Crabbox is a remote execution control plane that lets a local command run on managed cloud capacity, an SSH host, or another delegated sandbox while syncing code, streaming output, and recording evidence. It is for maintainers, contributors, teams, AI agents, and automation that need repeatable remote testing, builds, browser checks, or platform-specific validation. The catalogue add-ons provide commands and instructions for controlling Crabbox runs.
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.
npx agentmods add commands/openclaw/crabbox/marketplacegit clone --depth 1 https://github.com/openclaw/crabboxWrote 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.
[](https://agentmods.dev/commands/openclaw/crabbox/marketplace)<a href="https://agentmods.dev/commands/openclaw/crabbox/marketplace"><img src="https://agentmods.dev/badge/commands/openclaw/crabbox/marketplace.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01260 |
| Opus 5 | $0.00000 | $0.00630 |
| Sonnet 5 | $0.00000 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
marketplace 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
marketplace
crabbox marketplace previews the Crabbox credits gateway: one Crabbox billing
relationship, one credit balance, and smart routing across brokered sandbox
providers.
This is a skeleton command surface. It can show broker status and compute preview quotes, but it does not capture payment, mutate a credit ledger, reserve credits, or enforce credits during lease creation.
crabbox marketplace status
crabbox marketplace status --json
crabbox marketplace quote --provider auto --class beast --ttl 1h
crabbox marketplace quote --providers aws,hetzner --class beast --max-credits 5
crabbox marketplace quote --provider aws --class standard --ttl 30m --json
Subcommands
status show gateway mode, supported providers, enabled features, and open product decisions
quote preview provider candidates, credit price, provider cost, margin, and selected route
marketplace requires a configured coordinator. Direct-provider mode has no
central customer identity, credit balance, or provider routing policy to query.
Quote Flags
--provider <name|auto> single provider or auto smart routing (default auto)
--providers <a,b> explicit provider candidate list
--class <name> machine class or marketplace SKU (default standard)
--type <name> provider-native server type or marketplace SKU
--target <os> target OS (default linux)
--ttl <duration> quote duration, e.g. 30m, 1h, or 3600s
--max-credits <amount> mark routes above this credit ceiling unavailable
--strategy <name> cheapest, balanced, weighted, or provider-default
--json print raw broker response
Gateway Model
The intended product shape is OpenRouter-like for sandbox capacity:
- Customers put a credit card in one place: Crabbox.
- Crabbox exposes credits as the customer-facing unit, currently denominated as USD-equivalent preview credits.
- Crabbox keeps provider credentials and settlement behind the broker, not in each user checkout.
- Users request intent such as
provider=auto,class=beast,target=linux,ttl=1h, and optionally a credit ceiling. - The broker ranks compatible provider candidates by routing policy such as cheapest, balanced margin/cost, weighted same-priority load balancing, or provider-default order.
- Direct-provider mode remains available and is not forced through payment.
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.
- 5d ago First seen · 137 lines · 0 tokens per session scan A 95df2e77df62
marketplace is a command published in the GitHub repository openclaw/crabbox (1,368 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,260 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.
Other commands, from other repositories
dev
Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).
start
Runs a project that has already been compiled with vendure build.
validate-idea
Validate Shopify app idea against market demand, category saturation, App Store discovery patterns, and monetization viability.
intake
You are running the intake for this purchase. The goal is to populate spec.md at the repo root with the per-purchase brief.
price-strategy
You are a senior E-commerce & Retail specialist. The user needs help with price strategy in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.
price-strategy
You are a senior E-commerce & Retail specialist. The user needs help with price strategy in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.