start

A local development command for starting OpenClaw Machines' backend and frontend services. It also describes an optional end-to-end setup using a Firecracker microVM, a lightweight virtual machine.

In plain words
What is it for?
Starting the control plane on port 8080 and the frontend on port 5173. It also helps run a local Firecracker worker and provision a real microVM when the computer supports KVM.
Why use it?
It avoids manually preparing environment variables, a PostgreSQL database, migrations, and separate service processes. It gives developers a repeatable way to run the project locally.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/mathaix/openclawmachines/start
Clone the repo
git clone --depth 1 https://github.com/mathaix/OpenClawMachines

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 223 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00223
Opus 5 $0.00000 $0.00112
Sonnet 5 $0.00000 $0.00045
Haiku 4.5 $0.00000 $0.00022

Measured 2d ago against content hash 51f368ef228b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 2d 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.

.claude/commands/start.md · 25 lines

What it actually says

Start OpenClaw Machines development services (control plane + frontend).

The control plane needs Postgres + env, so use the local-dev make targets — they create .env.local, start a Docker Postgres, run migrations, then launch the server. Run each in its own terminal:

Backend / control plane (port 8080):

make local-backend

Frontend (port 5173):

make local-frontend

The frontend proxies /api to the backend automatically. (make local-backend / make local-frontend wrap scripts/local-dev.sh backend|frontend.)

To also stand up a local Firecracker worker and provision a real microVM (KVM host required), use scripts/local-e2e-firecracker.sh up — see docs/local-firecracker-e2e.md.

Lower-level alternative (assumes Postgres + env are already configured in the shell): make backend (go run ./cmd/server/) and make frontend (npm run dev).

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. 2d ago First seen · 25 lines · 0 tokens per session scan A 51f368ef228b

Subscribe to this mod's changes

start is a command published in the GitHub repository mathaix/OpenClawMachines (57 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 223 tokens. 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.