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 skills/madarco/agentbox/agentbox-infonpx skills add madarco/agentbox --skill agentbox-infogit clone --depth 1 https://github.com/madarco/agentboxWrote 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/skills/madarco/agentbox/agentbox-info)<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>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 | $0.00079 | $0.05640 |
| Opus 5 | $0.00039 | $0.02820 |
| Sonnet 5 | $0.00016 | $0.01128 |
| Haiku 4.5 | $0.00008 | $0.00564 |
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 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 credentials — git 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.
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.
- 4d ago First seen · 285 lines · 79 tokens per session scan A b511fb4022f9
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.
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…
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"…
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.
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.
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.
analyzing-docker-container-forensics
Investigate compromised Docker containers by analyzing images, layers, volumes, logs, and runtime artifacts to identify malicious activity and evidence.