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

Execute Code Fallback

by HKUDS in HKUDS/OpenSpace

Fallback from executecodesandbox to runshell when e2b sandbox is unavailable

MITAuto-check passed

Install Execute Code Fallback

skills CLI
$ npx skills add HKUDS/OpenSpace --skill execute-code-fallback -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace execute-code-fallback --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/execute-code-fallback .claude/skills/execute-code-fallback && 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
execute-code-fallback
GitHub stars
7.7k
Token cost
~1k tokens
SKILL.md length
345 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Fallback from executecodesandbox to runshell when e2b sandbox is unavailable

  • Works in 4 steps: Detect the Failure → Switch to run_shell with Embedded Python → Install Dependencies First (If Needed) → …
  • SKILL.md covers When to Apply, Fallback Procedure, Complete Example and Important Considerations, plus 2 more sections
  • Calls python3 and pip

What it does

Execute Code Fallback is an agent skill from HKUDS/OpenSpace. Fallback from executecodesandbox to runshell when e2b sandbox is unavailable

Its SKILL.md is about 1k 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

  • “/execute-code-fallback”

Requirements

  • Python 3

Workflow steps

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

  1. Detect the Failure
  2. Switch to run_shell with Embedded Python
  3. Install Dependencies First (If Needed)
  4. Use Heredoc for Multi-line Code

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
    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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

Execute Code Fallback loads about 1k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 345 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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). 345 words, ~1,021 tokens.

Download SKILL.mdSave it as .claude/skills/execute-code-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
execute-code-fallback
description
Fallback from execute_code_sandbox to run_shell when e2b sandbox is unavailable

Execute Code Fallback Pattern

When execute_code_sandbox fails due to e2b unavailability, immediately fall back to run_shell with embedded Python code. This ensures task continuity when the sandbox service is down.

When to Apply

Use this pattern when you observe:

  • execute_code_sandbox returns errors mentioning "e2b", "sandbox unavailable", or connection timeouts
  • Repeated sandbox execution failures (2+ attempts)
  • Error messages indicating the code execution environment is unreachable

Fallback Procedure

Step 1: Detect the Failure

Identify that execute_code_sandbox has failed. Common error indicators:

  • "e2b service unavailable"
  • "Sandbox connection failed"
  • "Execution environment not reachable"
  • Timeout errors during code execution
Step 2: Switch to run_shell with Embedded Python

Instead of:

python
execute_code_sandbox(code="...")

Use:

bash
run_shell(command="python3 -c '...your Python code...'")
Step 3: Install Dependencies First (If Needed)

If your Python code requires external packages, install them first:

bash
run_shell(command="pip install pandas requests matplotlib")

Then execute your main code:

bash
run_shell(command="python3 << 'EOF'
import pandas as pd
import requests

# Your code here
print("Success")
EOF
")
Step 4: Use Heredoc for Multi-line Code

For complex Python scripts, use heredoc syntax for cleaner code:

bash
run_shell(command="python3 << 'PYTHON_SCRIPT'
import json
import os

# Complex logic here
data = {'key': 'value'}
with open('output.json', 'w') as f:
    json.dump(data, f)

print('File created successfully')
PYTHON_SCRIPT
")

Complete Example

Scenario: You need to process a CSV file and generate a report.

Original approach (sandbox):

python
execute_code_sandbox(code="""
import pandas as pd
df = pd.read_csv('data.csv')
summary = df.describe()
print(summary)
""")

Fallback approach (run_shell):

bash
# First install dependencies if needed
run_shell(command="pip install pandas --quiet")

# Then execute the code
run_shell(command="python3 << 'EOF'
import pandas as pd
df = pd.read_csv('data.csv')
summary = df.describe()
print(summary)
EOF
")

Important Considerations

  1. State Persistence: Unlike execute_code_sandbox, run_shell executions may not share state between calls. Save intermediate results to files if needed.

  2. Working Directory: Ensure you're operating in the correct directory. Use pwd to verify or include cd /path/to/workdir in your commands.

  3. Python Version: Use python3 explicitly to avoid ambiguity. Verify with python3 --version if needed.

  4. Error Handling: Check the stdout/stderr from run_shell to confirm success. Failed Python scripts will return non-zero exit codes.

  5. Security: Be cautious when embedding user-provided data into shell commands. Escape appropriately or use file-based input.

  6. Performance: For large computations, run_shell may be slower than sandbox. Consider breaking into smaller steps if timeouts occur.

Quick Reference

TaskSandbox ApproachFallback Approach
Simple calculationexecute_code_sandbox(code="print(2+2)")run_shell(command="python3 -c 'print(2+2)'")
Install + runexecute_code_sandbox(code="import pkg; ...")run_shell(command="pip install pkg && python3 -c '...'")
Multi-line scriptexecute_code_sandbox(code="...")run_shell(command="python3 << 'EOF'...EOF")
File I/Oexecute_code_sandbox(code="...")run_shell(command="python3 << 'EOF'...EOF")

Recovery Checklist

  • Confirm execute_code_sandbox failure (not a code bug)
  • Switch to run_shell immediately
  • Install required packages with pip install
  • Use heredoc for multi-line Python
  • Verify output and handle errors
  • Save intermediate results to files if multi-step

© 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/execute-code-fallback of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Execute Code Fallback 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.

Execute Code Fallback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Execute Code Fallback this skillHKUDS/OpenSpace7.7k—~1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k64 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 64 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.

    7.7k 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

    7.7k 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.

    7.7k 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.

    7.7k 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.

    7.7k 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

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

Works with

Questions about Execute Code Fallback

What does Execute Code Fallback do?

Fallback from executecodesandbox to runshell when e2b sandbox is unavailable. Execute Code Fallback is an agent skill from HKUDS/OpenSpace.

How do I install Execute Code Fallback in Claude Code?

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

How do I install Execute Code Fallback in Codex?

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

Can I use Execute Code Fallback 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 execute-code-fallback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/execute-code-fallback, .gemini/skills/execute-code-fallback, .github/skills/execute-code-fallback and .opencode/skills/execute-code-fallback in your project.

What does Execute Code Fallback need to run?

Going by SKILL.md and its folder, Execute Code Fallback needs the command-line tools its instructions call (python3 and pip). Our summary lists: Python 3.

Does Execute Code Fallback access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Execute Code Fallback 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 Execute Code Fallback use?

Execute Code Fallback 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 Execute Code Fallback use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Execute Code Fallback?

Skills that share tags, products or a category with Execute Code Fallback: 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 Execute Code Fallback?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,749 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.