sandbox_exec

A tool for running shell commands and managing files in an isolated Foundry sandbox.

In plain words
What is it for?
Running commands, listing workspace files, writing files, and acquiring or releasing sandbox access.
Why use it?
It lets an agent work in a separate environment and monitor whether commands succeed or fail, without relying on the main workspace.

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/ic-star-tech/ccfoundry-agent-kit/sandbox_exec
Any agent
npx skills add ic-star-tech/ccfoundry-agent-kit --skill sandbox_exec
Clone the repo
git clone --depth 1 https://github.com/ic-star-tech/ccfoundry-agent-kit

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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 $0.00014 $0.00569
Opus 5 $0.00007 $0.00284
Sonnet 5 $0.00003 $0.00114
Haiku 4.5 $0.00001 $0.00057

Measured 2d ago against content hash bba3aeaf9a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox_exec 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 2d 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.

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.

examples/verilog_module_writer/agent_space/skills/sandbox_exec/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandbox Executor Skill

Trigger

Use this skill when the task requires executing commands in an isolated sandbox environment, or when managing workspace files.

Capabilities

  • Acquire and release sandbox leases from the Foundry sandbox pool
  • Execute shell commands inside the sandbox container
  • Write files to the sandbox workspace via API
  • Monitor command output and detect success/failure

API Reference

Acquire a sandbox lease

POST {SANDBOX_DAEMON_URL}/acquire
Content-Type: application/json
x-sandbox-token: {token}

{"username": "<agent_username>"}

Returns: {"lease_id": "...", "slot": 1, ...}

Execute a command

POST {SANDBOX_DAEMON_URL}/leases/{lease_id}/terminal/exec
Content-Type: application/json

{"command": "<shell_command>"}

Returns: Terminal output

Write a file to workspace

PUT {SANDBOX_DAEMON_URL}/users/{username}/workspace/write
Content-Type: application/json
x-sandbox-token: {token}

{"path": "relative/path/to/file.txt", "content": "file content here"}

List workspace files

GET {SANDBOX_DAEMON_URL}/users/{username}/workspace/tree
x-sandbox-token: {token}

Release the sandbox

POST {SANDBOX_DAEMON_URL}/release
Content-Type: application/json

{"lease_id": "<lease_id>"}

Best Practices

  • Always release the sandbox lease after use (even on error — use try/finally)
  • Wait 3-5 seconds after sandbox acquisition for container initialization
  • Use unique markers in commands to detect success: echo EXIT_CODE=$?
  • Set reasonable timeouts for long-running commands: timeout 30 <command>
  • Check pool status before acquiring: GET /pool-status

Environment Variables

  • SANDBOX_DAEMON_URL: Daemon endpoint (default: http://localhost:9000)
  • SANDBOX_TOKEN: Authentication token for the daemon API

Error Handling

  • If lease acquisition fails, the pool may be full — retry after delay
  • If command execution times out, the sandbox may need to be released and re-acquired
  • Always check HTTP status codes: 200/201 = success, 4xx = client error, 5xx = server error

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 14 tokens per session scan A bba3aeaf9a42

Subscribe to this mod's changes

sandbox_exec is a skill published in the GitHub repository ic-star-tech/ccfoundry-agent-kit (24 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 569 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens