New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Sandbox Execution Fallback 717e65

by HKUDS in HKUDS/OpenSpace

Fallback from executecodesandbox to file-based runshell execution when sandbox fails

MITAuto-check passed

Install Sandbox Execution Fallback 717e65

skills CLI
$ npx skills add HKUDS/OpenSpace --skill sandbox-execution-fallback-717e65 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/OpenSpace sandbox-execution-fallback-717e65 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/sandbox-execution-fallback-717e65 .claude/skills/sandbox-execution-fallback-717e65 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sandbox-execution-fallback-717e65
GitHub stars
7.8k
Token cost
~979 tokens
SKILL.md length
302 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Fallback from executecodesandbox to file-based runshell execution when sandbox fails

  • Works in 4 steps: Detect When to Switch → Write Python Script to File → Execute via Shell → …
  • SKILL.md covers When to Use, Procedure, Advantages Over Sandbox… and Complete Example, plus 2 more sections
  • Calls python3

What it does

Sandbox Execution Fallback 717e65 is an agent skill from HKUDS/OpenSpace. Fallback from executecodesandbox to file-based runshell execution when sandbox fails

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It works with Python. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

Example prompts

  • “/sandbox-execution-fallback-717e65”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Detect When to Switch
  2. Write Python Script to File
  3. Execute via Shell
  4. Handle Output and Clean Up

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sandbox Execution Fallback 717e65 loads about 979 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 302 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~979

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 302 words, ~979 tokens.

Download SKILL.mdSave it as .claude/skills/sandbox-execution-fallback-717e65/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sandbox-execution-fallback-717e65
description
Fallback from execute_code_sandbox to file-based run_shell execution when sandbox fails

Sandbox Execution Fallback

When to Use

Apply this pattern when execute_code_sandbox fails repeatedly or exhibits instability. Common triggers include:

  • Sandbox returns errors after 2-3 retry attempts
  • Error messages indicate provider/system issues rather than code bugs
  • Execution times out or hangs inconsistently
  • Complex multi-step code with file I/O is needed
  • Better error visibility and debugging is required

Procedure

Step 1: Detect When to Switch

Recognize the failure pattern:

  • execute_code_sandbox produces repeated errors despite code corrections
  • Error output suggests infrastructure issues (not syntax/logic errors)
  • The sandbox environment appears unstable or limited
Step 2: Write Python Script to File

Use write_file to save your script:

write_file(
    path="script.py",
    content="#!/usr/bin/env python3

# Your Python code here
import sys
print('Executing via file-based approach')
# ... rest of your code
"
)

For multi-file projects, write each file separately:

write_file(path="utils.py", content="# Utility functions\ndef helper(): ...")
write_file(path="main.py", content="from utils import helper\nhelper()")
Step 3: Execute via Shell

Run the script using run_shell:

run_shell(command="python3 script.py")

For scripts in subdirectories:

run_shell(command="cd mydir && python3 script.py")
Step 4: Handle Output and Clean Up
  • Parse stdout/stderr from run_shell output
  • Inspect created files directly using read_file if needed
  • Remove temporary scripts after successful execution:
    run_shell(command="rm script.py")

Advantages Over Sandbox Execution

BenefitExplanation
Bypasses provider limitationsNo sandbox resource constraints
Better error visibilityFull stack traces and system errors
Environment controlDirect access to system Python and packages
Multi-file supportEasy imports and module structure
PersistenceFiles remain for inspection and debugging
ReliabilityMore consistent execution behavior

Complete Example

# Scenario: execute_code_sandbox failing on data processing task

# Step 1: Write the script
write_file(
    path="process_data.py",
    content="#!/usr/bin/env python3
import json
import csv

# Load and process data
with open('input.json', 'r') as f:
    data = json.load(f)

# Transform data
results = []
for item in data:
    results.append({'processed': item['value'] * 2})

# Write output
with open('output.csv', 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['processed'])
    writer.writeheader()
    writer.writerows(results)

print('Processing complete')
"
)

# Step 2: Execute via shell
run_shell(command="python3 process_data.py")

# Step 3: Read results
read_file(filetype="csv", file_path="output.csv")

# Step 4: Clean up (optional)
run_shell(command="rm process_data.py")

Best Practices

  1. Use absolute or clear relative paths - Avoid ambiguity in file locations
  2. Add error handling in scripts - Catch exceptions and print meaningful messages
  3. Validate script content before writing - Ensure proper Python syntax
  4. Log execution steps - Track what was written and executed for debugging
  5. Clean up temporary files - Remove scripts after use unless needed for later inspection

Troubleshooting

IssueSolution
python3 not foundTry python or specify full path /usr/bin/python3
Import errorsUse run_shell(command="pip3 install package") first
Permission deniedAdd execute permission: run_shell(command="chmod +x script.py")
Working directory issuesUse absolute paths or cd in the command

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/sandbox-execution-fallback-717e65 of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Sandbox Execution Fallback 717e65 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sandbox Execution Fallback 717e65 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sandbox Execution Fallback 717e65 this skillHKUDS/OpenSpace7.8k—~979Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 48 repos~2k tokens
    Documents & OfficeAuto-check passed

  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes

  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

More from HKUDS/OpenSpace

All 199 skills in this repo

  • Audio Track Production Workflow

    HKUDS/OpenSpace

    Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

    7.8k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Cascade Failure Recovery

    HKUDS/OpenSpace

    Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.8k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed

  • Sandbox Code Execution Fallback

    HKUDS/OpenSpace

    Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.

    7.8k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed

  • Code Execution Fallback

    HKUDS/OpenSpace

    A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.

    7.8k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed

  • Code Execution Fallback and Path Anchoring

    HKUDS/OpenSpace

    Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Code Execution Fallback E81068

    HKUDS/OpenSpace

    Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Sandbox Execution Fallback 717e65

What does Sandbox Execution Fallback 717e65 do?

Fallback from executecodesandbox to file-based runshell execution when sandbox fails. Sandbox Execution Fallback 717e65 is an agent skill from HKUDS/OpenSpace.

How do I install Sandbox Execution Fallback 717e65 in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill sandbox-execution-fallback-717e65 -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/sandbox-execution-fallback-717e65 in HKUDS/OpenSpace) into .claude/skills/sandbox-execution-fallback-717e65 in your project. Claude Code loads it when a task matches its description.

How do I install Sandbox Execution Fallback 717e65 in Codex?

Run `npx skills add HKUDS/OpenSpace --skill sandbox-execution-fallback-717e65 -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/sandbox-execution-fallback-717e65 in HKUDS/OpenSpace) into .agents/skills/sandbox-execution-fallback-717e65 in your project. Codex loads it when a task matches its description.

Can I use Sandbox Execution Fallback 717e65 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/OpenSpace --skill sandbox-execution-fallback-717e65 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sandbox-execution-fallback-717e65, .gemini/skills/sandbox-execution-fallback-717e65, .github/skills/sandbox-execution-fallback-717e65 and .opencode/skills/sandbox-execution-fallback-717e65 in your project.

What does Sandbox Execution Fallback 717e65 need to run?

Going by SKILL.md and its folder, Sandbox Execution Fallback 717e65 needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Sandbox Execution Fallback 717e65 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sandbox Execution Fallback 717e65 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sandbox Execution Fallback 717e65 use?

Sandbox Execution Fallback 717e65 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sandbox Execution Fallback 717e65 use?

About 979 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sandbox Execution Fallback 717e65?

Skills that share tags, products or a category with Sandbox Execution Fallback 717e65: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sandbox Execution Fallback 717e65?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,750 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.