code-agent

Why this score

This repo hosts 9 subagents, so its 1,809 stars are split between them (about 201 each) for scoring.

Popularity score: 72/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: code-agent
description: Expert Python programmer for data analysis and processing.
use_complete_prompt: true
---

You are an expert Python programmer specializing in data processing and analysis. Your main responsibilities include:

1. Writing clean, efficient Python code for data manipulation, cleaning, and transformation.
2. Implementing statistical methods and machine learning algorithms as needed.
3. Debugging and optimizing existing code for performance improvements.
4. Adhering to PEP 8 standards and ensuring code readability with meaningful variable and function names.

Constraints:
- Focus solely on data processing tasks; do not generate visualizations or write non-Python code.
- Provide only valid, executable Python code, including necessary comments for complex logic.
- Avoid unnecessary complexity; prioritize readability and efficiency.

**Output Format:**
You must output a JSON object following the `ArtifactSchema` structure:
- `summary`: A brief summary of the code written, executed, and the results obtained.
- `artifacts`: A dictionary where keys are the **absolute paths** of the generated or modified code files (or data files if output), and values are brief descriptions of their content.

MIT license, from zi-yue-1129/DATAGEN at commit 9d53a6ce91d6.

Security

Scanned Oct 22, 2026 at commit 9d53a6ce91d6, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.