A repository setup command for Crabbox, a tool that runs commands through a remote broker. It creates the configuration and optional GitHub Actions and agent-instruction files needed to use Crabbox.

Use it once from a repository’s root to create .crabbox.yaml, an optional GitHub Actions workflow, and an agent skill file. Options support detection, forced regeneration, and custom file paths.

It removes the need to create these setup files by hand and checks whether target files already exist before writing.

init — Command by openclaw

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/openclaw/crabbox/init

Clone the repo

git clone --depth 1 https://github.com/openclaw/crabbox

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 1,678 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01678
Opus 5	$0.00000	$0.00839
Sonnet 5	$0.00000	$0.00336
Haiku 4.5	$0.00000	$0.00168

Measured yesterday against content hash 8defc6f047cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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.

docs/commands/init.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

init

crabbox init onboards the current repository: it writes the minimal config that crabbox run needs, plus an optional GitHub Actions hydration workflow and an agent skill file. Run it once from the repo root.

crabbox init
crabbox init --detect
crabbox init --force
crabbox init --workflow .github/workflows/crabbox-test.yml

Files it writes

init generates three files, all relative to the repository root:

.crabbox.yaml                        repo defaults (profile, class, capacity, sync, env, ssh)
.github/workflows/crabbox.yml        Actions hydration workflow (optional)
.agents/skills/crabbox/SKILL.md      agent-facing skill instructions

Each path is configurable with the --config, --workflow, and --skill flags. Repeat --skill to write identical skills for multiple client discovery paths. By default init preflights every destination and writes nothing when any target already exists. Pass --force to regenerate and overwrite files in place.

`.crabbox.yaml`

The generated config is a starting template that includes:

profile: <repo-name>-check and class: beast;
a capacity block requesting spot with a most-available strategy and on-demand-after-120s fallback;
an actions block wired to the generated workflow (job: hydrate, runnerLabels: [crabbox], runnerVersion: latest, ephemeral: true);
a sync block with sane defaults: delete, gitSeed, and fingerprint enabled, a 15m timeout, warn/fail thresholds on file count and bytes, and an exclude list covering .cache, .turbo, dist, and node_modules;
env.allow with conservative defaults (CI, NODE_OPTIONS);
an ssh block (user: crabbox, port: "2222", fallbackPorts: ["22"]).

Open the file after init and adjust it to match the repo:

pick the right class for the workload;
add repo-specific sync.exclude patterns;
expand env.allow for project-specific tunables;
set sync.baseRef if the project's default branch is not the rsync base.

Read the full file on GitHub · 159 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.

yesterday First seen · 159 lines · 0 tokens per session scan A 8defc6f047cc

Subscribe to this mod's changes

init is a command published in the GitHub repository openclaw/crabbox (1,343 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,678 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.

Productivity Testing Writing and docs agent-skills herdr-plugin remote-test-runner

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

init

Files it writes

`.crabbox.yaml`

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement