MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Use runshell with inline Python as a reliable fallback when executecodesandbox or readfile fail
MITAuto-check passed
Install Run Shell Fallback
$ npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/OpenSpace run-shell-fallback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/run-shell-fallback .claude/skills/run-shell-fallback && rm -rf skills-srcUse ~/.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/
Install the "run-shell-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallback into .claude/skills/run-shell-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-shell-fallback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/OpenSpace run-shell-fallback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/run-shell-fallback .agents/skills/run-shell-fallback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "run-shell-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallback into .agents/skills/run-shell-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-shell-fallback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/OpenSpace run-shell-fallback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/run-shell-fallback .cursor/skills/run-shell-fallback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "run-shell-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallback into .cursor/skills/run-shell-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-shell-fallback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/run-shell-fallback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/OpenSpace run-shell-fallback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/run-shell-fallback .gemini/skills/run-shell-fallback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "run-shell-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallback into .gemini/skills/run-shell-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-shell-fallback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HKUDS/OpenSpace run-shell-fallbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/run-shell-fallback .github/skills/run-shell-fallback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "run-shell-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallback into .github/skills/run-shell-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-shell-fallback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/OpenSpace run-shell-fallback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/run-shell-fallback .opencode/skills/run-shell-fallback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "run-shell-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/run-shell-fallback into .opencode/skills/run-shell-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "run-shell-fallback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
run-shell-fallback- GitHub stars
- 7.7k
- Token cost
- ~1k tokens
- SKILL.md length
- 268 words
- Files
- 2
- Skills in repo
- 199
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use runshell with inline Python as a reliable fallback when executecodesandbox or readfile fail
- Works in 3 steps: File Reading Fallback → Code Execution Fallback → Decision Flow
- SKILL.md covers When to Use, How to Implement, Best Practices and Examples, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Run Shell Fallback is an agent skill from HKUDS/OpenSpace. Use runshell with inline Python as a reliable fallback when executecodesandbox or readfile fail
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
- “/run-shell-fallback”
Requirements
- Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Run Shell Fallback loads about 1k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 268 words of instructions outside code blocks.
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). 268 words, ~1,012 tokens.
Download SKILL.mdSave it as
.claude/skills/run-shell-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- run-shell-fallback
- description
- Use run_shell with inline Python as a reliable fallback when execute_code_sandbox or read_file fail
Run Shell Fallback Pattern
This skill provides a reliable workaround when execute_code_sandbox or read_file fail with 'unknown error' by switching to run_shell with inline Python code.
When to Use
Apply this pattern when you encounter:
execute_code_sandboxfails with "unknown error" or timeoutread_filefails to read accessible files with "unknown error"- Sandbox environment is unreliable for your specific task
How to Implement
1. File Reading Fallback
When read_file fails, use run_shell with Python or cat:
For text files:
run_shell(command="cat /path/to/file.txt")For structured parsing (Python one-liner):
run_shell(command="python3 -c \"import json; print(json.load(open('/path/to/file.json')))\"")For multi-line Python processing:
run_shell(command="python3 << 'EOF'
with open('/path/to/file.txt', 'r') as f:
content = f.read()
# Process content here
print(content.upper())
EOF")2. Code Execution Fallback
When execute_code_sandbox fails, use run_shell with inline Python:
Simple one-liners:
run_shell(command="python3 -c \"print('Hello'); import os; print(os.getcwd())\"")Multi-line scripts (heredoc):
run_shell(command="python3 << 'EOF'
import os
import json
def process_data(data):
return {k: v.upper() if isinstance(v, str) else v for k, v in data.items()}
with open('input.json') as f:
data = json.load(f)
result = process_data(data)
print(json.dumps(result, indent=2))
EOF")With inline file write:
run_shell(command="python3 << 'EOF'
result = {'status': 'success', 'count': 42}
with open('output.json', 'w') as f:
json.dump(result, f, indent=2)
print('File written successfully')
EOF")3. Decision Flow
1. Attempt execute_code_sandbox or read_file
2. If failure with 'unknown error':
a. Determine task type (code execution vs file reading)
b. Choose inline Python approach (-c for simple, heredoc for complex)
c. Execute via run_shell
d. Parse output as needed
3. Continue with task using results from run_shellBest Practices
Escape quotes properly in
-ccommands: Use\"for double quotes inside the command stringUse heredoc for complex scripts: When code exceeds 2-3 lines or needs multiple imports, use
<< 'EOF'syntaxQuote EOF marker: Use
<< 'EOF'(with quotes) to prevent variable expansion in the heredocCapture stdout: Design your inline Python to print results to stdout for easy capture
Error handling: Add try/except blocks in your inline Python to catch and report errors clearly
File paths: Use absolute paths when possible, or ensure working directory is correct
Examples
Example 1: Read and parse JSON after read_file failure
run_shell(command="python3 -c \"import json; data=json.load(open('config.json')); print(data['key'])\"")Example 2: Process CSV data after execute_code_sandbox failure
run_shell(command="python3 << 'EOF'
import csv
with open('data.csv', 'r') as f:
reader = csv.DictReader(f)
rows = list(reader)
print(f\"Total rows: {len(rows)}\")
for row in rows[:5]:
print(row)
EOF")Example 3: Transform and write output file
run_shell(command="python3 << 'EOF'
import json
with open('input.json') as f:
data = json.load(f)
transformed = [item.upper() if isinstance(item, str) else item for item in data]
with open('output.json', 'w') as f:
json.dump(transformed, f, indent=2)
print('Transformation complete')
EOF")Limitations
- run_shell executes in the shell environment, not the sandbox - ensure paths and dependencies are available
- Output is limited to stdout/stderr - use file writes for large data
- Complex multi-file projects may require creating temporary script files first
© 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/run-shell-fallback of HKUDS/OpenSpace.
- SKILL.md
- .skill_id
Open the folder on GitHubat commit 3827781
Compare with similar skills
Run Shell 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Run Shell Fallback this skillHKUDS/OpenSpace | 7.7k | — | ~1k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PDF Processinganthropics/skills | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | |
| NotebookLM Research AssistantPleasePrompto/notebooklm-skill | 7.8k | 13 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Manim Video Productionbrowser-use/video-use | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
PDF Processing
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
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.
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.
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.
PPT Master
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
More from HKUDS/OpenSpace
All 199 skills in this repoAudio 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.
Cascade Failure Recovery
HKUDS/OpenSpace
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
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.
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.
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.
Code Execution Fallback E81068
HKUDS/OpenSpace
Fallback workflow for executing Python code when executecodesandbox fails repeatedly
Related
Works with
Questions about Run Shell Fallback
What does Run Shell Fallback do?
Use runshell with inline Python as a reliable fallback when executecodesandbox or readfile fail. Run Shell Fallback is an agent skill from HKUDS/OpenSpace.
How do I install Run Shell Fallback in Claude Code?
Run `npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/run-shell-fallback in HKUDS/OpenSpace) into .claude/skills/run-shell-fallback in your project. Claude Code loads it when a task matches its description.
How do I install Run Shell Fallback in Codex?
Run `npx skills add HKUDS/OpenSpace --skill run-shell-fallback -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/run-shell-fallback in HKUDS/OpenSpace) into .agents/skills/run-shell-fallback in your project. Codex loads it when a task matches its description.
Can I use Run Shell 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 run-shell-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/run-shell-fallback, .gemini/skills/run-shell-fallback, .github/skills/run-shell-fallback and .opencode/skills/run-shell-fallback in your project.
What does Run Shell Fallback need to run?
SKILL.md names no scripts, command-line tools or credentials: Run Shell Fallback is instructions for the agent only. Our summary lists: Python 3.
Does Run Shell Fallback access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Run Shell 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 Run Shell Fallback use?
Run Shell 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 Run Shell Fallback use?
About 1k tokens (SKILL.md is roughly 4k 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 Run Shell Fallback?
Skills that share tags, products or a category with Run Shell 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 Run Shell Fallback?
HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 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.