Skip to content
Agentmart
Submit a tool

run-command

Run shell commands (git, build tools, tests, package managers, etc).

Skill by tzaeb

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tzaeb-run-command-f7a2f1

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Run shell commands (git, build tools, tests, package managers, etc). Use when the user asks to run, execute, build, test, or install something.

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/run-command

What's inside

Skill name
run-command
Description
Run shell commands (git, build tools, tests, package managers, etc). Use when the user asks to run, execute, build, test, or install something.
License
MIT
Instructions
41 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • STREAMING.md

SKILL.md (first lines)

# Run Command

## Instructions

Execute shell commands using `subprocess` and capture output.

```python
import subprocess

result = subprocess.run(
    ["git", "status"],
    capture_output=True, text=True, timeout=30
)
print(result.stdout)
if result.returncode != 0:
    print(f"STDERR: {result.stderr}")
    print(f"Exit code: {result.returncode}")
```

For commands that need shell features (pipes, redirection):

```python
import subprocess

result = subprocess.run(
    "ls -la | head -20",
    shell=True, capture_output=True, text=True, timeout=30
)
print(result.stdout)
```

For long-running commands, use a longer timeout or stream output. See [STREAMING.md](STREAMING.md).

## Guidelines

- Always set a `timeout` to prevent hanging
- Prefer list form (`["cmd", "arg"]`) over `shell=True` when possible
- Always check `returncode` and show stderr on failure
- Print the output so the user can see the results

From tzaeb/skills_example, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 5, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tzaeb

Cite this page

run-command skill. Agent Mart. https://agentmart.dev/skills/tzaeb-run-command-f7a2f1 (last updated 2026-10-24)