fallback-python-shell

A fallback procedure for using Python through a shell when code-execution or file-reading tools fail. It describes how to run Python with a shell heredoc and print results.

In plain words
What is it for?
Use it to read and process files, analyse data, or generate output with Python through the shell during tool failures.
Why use it?
It offers another way to process documents, analyse data, or read files when the usual execution tools return errors.

Skill for Claude CodeCodex

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.

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

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.01053
Opus 5 $0.00010 $0.00526
Sonnet 5 $0.00004 $0.00211
Haiku 4.5 $0.00002 $0.00105

Measured yesterday against content hash f908ed3ecada, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fallback-python-shell 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 yesterday.

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/fallback-python-shell/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell-Based Python Fallback

When to Use

Use this fallback pattern when:

  • execute_code_sandbox returns 'unknown error'
  • read_file returns 'unknown error' for supported formats
  • You need to process documents, analyze data, or read files programmatically

Core Technique

Run Python code through run_shell using a heredoc. This bypasses sandbox execution issues while maintaining Python's full capabilities for file I/O and data processing.

Basic Pattern

python3 << 'EOF'
# Your Python code here
import json
import os

# Example: Read and process a file
with open('/path/to/file.txt', 'r') as f:
    content = f.read()
    print(content)
EOF

Key Syntax Points

  1. Use python3 << 'EOF' (quoted EOF prevents variable expansion in the heredoc)
  2. Indent Python code starting from column 0 (no extra indentation from shell)
  3. End with EOF on its own line with no leading/trailing whitespace
  4. Print results to stdout to capture them in the tool response

Common Use Cases

Reading Files (Fallback for read_file)

python3 << 'EOF'
import json

# Read text file
with open('document.txt', 'r') as f:
    content = f.read()
    print(content)

# Read JSON file
with open('data.json', 'r') as f:
    data = json.load(f)
    print(json.dumps(data, indent=2))
EOF

Processing Excel/CSV Files

python3 << 'EOF'
import pandas as pd

# Read Excel file
df = pd.read_excel('data.xlsx', sheet_name='Sheet1')
print(df.to_string())
print(f"Shape: {df.shape}")

# Read CSV
df = pd.read_csv('data.csv')
print(df.head(10))
EOF

Reading PDF Files

python3 << 'EOF'
import fitz  # PyMuPDF

doc = fitz.open('document.pdf')
for page_num in range(len(doc)):
    page = doc[page_num]
    text = page.get_text()
    print(f"=== Page {page_num + 1} ===")
    print(text)
doc.close()
EOF

Reading Word Documents

python3 << 'EOF'
from docx import Document

doc = Document('document.docx')
for para in doc.paragraphs:
    print(para.text)
EOF

Read the full file on GitHub · 178 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. yesterday First seen · 178 lines · 20 tokens per session scan A f908ed3ecada

Subscribe to this mod's changes

fallback-python-shell is a skill published in the GitHub repository HKUDS/OpenSpace (7,479 stars, last pushed 19d ago), licensed MIT. It adds 20 tokens to every session and 1,053 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 2026-08-30.

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

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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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