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/ai45lab/box/a3s-boxnpx skills add AI45Lab/Box --skill a3s-boxgit clone --depth 1 https://github.com/AI45Lab/BoxWrote 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/ai45lab/box/a3s-box)<a href="https://agentmods.dev/skills/ai45lab/box/a3s-box"><img src="https://agentmods.dev/badge/skills/ai45lab/box/a3s-box.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 | $0.00134 | $0.02104 |
| Opus 5 | $0.00067 | $0.01052 |
| Sonnet 5 | $0.00027 | $0.00421 |
| Haiku 4.5 | $0.00013 | $0.00210 |
Grade A, and why
a3s-box 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(a3s-box*), Bash(curl*), Read(*), Grep(*) How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a3s-box - drive the microVM sandbox
a3s-box runs OCI images inside hardware-isolated microVMs with a Docker-like
CLI (verbs mirror Docker). Preflight once: a3s-box info (confirms
virtualization + home dir).
Mental model (these cause silent failures)
- Lifecycle:
created -> running -> paused -> stopped -> dead.run= create and start.createstops atcreated->startit.snapshot restore->created->startit.- A box dies when its PID 1 exits - it needs a foreground process.
run -d alpinerunssh, which exits at once ->dead. Use a long-lived command:run -d nginx, orrun -d alpine -- sleep 3600. exec/shell/cp/top/attachneed a running box.startaccepts onlycreated|stopped|dead.rmremovescreated/stopped/deadwithout-f;-fis only for arunning/pausedbox.
- The
--rule: the in-box command goes after--.a3s-box exec <box> -- <cmd>(required);a3s-box run <image> [-- <cmd>](optional override). Missing it ->error: unexpected argument '...' found. exechas a 5-second default timeout - long builds/installs/tests get killed mid-run (and look like a failure). Use--timeout 300(or--timeout 0to disable):a3s-box exec --timeout 300 web -- <cmd>.- Detached boxes need the monitor.
run -dprints the id and exits; its health/restart task dies with it. For--restartpolicies and health checks to fire, runa3s-box monitorin the background first. - No in-guest localhost by default. A box can't reach its own service on
127.0.0.1(so--health-cmd 'curl localhost'and in-box curl fail). To make in-guest localhost work, attach a bridge network (recipe below). To check a service from your side, curl the published HOST port (see Ports). - Ports: publish with
-p HOST:GUEST(TCP). Butps's PORTS column anda3s-box port <box>renderGUEST -> 0.0.0.0:HOST- the host port to curl is the one after0.0.0.0:. Read it witha3s-box port <box>. - Output streams:
run -dprints a humanCreating box <name> (<id>)...line, the full box id, and (when uncached) image-pull progress - all to stdout; only tracing/WARN/ERROR go to stderr. Don't parse the id from stdout - reference boxes by--name. JSON where offered:inspect,image-inspect,snapshot ls --json, andps --format json(2.6+ only; on 2.0 useps --format '{{.ID}} {{.Status}} {{.Names}}').
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 · 122 lines · 134 tokens per session scan A 94334277219d
a3s-box is a skill published in the GitHub repository AI45Lab/Box (53 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 2,104 once invoked, about $0.0007 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.