openclaw-sandboxing

openclaw-sandboxing is a skill for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 54 tokens per session (1,568 once invoked), scanned A, original, MIT.

A guide for running OpenClaw tools inside Docker containers, which are isolated environments for running software. It covers how sessions, workspaces, mounted files, browsers, resources, and network access are isolated.

In plain words
What is it for?
Use it to configure or troubleshoot OpenClaw’s Docker sandbox, choose which sessions are isolated, control workspace access, manage mounted folders, and set up custom sandbox images or network rules.
Why use it?
It reduces the damage a tool could cause to the main computer if something goes wrong. It also helps control which files and network connections the sandbox can use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for openclaw.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/data:/data:ro.

Part of the openclaw plugin — 31 skills, 22 commands, 4 agents, 3 hooks shipped together

Good fit Use it to configure or troubleshoot OpenClaw’s Docker sandbox, choose which sessions are isolated, control workspace access, manage mounted folders, and set up custom sandbox images or network rules.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add TheophilusChinomona/claude-openclaw-plugin
Claude Code
/plugin install openclaw

Made for: Claude Code.

Or install openclaw, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 4 agents, 3 hooks.

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 openclaw-sandboxing

README.md
[![agentmods](https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-sandboxing/github.svg)](https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-sandboxing)
Your own site
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-sandboxing"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-sandboxing/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.

agentmods 80×15 button for openclaw-sandboxing

Your own site · 80×15
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-sandboxing"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-sandboxing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.01568
Opus 5 $0.00027 $0.00784
Sonnet 5 $0.00011 $0.00314
Haiku 4.5 $0.00005 $0.00157

Measured 12d ago against content hash 52d8bbd2aa68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

openclaw-sandboxing 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 12d 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.

# Includes: curl, jq, nodejs, python3, git
plugins/openclaw/skills/openclaw-sandboxing/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw Sandboxing

Guide the user through Docker sandbox configuration for isolated tool execution.

Sandboxing runs tools inside Docker containers to reduce blast radius. The Gateway stays on the host; tool execution runs in an isolated sandbox. This is optional and controlled by configuration.

Sandbox Modes

agents.defaults.sandbox.mode:

Mode Behavior
off No sandboxing (tools run on host)
non-main Sandbox only non-main sessions (default for multi-user)
all Every session runs in a sandbox

non-main is based on session.mainKey (default "main"). Group/channel sessions use their own keys, so they count as non-main and will be sandboxed.

Sandbox Scope

agents.defaults.sandbox.scope:

Scope Containers Use Case
session (default) One per session Maximum isolation
agent One per agent Shared state within agent
shared One for all sandboxed sessions Resource-efficient

Workspace Access

agents.defaults.sandbox.workspaceAccess:

Access Behavior
none (default) Sandbox workspace under ~/.openclaw/sandboxes
ro Agent workspace mounted read-only at /agent
rw Agent workspace mounted read/write at /workspace

With ro, write/edit/apply_patch tools are disabled in the sandbox.

Docker Configuration

{
  agents: {
    defaults: {
      sandbox: {
        mode: "non-main",
        scope: "session",
        workspaceAccess: "none",
        docker: {
          image: "openclaw-sandbox:bookworm-slim",
          network: "none",           // none | bridge | host (blocked)
          env: { NODE_ENV: "sandbox" },
          setupCommand: "apt-get update && apt-get install -y nodejs",
          user: "1000:1000",
          readOnlyRoot: false,
          binds: ["/home/user/data:/data:ro"],
        },
      },
    },
  },
}

Bind Mounts

Format: host:container:mode (e.g., /home/user/source:/source:ro)

Read the full file on GitHub · 239 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 239 lines · 54 tokens per session scan A 52d8bbd2aa68

Subscribe to this mod's changes

openclaw-sandboxing is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,568 once invoked, about $0.0003 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 2026-08-31.

Related

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…

omnigent-ai/omnigent · 84 tokens

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.

companion-inc/feynman · 45 tokens

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…

xalgorix/xalgorix · 80 tokens

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.

xalgorix/xalgorix · 40 tokens

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.

xalgorix/xalgorix · 41 tokens

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.

PurpleAILAB/Decepticon · 67 tokens