agentbox-info

agentbox-info is a skill for Claude Code, Codex from madarco/agentbox. It costs 79 tokens per session (5,640 once invoked), scanned A, original, MIT.

A host-side tool for creating isolated sandboxes, called boxes, where coding agents can run. Boxes can be local containers or supported cloud environments, with a relay handling host-side operations such as pushing commits.

In plain words
What is it for?
Use it to create boxes, run Claude Code, Codex, or OpenCode in parallel or in the background, attach to running boxes, and safely push commits.
Why use it?
It lets agents work separately from the host machine and from one another while preserving a controlled way to share changes.

Skill for Claude CodeCodex

Part of the agentbox plugin — 3 skills, 1 command shipped together

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 skills/madarco/agentbox/agentbox-info
Any agent
npx skills add madarco/agentbox --skill agentbox-info
Clone the repo
git clone --depth 1 https://github.com/madarco/agentbox

Made for: Claude Code, Codex.

Or install agentbox, the plugin that ships this one along with the rest of its 3 skills, 1 command.

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 agentbox-info

README.md
[![agentmods](https://agentmods.dev/badge/skills/madarco/agentbox/agentbox-info.svg)](https://agentmods.dev/skills/madarco/agentbox/agentbox-info)
Your own site
<a href="https://agentmods.dev/skills/madarco/agentbox/agentbox-info"><img src="https://agentmods.dev/badge/skills/madarco/agentbox/agentbox-info.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00079 $0.05640
Opus 5 $0.00039 $0.02820
Sonnet 5 $0.00016 $0.01128
Haiku 4.5 $0.00008 $0.00564

Measured 4d ago against content hash b511fb4022f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentbox-info scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**The id is a safety token — inspect, then approve that exact id.** `approve <id>` answers the specific prompt you listed; if a *different* prompt has since taken its place, the recomputed id won't match and the approve
apps/cli/share/host-skills/agentbox-info/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentBox (host-side)

You are operating on the user's host machine (laptop / dev workstation), not inside a box. Use the agentbox CLI to provision isolated sandboxes for coding agents and to attach to them.

If you find yourself inside a box (/workspace exists and AGENTBOX_RELAY_URL is set in the env), this is the wrong skill — use the in-box /agentbox-setup skill instead.

What AgentBox is, in one paragraph

AgentBox spins up one isolated sandbox per agent run — a local Docker container (default), a Hetzner VPS (--provider hetzner), a Vercel Sandbox (--provider vercel), an E2B microVM (--provider e2b), or a Daytona cloud sandbox (--provider daytona, partial support). Each box has its own /workspace, but the host's .git/ is shared, so commits made inside the box land on the host immediately. The agent inside the box has no host credentialsgit push, opening URLs in the host browser, capturing checkpoints, and all other host-side operations flow through a small host process called the relay that runs alongside the CLI.

The two starting commands

agentbox create

Provision a box and stop. The box exists and is ready, but nothing is launched inside it.

agentbox create                       # docker, auto-named after the workspace
agentbox create -n review             # docker, friendly name
agentbox create --provider hetzner    # cloud VPS (requires `agentbox prepare --provider hetzner` once)
agentbox create --attach              # drop into a shell inside the box after create

Useful flags: -n <name> (friendly box name), --provider docker|daytona|hetzner|vercel|e2b, --attach, -w <path> (workspace to mount; defaults to cwd), --snapshot <ref> (start from a checkpoint).

Non-docker providers require a one-time agentbox prepare --provider <name> to bake the base image / snapshot.

agentbox claude

Provision (same as create) and launch Claude Code inside the box, in a detachable tmux session. This is the main entry point most users want.

Read the full file on GitHub · 285 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. 4d ago First seen · 285 lines · 79 tokens per session scan A b511fb4022f9

Subscribe to this mod's changes

agentbox-info is a skill published in the GitHub repository madarco/agentbox (378 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 5,640 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

new-service

Add a new service to Harbor — scaffold the compose config, environment variables, metadata, documentation, and cross-service integrations. Use this skill whenever the user wants to add a new service to Harbor, integrate a new tool/app/model server, create a compose configuration for a new project, or onboard any…

av/harbor · 139 tokens

harbor

CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…

av/harbor · 114 tokens

exec-local-docker

Execute a TensorRT-LLM workload locally in Docker. Runs a fully-resolved Docker command in background, monitors completion, reads logs, and reports results. Workflow-agnostic — does not need to know if the workload is pytest, eval, benchmark, or a custom script.

NVIDIA/TensorRT-LLM · 62 tokens

e2b-sandbox

Create, manage, and use E2B sandboxes — run commands, manage files, use git, persist state, and configure networking. Use when building agent workflows that need isolated execution environments.

agent-sandbox/agent-sandbox · 45 tokens

verify

Verify a Txtify change end-to-end. Use before committing any nontrivial change, when asked to "verify", "test this", or "make sure nothing breaks", and always after touching the worker/transcription path, dependencies, or the Dockerfile.

lkmeta/txtify · 54 tokens

analyzing-docker-container-forensics

Investigate compromised Docker containers by analyzing images, layers, volumes, logs, and runtime artifacts to identify malicious activity and evidence.

mukul975/Anthropic-Cybersecurity-Skills · 34 tokens