Agent skill

Sandbox Fallback Python E5d7ae

by HKUDS in HKUDS/OpenSpace

Fallback to runshell with Python heredoc when executecodesandbox fails

MITAuto-check passed

Install Sandbox Fallback Python E5d7ae

skills CLI
$ npx skills add HKUDS/OpenSpace --skill sandbox-fallback-python-e5d7ae -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace sandbox-fallback-python-e5d7ae --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-fallback-python-e5d7ae .claude/skills/sandbox-fallback-python-e5d7ae && 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-fallback-python-e5d7ae
GitHub stars
7.7k
Token cost
~916 tokens
SKILL.md length
256 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Fallback to runshell with Python heredoc when executecodesandbox fails

  • SKILL.md covers When to Use, Common Failure Indicators, The Fallback Pattern and Key Considerations, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sandbox Fallback Python E5d7ae is an agent skill from HKUDS/OpenSpace. Fallback to runshell with Python heredoc when executecodesandbox fails

Its SKILL.md is about 920 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-fallback-python-e5d7ae”

Requirements

  • Python 3

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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    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 Fallback Python E5d7ae loads about 916 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 256 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~916

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). 256 words, ~916 tokens.

Download SKILL.mdSave it as .claude/skills/sandbox-fallback-python-e5d7ae/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sandbox-fallback-python-e5d7ae
description
Fallback to run_shell with Python heredoc when execute_code_sandbox fails

Python Sandbox Fallback Pattern

When to Use

Use this pattern when execute_code_sandbox fails with e2b/sandbox initialization errors, especially when running Python code that requires external libraries like reportlab, pandas, numpy, etc.

Common Failure Indicators

Detect these error patterns to trigger the fallback:

  • e2b initialization errors
  • sandbox creation/creation timeout failures
  • container startup errors
  • Connection/refusal errors from sandbox service

The Fallback Pattern

Basic Heredoc Approach

For short scripts, use a Python heredoc directly in run_shell:

python
run_shell(
    command="""python3 << 'EOF'
import sys
print(f"Python version: {sys.version}")
# Your code here
EOF
""",
    timeout=60
)
File-Based Approach for Complex Scripts

For longer scripts or when you need to preserve state across multiple executions:

python
# Step 1: Write the script to a temporary file
script_content = '''
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
import os

# Your code here
'''

run_shell(command=f"cat > /tmp/script.py << 'SCRIPT_EOF'\n{script_content}\nSCRIPT_EOF")

# Step 2: Execute the script
result = run_shell(command="python3 /tmp/script.py", timeout=120)

Key Considerations

Timeouts
  • run_shell typically needs longer timeouts than execute_code_sandbox
  • Use timeout=60 for simple scripts
  • Use timeout=120 or higher for library-heavy operations (PDF generation, data processing)
Library Availability
  • Verify required libraries are installed in the shell environment
  • Install missing libraries first if needed:
    python
    run_shell(command="pip install reportlab", timeout=60)
Error Handling
  • Capture and inspect run_shell output for Python errors
  • Check stderr for import failures or runtime exceptions
Working Directory
  • Files created via run_shell are in the current working directory by default
  • Use absolute paths or os.getcwd() to reference files reliably

Example: PDF Generation with reportlab

python
# FALLBACK VERSION (when execute_code_sandbox fails):

pdf_code = """
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.lib.units import inch

def create_memo(filename):
    c = canvas.Canvas(filename, pagesize=letter)
    c.drawString(1*inch, 10*inch, "Legal Memorandum")
    c.save()
    print(f"Created {filename}")

create_memo('/workspace/output.pdf')
"""

# Write script to file
run_shell(command=f"cat > /tmp/create_pdf.py << 'PYEOF'\n{pdf_code}\nPYEOF")

# Execute and verify
run_shell(command="python3 /tmp/create_pdf.py", timeout=120)

# Verify output exists
run_shell(command="ls -la /workspace/output.pdf", timeout=30)

Comparison Table

Aspectexecute_code_sandboxrun_shell (fallback)
IsolationHigh (containerized)Low (host environment)
ReliabilityCan fail with e2b errorsMore reliable
Library AccessPre-configured sandboxDepends on host
TimeoutDefault 30sConfigurable
File AccessARTIFACT_PATH conventionDirect filesystem

Migration Checklist

When switching from execute_code_sandbox to run_shell:

  • Increase timeout values (typically 2-4x)
  • Convert ARTIFACT_PATH references to actual file paths
  • Add explicit file verification steps after execution
  • Handle potential library import errors
  • Test script execution in shell environment first

© 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-fallback-python-e5d7ae of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Sandbox Fallback Python E5d7ae 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 Fallback Python E5d7ae compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sandbox Fallback Python E5d7ae this skillHKUDS/OpenSpace7.7k—~916Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k13 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 62 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 13 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
  • 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.

    7.7k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.7k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed
  • 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.

    7.7k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed
  • 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.

    7.7k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Sandbox Fallback Python E5d7ae

What does Sandbox Fallback Python E5d7ae do?

Fallback to runshell with Python heredoc when executecodesandbox fails. Sandbox Fallback Python E5d7ae is an agent skill from HKUDS/OpenSpace.

How do I install Sandbox Fallback Python E5d7ae in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill sandbox-fallback-python-e5d7ae -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/sandbox-fallback-python-e5d7ae in HKUDS/OpenSpace) into .claude/skills/sandbox-fallback-python-e5d7ae in your project. Claude Code loads it when a task matches its description.

How do I install Sandbox Fallback Python E5d7ae in Codex?

Run `npx skills add HKUDS/OpenSpace --skill sandbox-fallback-python-e5d7ae -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/sandbox-fallback-python-e5d7ae in HKUDS/OpenSpace) into .agents/skills/sandbox-fallback-python-e5d7ae in your project. Codex loads it when a task matches its description.

Can I use Sandbox Fallback Python E5d7ae 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-fallback-python-e5d7ae -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-fallback-python-e5d7ae, .gemini/skills/sandbox-fallback-python-e5d7ae, .github/skills/sandbox-fallback-python-e5d7ae and .opencode/skills/sandbox-fallback-python-e5d7ae in your project.

What does Sandbox Fallback Python E5d7ae need to run?

SKILL.md names no scripts, command-line tools or credentials: Sandbox Fallback Python E5d7ae is instructions for the agent only. Our summary lists: Python 3.

Does Sandbox Fallback Python E5d7ae 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 Fallback Python E5d7ae 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 Fallback Python E5d7ae use?

Sandbox Fallback Python E5d7ae 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 Fallback Python E5d7ae use?

About 916 tokens (SKILL.md is roughly 3.7k 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 Fallback Python E5d7ae?

Skills that share tags, products or a category with Sandbox Fallback Python E5d7ae: 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 Fallback Python E5d7ae?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 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.