Skip to main content
skill CX Codex

octoguard-openclaw-security-supervision — Claude Code skill

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.

no license 168 installs ★ 13 updated 2026-10-09

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a claude-code
Open on GitHub

What octoguard-openclaw-security-supervision 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.

What it helps with

  • 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 for the agent

  • 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?

How to install octoguard-openclaw-security-supervision

1Skills CLI (Vercel)

npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a claude-code

2Manually: put the files in place

~/.claude/skills/octoguard-openclaw-security-supervision/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/octoguard-openclaw-security-supervision/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about octoguard-openclaw-security-supervision

How do I install octoguard-openclaw-security-supervision in Claude Code?

Run npx skills add reason-machines/security-skills --skill octoguard-openclaw-security-supervision -a claude-code. The skill file lands at ~/.claude/skills/octoguard-openclaw-security-supervision/SKILL.md.

What does octoguard-openclaw-security-supervision do?

It guides you through deploying OctoGuard, a gateway in front of OpenClaw that checks tool calls against policies, writes an audit log and sends alerts.

What does OctoGuard need to run?

Node.js v14+, a MySQL database and a running OpenClaw instance with OPENCLAW_API_KEY. DingTalk and WeChat Work webhooks are only for notifications.

Similar skills

All skills for Security →

From the same set129

The whole set →
pentesting-checklist-security-assessment pentesting-checklist-security-assessment — a checklist skill for security work: 23 platforms and 1,000+ checks, from web apps and APIs to Kubernetes and LLM. CX Codex +1 180installs pentesting-checklist-platform pentesting-checklist-platform gives the agent a structured checklist with over a thousand security checks across 23 platforms, from web and API to Kubernetes and LLM. CX Codex +1 177installs claude-code-cybersecurity-skill claude-code-cybersecurity-skill — a 15-skill collection for security work, covering reconnaissance, malware analysis, threat hunting, incident response, and defensive operations. CX Codex +1 174installs spoof-suite-security-hardware spoof-suite-security-hardware configures device identity masking, network spoofing, and browser fingerprint randomization through the hardsp00fd daemon. CX Codex +1 172installs pentest-lyan-web-security-testing pentest-lyan-web-security-testing is a Claude Code skill for web penetration testing: it models threats, reads frontend JavaScript and checks whether one role can reach past another. CX Codex +1 166installs jamboree-android-security-sandbox jamboree-android-security-sandbox is a Claude Code skill that sets up Android security testing environments with Magisk, Burp Suite, Objection, and a rooted emulator. CX Codex +1 156installs android-mobile-security-sandbox-jamboree The android-mobile-security-sandbox-jamboree skill guides setup of an Android app security environment using Magisk, Burp Suite, Objection, and Frida. Use it to inspect app traffic and runtime behavior. CX Codex +1 155installs jamboree-android-security-testing jamboree-android-security-testing — a skill that assembles an Android pentest rig: rooted emulator, Magisk, Burp Suite traffic interception and Objection/Frida hooks. CX Codex +1 149installs

Project sponsors

Companies that keep this analytics open