sandbox-fallback-execution-048d5a

sandbox-fallback-execution-048d5a is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 28 tokens per session (614 once invoked), scanned A, original, MIT.

A way to run Python on the host system when the sandbox repeatedly fails to start or connect.

In plain words
What is it for?
Use it to run Python scripts, process data, and confirm that expected files were created.
Why use it?
It offers a practical alternative after several sandbox errors when the task does not require sandbox isolation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is command: python3 /workspace/script_name.py.

Good fit Use it to run Python scripts, process data, and confirm that expected files were created.

Compare 6 skills from other repositories ↓
About the project

OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.

HKUDS/OpenSpace · 7,534 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace
agentmods
npx agentmods add skills/hkuds/openspace/sandbox-fallback-execution-048d5a

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sandbox-fallback-execution-048d5a

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-fallback-execution-048d5a.svg)](https://agentmods.dev/skills/hkuds/openspace/sandbox-fallback-execution-048d5a)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/sandbox-fallback-execution-048d5a"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-fallback-execution-048d5a.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00028 $0.00614
Opus 5 $0.00014 $0.00307
Sonnet 5 $0.00006 $0.00123
Haiku 4.5 $0.00003 $0.00061

Measured 4d ago against content hash 1a5bd85c97f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sandbox-fallback-execution-048d5a 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 4d 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.

benchmarks/gdpval/skills/sandbox-fallback-execution-048d5a/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandbox Fallback Execution

When execute_code_sandbox repeatedly fails with e2b sandbox errors, use this fallback pattern to execute Python code directly on the host system.

When to Use

Use this skill when:

  • execute_code_sandbox fails with e2b-related errors
  • Multiple retry attempts (3+) have not resolved the issue
  • The code does not require sandbox isolation

Steps

Step 1: Write Python Script to File

Use write_file to save your Python code as a .py file:

Tool: write_file
path: /workspace/script_name.py
content: |
  # Your Python code here
  import pandas as pd
  # ... rest of code

Step 2: Execute via Shell

Use run_shell with explicit python3 path:

Tool: run_shell
command: python3 /workspace/script_name.py
timeout: 120

Step 3: Verify Output

Check the stdout/stderr from run_shell for:

  • Successful execution messages
  • Expected output or file creation confirmations
  • Any errors that need debugging

Complete Example

# Instead of this (failing):
Tool: execute_code_sandbox
code: |
  import pandas as pd
  df = pd.DataFrame({'a': [1,2,3]})
  df.to_excel('output.xlsx')

# Use this fallback:
Tool: write_file
path: /workspace/generate_report.py
content: |
  import pandas as pd
  
  # Create sample data
  df = pd.DataFrame({'a': [1,2,3], 'b': [4,5,6]})
  
  # Save to Excel
  df.to_excel('/workspace/output.xlsx', index=False)
  print('File created successfully')

Tool: run_shell
command: python3 /workspace/generate_report.py
timeout: 120

Tips

  1. Use absolute paths in your Python script when reading/writing files
  2. Add print statements for debugging since you won't get interactive output
  3. Increase timeout if the script performs heavy computation
  4. Check working directory - scripts run from the workspace root by default
  5. Handle errors explicitly with try/except blocks and meaningful error messages

Common e2b Errors That Trigger This Fallback

  • E2B execution error
  • Sandbox timeout
  • Connection refused
  • Sandbox initialization failed
  • Repeated retry failures (3+ attempts)

Read the full file on GitHub · 97 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. 4d ago First seen · 97 lines · 28 tokens per session scan A 1a5bd85c97f0

Subscribe to this mod's changes

sandbox-fallback-execution-048d5a is a skill published in the GitHub repository HKUDS/OpenSpace (7,534 stars, last pushed 26d ago), licensed MIT. It adds 28 tokens to every session and 614 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 2026-09-03.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens