> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CodingTools: Minimal Tools for Coding Agents

> A single toolkit with 4 core tools (read, edit, write, shell) that lets an agent perform any coding task.

A single toolkit with 4 core tools (read, edit, write, shell) that lets an agent perform any coding task. Inspired by the Pi coding agent's philosophy: a small number of composable tools is more powerful than many specialized ones.

```python basic_usage.py theme={null}
"""
CodingTools: Minimal Tools for Coding Agents
=============================================
A single toolkit with 4 core tools (read, edit, write, shell) that lets
an agent perform any coding task. Inspired by the Pi coding agent's
philosophy: a small number of composable tools is more powerful than
many specialized ones.

Core tools (enabled by default):
- read_file: Read files with line numbers and pagination
- edit_file: Exact text find-and-replace with diff output
- write_file: Create or overwrite files
- run_shell: Execute shell commands with timeout

Exploration tools (opt-in):
- grep: Search file contents
- find: Search for files by glob pattern
- ls: List directory contents
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.coding import CodingTools

# ---------------------------------------------------------------------------
# Create Agent with CodingTools
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[CodingTools(base_dir=".")],
    instructions="You are a coding assistant. Use the coding tools to help the user.",
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "List the files in the current directory and read the README.md file if it exists.",
        stream=True,
    )
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai
```

**2. Export your OpenAI API key**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

Save the code above as `basic_usage.py`, then run:

```bash theme={null}
python basic_usage.py
```

Full source: [cookbook/91\_tools/coding\_tools/01\_basic\_usage.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/91_tools/coding_tools/01_basic_usage.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.