A local system for working with untrusted repositories in temporary Docker containers. It isolates the container from the host filesystem, controls network access, caches dependencies, and removes the workspace afterward.

Use it to fetch, build, test, and inspect repositories in isolated workspaces with configurable network access.

It provides a safer place to inspect or run unfamiliar code without giving that code direct access to the host machine.

ca-sandbox — Plugin for Claude Code by arbiterForge: A local system for working with untrusted repositories in…

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.

Claude Code

/plugin marketplace add arbiterForge/codeArbiter

agentmods

npx agentmods add plugins/arbiterforge/codearbiter/ca-sandbox

Clone the repo

git clone --depth 1 https://github.com/arbiterForge/codeArbiter

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/arbiterforge/codearbiter/ca-sandbox.svg)](https://agentmods.dev/plugins/arbiterforge/codearbiter/ca-sandbox)

Your own site

<a href="https://agentmods.dev/plugins/arbiterforge/codearbiter/ca-sandbox"><img src="https://agentmods.dev/badge/plugins/arbiterforge/codearbiter/ca-sandbox.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

ca-sandbox 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 yesterday.

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.

plugins/ca-sandbox/.claude-plugin/plugin.json · 12 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

yesterday First seen · 12 lines scan A 6e6e9e45f18e

Subscribe to this mod's changes

ca-sandbox is a plugin published in the GitHub repository arbiterForge/codeArbiter (141 stars, last pushed yesterday), licensed AGPL-3.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

AI Safety Containers DevOps and cloud Security ai ai-agents ai-coding ai-governance ai-tools

techwolf-brand-kit

Official TechWolf brand assets for AI-generated outputs. Provides logo files in multiple variants (dark, white, monochrome) as SVG and PNG.

techwolf-ai/ai-first-toolkit · not measured

master-skills-ai-agent-builder

AI & Agents bundle — 388 curated skills (agents, ai-ml, prompt-engineering) for Claude Code, Codex & Antigravity.

sinhoneyy/master-skills · not measured

claude-dejavu

Memory + recovery + code grounding for Claude Code. Restores deleted sessions, hybrid Postgres+Weaviate recall across every past conversation, tree-sitter symbol indexing across 12 languages, eight identifier-grounding domains (env / DB / route / GraphQL / flag / CSS / i18n / module-export), and a 14-strategy…

HthSolid/claude-dejavu · not measured

ca-sandbox