How do I install the Run Code skill?

Run npx skillmds@latest add tashfeenahmed/run-code in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Run Code safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Run Code?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Run Code free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Run Code?

tashfeenahmed (@tashfeenahmed) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Run Code by tashfeenahmed — Agent Skill

Name: Run Code
Author: tashfeenahmed

Run Code

Write and execute a throwaway multi-line program (python, javascript/node, or bash) and capture its output. Use this instead of bash when you need real logic — loops, parsing, math, data transforms, calling a library — rather than a single shell command. The agent authors a small program on the fly and runs it as a first-class action.

tashfeenahmed Updated Sep 21, 2026

File contents

Run Code Skill

Author a small program and run it. This is the "code-execution-as-action" primitive: rather than being limited to a fixed catalog of tools, the agent can write a throwaway script to do exactly what a task needs and execute it.

When to Use

Reach for run_code over bash when the task is really a small program:

Data transforms: parse JSON/CSV, reshape, aggregate, filter
Math / computation: anything beyond a one-liner
Using a library: call a python or node module to do the heavy lifting
Generating a tool on the fly: write the logic once, run it, read the result

For a single shell command (ls, git status, npm install), use bash.

Input

{
  "language": "python",
  "code": "import json\nprint(json.dumps({'sum': sum(range(10))}))",
  "timeout": 60000
}

Parameter	Type	Required	Default	Description
`language`	string	Yes	-	`python`, `javascript`, or `bash`
`code`	string	Yes	-	Full program source; print results to stdout
`timeout`	number	No	60000	Timeout in ms (max 120000)

Output

{
  "success": true,
  "output": "{\"sum\": 45}\n",
  "error": "",
  "exitCode": 0,
  "language": "python"
}

Field	Type	Description
`success`	boolean	True if the program exited 0
`output`	string	Captured stdout
`error`	string	Captured stderr (or error message)
`exitCode`	number	Process exit code

Notes

The program runs in the workspace directory; temp source files are written to the OS temp dir and cleaned up after execution.
python requires python3 on PATH; if it's missing, the result explains how to install it. javascript runs under node. bash runs under bash.
Output is captured up to 1 MB; long-running programs are killed at the timeout.
This is not a security sandbox — the same trust model as the bash skill.

---name: run-codedescription: Write and execute a throwaway multi-line program (python, javascript/node, or bash) and capture its output. Use this instead of bash when you need real logic — loops, parsing, math, data transforms, calling a library — rather than a single shell command. The agent authors a small program on the fly and runs it as a first-class action.---# Run Code SkillAuthor a small program and run it. This is the "code-execution-as-action"primitive: rather than being limited to a fixed catalog of tools, the agent canwrite a throwaway script to do exactly what a task needs and execute it.## When to UseReach for `run_code` over `bash` when the task is really a small *program*:- **Data transforms**: parse JSON/CSV, reshape, aggregate, filter- **Math / computation**: anything beyond a one-liner- **Using a library**: call a python or node module to do the heavy lifting- **Generating a tool on the fly**: write the logic once, run it, read the resultFor a single shell command (`ls`, `git status`, `npm install`), use `bash`.## Input```json{ "language": "python", "code": "import json\nprint(json.dumps({'sum': sum(range(10))}))", "timeout": 60000}```| Parameter | Type | Required | Default | Description ||-----------|------|----------|---------|-------------|| `language` | string | Yes | - | `python`, `javascript`, or `bash` || `code` | string | Yes | - | Full program source; print results to stdout || `timeout` | number | No | 60000 | Timeout in ms (max 120000) |## Output```json{ "success": true, "output": "{\"sum\": 45}\n", "error": "", "exitCode": 0, "language": "python"}```| Field | Type | Description ||-------|------|-------------|| `success` | boolean | True if the program exited 0 || `output` | string | Captured stdout || `error` | string | Captured stderr (or error message) || `exitCode` | number | Process exit code |## Notes- The program runs in the workspace directory; temp source files are written to the OS temp dir and cleaned up after execution.- `python` requires `python3` on PATH; if it's missing, the result explains how to install it. `javascript` runs under `node`. `bash` runs under `bash`.- Output is captured up to 1 MB; long-running programs are killed at the timeout.- This is not a security sandbox — the same trust model as the `bash` skill.

Frequently asked questions