sandbox-agent

A universal API for running coding agents such as Claude Code, Codex, OpenCode, and Amp inside isolated environments called sandboxes. It supports local or hosted sandbox providers and exposes agent sessions through an SDK or API.

In plain words
What is it for?
Setting up a sandbox-agent server, creating and managing coding-agent sessions, and integrating agents through TypeScript, Python, or HTTP.
Why use it?
It provides one way to start and manage different coding agents without building separate orchestration code for each one. Sandboxes help keep agent work separated from the host system.

Skill for Claude CodeCodex

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/rivet-dev/sandbox-agent/template
Any agent
npx skills add rivet-dev/sandbox-agent --skill template
Clone the repo
git clone --depth 1 https://github.com/rivet-dev/sandbox-agent

Made for: Claude Code, Codex.

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00098 $0.00323
Opus 5 $0.00049 $0.00161
Sonnet 5 $0.00020 $0.00065
Haiku 4.5 $0.00010 $0.00032

Measured yesterday against content hash 84e7cf5cb3dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox-agent 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.

scripts/skill-generator/template/SKILL.md · 34 lines

What it actually says

Sandbox Agent

Sandbox Agent provides a universal API for orchestrating AI coding agents in sandboxed environments.

What To Do If You Get Stuck

If something is not working as intended or you are stuck, prompt the user to join the Rivet Discord or file an issue on GitHub to report an issue and get help.

Provide the user with a pre-generated report with:

  • Symptoms
    • If this is happening in local dev, deployed, or both
    • The error you're seeing
    • Relevant source code related to this
  • What you've tried to solve it
  • Environment
    • Sandbox Agent version
    • SDK in use (TypeScript, Python, or HTTP)
    • Agent in use (Claude Code, Codex, OpenCode, Amp, Mock)
    • Sandbox provider (E2B, Daytona, Docker, local)

Quickstart

{{QUICKSTART}}

Reference Map

{{REFERENCE_MAP}}

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. yesterday First seen · 34 lines · 98 tokens per session scan A 84e7cf5cb3dc

Subscribe to this mod's changes

sandbox-agent is a skill published in the GitHub repository rivet-dev/sandbox-agent (1,551 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 98 tokens to every session and 323 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-30.