sandbox-fallback-python

sandbox-fallback-python is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 25 tokens per session (732 once invoked), scanned A, original, MIT.

A method for running Python directly through shell commands when a sandbox service is unavailable or cannot be reached.

In plain words
What is it for?
Use it for Python tasks that need file handling or libraries such as pandas, NumPy, or ReportLab.
Why use it?
It bypasses failures in the separate sandbox environment so code can still run in the available workspace.

Skill for Claude CodeCodex

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

Good fit Use it for Python tasks that need file handling or libraries such as pandas, NumPy, or ReportLab.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/openspace/sandbox-fallback-python
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

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HKUDS/OpenSpace --skill sandbox-fallback-python
Clone the repo
git clone --depth 1 https://github.com/HKUDS/OpenSpace

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-python

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-fallback-python.svg)](https://agentmods.dev/skills/hkuds/openspace/sandbox-fallback-python)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/sandbox-fallback-python"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/sandbox-fallback-python.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 82
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00025 $0.00732
Opus 5 $0.00013 $0.00366
Sonnet 5 $0.00005 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 4d ago against content hash 4d22779a9daa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sandbox-fallback-python scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.get("https://api.example.com/data")
benchmarks/gdpval/skills/sandbox-fallback-python/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandbox Fallback: Python via run_shell

When to Use This Skill

Apply this skill when execute_code_sandbox fails with errors indicating:

  • e2b service unavailability
  • Sandbox timeout or connection issues
  • Code execution environment not accessible

This fallback allows you to execute Python code directly via shell, bypassing the sandbox infrastructure.

Fallback Procedure

Step 1: Detect Sandbox Failure

Identify fallback necessity from error messages like:

  • "e2b unavailable"
  • "sandbox connection failed"
  • "execution environment error"
  • Timeout errors during code execution

Step 2: Switch to run_shell with Embedded Python

Instead of execute_code_sandbox, use run_shell with a Python heredoc or inline script:

python3 << 'EOF'
# Your Python code here
print("Hello from fallback execution")
EOF

Step 3: Install Dependencies First

If your Python code requires packages not guaranteed to be installed:

pip install package_name package_name2 && python3 << 'EOF'
# Your Python code here
import package_name
print("Code with dependencies executed")
EOF

Step 4: Handle File I/O

For scripts that need to read/write files:

  • Use absolute or explicit relative paths
  • Files persist in the workspace directory
  • List directory contents with ls to verify file operations
python3 << 'EOF'
import os
# Write output to file
with open("output.txt", "w") as f:
    f.write("Results here")
# Verify
print(f"Working directory: {os.getcwd()}")
EOF

Code Examples

Simple Calculation

python3 << 'EOF'
result = sum(range(100))
print(f"Sum: {result}")
EOF

With Package Installation

pip install requests -q && python3 << 'EOF'
import requests
response = requests.get("https://api.example.com/data")
print(response.json())
EOF

With JSON Processing

python3 << 'EOF'
import json

data = {"key": "value", "count": 42}
output = json.dumps(data, indent=2)
print(output)

# Save to file
with open("data.json", "w") as f:
    f.write(output)
EOF

Read the full file on GitHub · 121 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 · 121 lines · 25 tokens per session scan A 4d22779a9daa

Subscribe to this mod's changes

sandbox-fallback-python is a skill published in the GitHub repository HKUDS/OpenSpace (7,534 stars, last pushed 26d ago), licensed MIT. It adds 25 tokens to every session and 732 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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