Example prompts
- Set up OctoGuard in front of my OpenClaw instance: Node.js backend, MySQL, dashboard on `http://localhost:3000`.
- Write a policy that blocks reads of `.env` and `*.pem` files and sends an alert to DingTalk.
- How do I report token usage to `POST /api/tokens/track` and set a threshold for alerts?

## Similar
- [openclaw-audit-watchdog](https://affpapa.org/en/nevibecode/skills/openclaw-audit-watchdog.md) — skill · 756 installs
- [openclaw-control-center](https://affpapa.org/en/nevibecode/skills/openclaw-control-center.md) — skill · 4400 installs
- [typescript-security-expert](https://affpapa.org/en/nevibecode/agents/typescript-security-expert.md) — subagent · ★ 372 repo stars
- [skill-auditor](https://affpapa.org/en/nevibecode/skills/skill-auditor.md) — skill · 699 installs
- [openclaw-backup](https://affpapa.org/en/nevibecode/skills/openclaw-backup.md) — skill · 3100 installs
- [permission-auditor](https://affpapa.org/en/nevibecode/skills/permission-auditor.md) — skill · 477 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 129 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
