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.
Borrowing it
Nothing to install: this file belongs to openclaw/crabbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openclaw/crabbox/main/AGENTS.mdgit 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/instructions/openclaw/crabbox/agents-md)<a href="https://agentmods.dev/instructions/openclaw/crabbox/agents-md"><img src="https://agentmods.dev/badge/instructions/openclaw/crabbox/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/openclaw/crabbox/agents-md"><img src="https://agentmods.dev/badge/instructions/openclaw/crabbox/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01916 | $0.01916 |
| Opus 5.5 | $0.00766 | $0.00766 |
| Sonnet 5.5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
crabbox AGENTS.md 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 14d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Edit AGENTS.md directly; do not add CLAUDE.md aliases.
Project Structure & Module Organization
Crabbox is a Go CLI with an optional coordinator on Cloudflare Workers or Node.js with PostgreSQL.
| Area | Location |
|---|---|
| CLI entrypoint and command behavior | cmd/crabbox, internal/cli |
| Go provider adapters | internal/providers/<name> |
| Shared coordinator and Node.js runtime | worker/src, worker/node |
| Coordinator tests | worker/test |
| Command and feature documentation | docs/commands, docs/features |
| CI and release configuration | .github/workflows, .goreleaser.yaml |
Use docs/source-map.md for the detailed code map. Generated outputs such as bin/, dist/, worker/dist/, and worker/node_modules/ should not be edited by hand.
Product Positioning
Crabbox is a generic remote software testing and execution tool. New code, docs, tests, and examples should not mention OpenClaw, Peter, or other project/person-specific workflows unless the file is explicitly about legacy compatibility or release history. Prefer neutral examples such as example-org, [email protected], my-app, test:live, and generic repository workflows.
Architecture Boundaries
Keep core provider-neutral. Core may pass generic request/lease context and call provider capabilities for defaults, access, provision, images, release, cleanup, and diagnostics. Provider-specific reconciliation, firewall/security-group semantics, labels, snapshots, hosts, regions, rollout compatibility, and resource naming live behind provider adapters. No provider == aws/gcp/... logic in core unless it is unavoidable routing/config glue and no provider hook fits.
Provider contracts and extension points are documented in docs/features/provider-authoring.md and docs/provider-backends.md; coordinator runtime boundaries are described in docs/architecture.md.
Build, Test, and Development Commands
Run from the repository root. Use the Go toolchain declared in go.mod and the Node version in .node-version.
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.
- 14d ago Changed · +2 lines · +89 tokens per session 81cc7a1544c0
- 1mo ago Changed · -12 tokens per session 3e5b6d872b98
- 1mo ago Changed · +21 lines · +191 tokens per session 695ad53ef323
- 1mo ago Changed · +2 tokens per session 04167a6255b2
- 1mo ago Changed · +42 tokens per session c7adcd500a8f
- 1mo ago Changed · +2 lines · +268 tokens per session 2e3de51029e7
- 2mo ago First seen · 56 lines · 1,336 tokens per session scan A ee9ba19045be
crabbox AGENTS.md is an instructions file published in the GitHub repository openclaw/crabbox (1,508 stars, last pushed yesterday), licensed MIT. It adds 1,916 tokens to every session, about $0.0077 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.