OhMyCode: Skill for Claude Code

Add a New Tool to OhMyCode

Create a new tool that the AI assistant can use during conversations.

When to Use

• User says "add a tool", "create a tool", "I want a new tool"
• User describes a capability they want the AI to have (e.g., "I want it to run SQL queries")

Prerequisites

• Read docs/DEVELOPMENT_GUIDE.md for project conventions
• Read ohmycode/tools/base.py to understand Tool, ToolContext, ToolResult, @register_tool
• Look at an existing tool (e.g., ohmycode/tools/bash.py) as reference

Step-by-Step Guide

Step 1: Define the Tool

Ask the user:

1. Tool name — short, lowercase, snake_case (e.g., sql_query, docker_run)
2. Description — one sentence for the LLM to understand when to use it
3. Parameters — what inputs does it need? (JSON Schema format)
4. Concurrent safety — can it run in parallel with other tools? (True for read-only, False for side effects)

Step 2: Create the Tool File

Copy the template from templates/tool_template.py to ohmycode/tools/<tool_name>.py.

Fill in:

• name, description, parameters, concurrent_safe class attributes
• execute() method with the actual logic

Step 3: Write Tests (TDD)

Create tests/tools/test_<tool_name>.py:

import pytest
from ohmycode.tools.base import ToolContext
from ohmycode.tools.<tool_name> import <ToolClass>

@pytest.fixture
def ctx(tmp_path):
    return ToolContext(mode="auto", agent_depth=0, cwd=str(tmp_path), is_sub_agent=False)

@pytest.mark.asyncio
async def test_<tool_name>_basic(ctx):
    tool = <ToolClass>()
    result = await tool.execute({"param": "value"}, ctx)
    assert not result.is_error
    assert "expected" in result.output

Step 4: Verify

python3 -m pytest tests/tools/test_<tool_name>.py -v   # New tests pass
python3 -m pytest tests/ -v                              # No regressions

Step 5: Test End-to-End

ohmycode -p "Use the <tool_name> tool to ..." --mode auto

Step 6: Commit