OpenClawMachines: Skill for Claude Code

.agents/skills/ocm-self-hosted/SKILL.md

ocm-self-hosted is a skill for Claude Code, Codex from mathaix/OpenClawMachines. It costs 35 tokens per session (623 once invoked), scanned A, original, Apache-2.0.

A set of instructions for developing and reviewing OpenClaw Machines on your own computers or infrastructure. It covers local development, operator-managed deployments, authentication, domains, Cloudflare, Firebase, and virtual machines.

In plain words
What is it for?
Use it when configuring local or self-hosted environments, enrolling hosts, setting up the control plane, or reviewing changes related to Firecracker virtual machines and deployment infrastructure.
Why use it?
It helps prevent secrets from being exposed and keeps self-hosted deployments separate from assumptions that only apply to a hosted service.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: installed under .agents/ (shared by several agents); built for openclaw.

This is mathaix/OpenClawMachines's own configuration. It tells Claude Code and Codex how to work on OpenClawMachines itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenClawMachines configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mathaix/OpenClawMachines. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mathaix/OpenClawMachines/main/.agents/skills/ocm-self-hosted/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mathaix/OpenClawMachines

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ocm-self-hosted

README.md
[![agentmods](https://agentmods.dev/badge/skills/mathaix/openclawmachines/ocm-self-hosted.svg)](https://agentmods.dev/skills/mathaix/openclawmachines/ocm-self-hosted)
Your own site
<a href="https://agentmods.dev/skills/mathaix/openclawmachines/ocm-self-hosted"><img src="https://agentmods.dev/badge/skills/mathaix/openclawmachines/ocm-self-hosted.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00623
Opus 5 $0.00017 $0.00311
Sonnet 5 $0.00007 $0.00125
Haiku 4.5 $0.00003 $0.00062

Measured 8d ago against content hash abbaadd51773, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ocm-self-hosted 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.

.agents/skills/ocm-self-hosted/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OCM Self-Hosted

Use this skill for local profile, operator profile, host enrollment, self-hosted deployment, Cloudflare Worker/KV, Firebase, Cloudflare Access, domain, cookie, and public-core portability work.

Read First

  • AGENT.md.
  • docs/control-plane-profiles.md.
  • docs/self-hosted-control-plane.md.
  • docs/local-setup.md.
  • docs/local-firecracker-e2e.md for single-box KVM flow.
  • llms/self-hosted-setup.txt for operator-oriented setup.
  • .agents/maintainer-notes/routing.md.
  • .agents/maintainer-notes/runtime.md.

Profile Contract

  • local: trusted localhost development. Dev auth may be enabled. Do not expose publicly.
  • operator: self-hosted production-like deployment on operator-managed infrastructure. It should preserve the hosted architecture: edge protection, control plane, OCM session token, Worker/KV data plane, enrolled KVM workers, and Firecracker VMs.
  • hosted: hosted/operator profile. Do not introduce private Mathaix defaults into public core.

Workflow

  1. Start with discovery. Inspect branch, dirty state, env examples, docs, and config without printing secrets.
  2. Identify operator inputs: domains, auth mode, Cloudflare account/zone/KV, Worker routes, control-plane URL, cookie domain, artifacts, and KVM hosts.
  3. Produce a redacted plan listing resources to create, update, or leave alone.
  4. Ask before changing live Cloudflare, DNS, Tunnel, Worker, KV, Firebase, Cloudflare Access, host enrollment, or running services.
  5. Implement neutral public-core primitives only. Leave private hosted policy, billing, and commercial admin behavior out of this repo.
  6. Validate with the smallest smoke that matches the change: login, /api/auth/me, ocm_token, host online, machine create/start, route resolution, terminal/gateway, optional SSH, stop/delete.

Review Checks

  • Worker origin hosts must be distinct backend origins, not routed hostnames served by the same Worker.
  • Cookie domains must work for operator domains and omit localhost domains.
  • /api/internal/resolve must be protected by service-token or equivalent operator controls in production-like deployments.
  • Worker and backend config examples must not encourage routing loops.
  • No-tunnel local routes still need persisted VM signing keys.
  • Worker hosts are infrastructure and must use enrollment/agent tokens, not Firebase human auth.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 8d ago First seen · 71 lines · 35 tokens per session scan A abbaadd51773

Subscribe to this mod's changes

ocm-self-hosted is a skill published in the GitHub repository mathaix/OpenClawMachines (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 623 once invoked, about $0.0002 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 2026-08-30.