python-shell-workaround

python-shell-workaround is a skill for Claude Code, Codex from HKUDS/OpenSpace. It costs 17 tokens per session (710 once invoked), scanned A, original, MIT.

A fallback procedure for running Python code through the shell when the sandbox cannot load external packages such as pandas or openpyxl.

In plain words
What is it for?
Use it to run package-dependent scripts, including spreadsheet and document-processing tasks, with shell commands or heredocs.
Why use it?
It helps separate sandbox package limitations from problems in the Python code itself.

Skill for Claude CodeCodex

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

Good fit Use it to run package-dependent scripts, including spreadsheet and document-processing tasks, with…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hkuds/openspace/python-shell-workaround
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 · 7,510 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 python-shell-workaround
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 python-shell-workaround

README.md
[![agentmods](https://agentmods.dev/badge/skills/hkuds/openspace/python-shell-workaround.svg)](https://agentmods.dev/skills/hkuds/openspace/python-shell-workaround)
Your own site
<a href="https://agentmods.dev/skills/hkuds/openspace/python-shell-workaround"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/python-shell-workaround.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 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.
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 $0.00017 $0.00710
Opus 5 $0.00009 $0.00355
Sonnet 5 $0.00003 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 3d ago against content hash cbdd5e16c912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

python-shell-workaround 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 3d 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/python-shell-workaround/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Shell Workaround

When to Use This Skill

Use this pattern when execute_code_sandbox fails with Python code that requires external packages (like openpyxl, python-docx, pandas, etc.) that may not be available in the sandbox environment.

The Pattern

Instead of relying solely on execute_code_sandbox, use run_shell with inline Python commands as a fallback:

python3 -c "your python code here"

Step-by-Step Instructions

Step 1: Detect Sandbox Failure

Watch for errors like:

  • ModuleNotFoundError for common packages
  • Import errors for external libraries
  • Sandbox environment limitations

Step 2: Convert Python Code to Shell Command

Transform your Python script into a one-liner or use a heredoc for longer scripts:

For simple code:

python3 -c "import openpyxl; wb = openpyxl.Workbook(); wb.save('file.xlsx')"

For complex code (using heredoc):

python3 << 'EOF'
import openpyxl
from openpyxl.utils import get_column_letter

wb = openpyxl.Workbook()
ws = wb.active
ws['A1'] = 'Header'
wb.save('output.xlsx')
print('File created successfully')
EOF

Step 3: Execute with run_shell

Use run_shell to execute the command:

tool: run_shell
command: python3 -c "import openpyxl; print('Package available')"

Step 4: Verify Output

Check the stdout/stderr from run_shell to confirm success, then proceed with subsequent steps.

Best Practices

  1. Escape quotes properly: Use single quotes inside double-quoted strings or vice versa
  2. Use heredocs for multiline code: Cleaner and easier to debug
  3. Install packages if needed: Add pip install package before your Python command if packages are missing
  4. Chain commands safely: Use && to ensure prerequisites succeed before running Python code

Example Scenarios

Creating Excel Files

python3 << 'EOF'
import openpyxl
from openpyxl.worksheet.datavalidation import DataValidation

wb = openpyxl.Workbook()
ws = wb.active
ws.title = "Data"

# Add headers
headers = ['Name', 'Email', 'Status']
for col, header in enumerate(headers, 1):
    ws.cell(row=1, column=col, value=header)

wb.save('output.xlsx')
EOF

Read the full file on GitHub · 113 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. 3d ago First seen · 113 lines · 17 tokens per session scan A cbdd5e16c912

Subscribe to this mod's changes

python-shell-workaround is a skill published in the GitHub repository HKUDS/OpenSpace (7,510 stars, last pushed 25d ago), licensed MIT. It adds 17 tokens to every session and 710 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

excel-addin-debugging

Debug and automate Excel add-ins running in WebView2 with Office.js awareness — active range inspection, Office context detection, dialog API handling, and requirement-set probing. Use when the user mentions Office.js, Excel.run, taskpane, ribbon command, named ranges, or an add-in dialog.

dsbissett/excel-webview2-mcp · 65 tokens

bug-report-writer

Converts rough notes, casual descriptions, console errors, or quick observations into professional, complete bug reports — exported as a formatted Excel (.xlsx) file ready for Excel, Google Sheets, Jira, or Azure DevOps. Use this skill whenever the user mentions: "write a bug report", "log a bug", "report this issue"…

ShreyasBh02/AI-Skills-Collection · 186 tokens

troubleshooting

Uses Excel WebView2 MCP and documentation to troubleshoot connection and target issues. Trigger this skill when listpages, newpage, or navigatepage fail, or when the server initialization fails.

dsbissett/excel-webview2-mcp · 41 tokens

dcf-model

Build discounted cash flow valuation workbooks in Excel.

NousResearch/hermes-agent · 14 tokens

audit-xls

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…

anthropics/financial-services · 104 tokens

google-drive-sheets

Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.

yc-software/qm · 31 tokens