sandbox
Skill2 starsChanged 6 months agoMITView on GitHub
Executes Python code in a temporary sandbox to verify it works before finalizing a mission.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- TakaGoto/rag-learning-academytheir own version, first seen Oct 28, 2026
- nakane1chome/claude-skillstheir own version, first seen Oct 15, 2026
- andreaiannarone/cc-profilestheir own version, first seen Oct 15, 2026
- Kooboo/Koobootheir own version, first seen Oct 13, 2026
- marcuskrogh/skillstheir own version, first seen Oct 13, 2026
- miracleEverywhere/dst-management-platform-apitheir own version, first seen Oct 8, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- icey1287/SuperMew★ 884same name
- miracleEverywhere/dst-management-platform-api★ 361same name
- Kooboo/Kooboo★ 345same name
- vercel/sandbox★ 222same name
- TakaGoto/rag-learning-academy★ 24same name
- andreaiannarone/cc-profiles★ 6same name
- marcuskrogh/skills★ 1same name
- nakane1chome/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- algorithmic-artSkill
- archive-researcherSkill
- browser-searchSkill
- claude-mem-clientSkill
- compose-emailSkill
- create-calendar-eventSkill
- evolve-coreSkill
- evolve-memorySkill
- index-filesSkill
- install-packageSkill
- manage-personaSkill
- merge-files-recursivelySkill
- recursive-mergeSkill
- repo-summarizerSkill
- search-personal-dataSkill
- search-webSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Verify Logic: Ensure that new algorithms or functions produce the expected output.
- Distinctive: line 17
Test Dependencies: Verify if specific third-party requirements function correctly.
- Distinctive: line 18
Prevent Loops: Use the built-in 15-second timeout to detect potential infinite loops safely.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
sandbox
Executes a snippet of Python code in an isolated temporary environment. This skill is primarily used by the Coder to verify that a proposed solution or script works as intended before it is delivered to the user or integrated into the core system.
Usage
This skill is used by the Coder to:
- Verify Logic: Ensure that new algorithms or functions produce the expected output.
- Check Syntax: Validate that generated code is free of syntax errors.
- Test Dependencies: Verify if specific third-party requirements function correctly.
- Prevent Loops: Use the built-in 15-second timeout to detect potential infinite loops safely.
Important Note
The sandbox can run in two modes:
- Docker-backed containment when
SANDBOX_BACKEND=dockerorautowith Docker available. - A process-isolated fallback when Docker is unavailable.
The Docker path disables container networking and mounts only the temporary workspace. The fallback path still uses subprocess.run, isolated Python startup, a temporary workspace, and a sanitized environment, but it is not equivalent to full container or WASM isolation.
Implementation
The execution logic is contained within scripts/sandbox.py. It captures STDOUT and STDERR to provide a full execution report back to the agent for debugging or confirmation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.