aboutme-index
Index-based file discovery using ABOUTME headers. Use INSTEAD of grep or Explore agent when searching for files by purpose or feature. Faster and more accurate than scanning code. Invoke this skill when user asks "which files handle X", "where is Y implemented", or when you need to find files related to a feature or task.
When & Why to Use This Skill
The aboutme-index Claude skill enables high-speed, index-based file discovery within complex codebases by leveraging descriptive ABOUTME headers. Designed as a superior alternative to traditional grep-searching, this tool allows developers to semantically locate files based on their purpose or feature set. By maintaining a centralized index, it significantly reduces the cognitive load of navigating large projects and accelerates the process of understanding where specific logic is implemented.
Use Cases
- Feature Discovery: Instantly identify which files handle specific business logic, such as 'Where is the payment gateway integrated?' or 'Which files manage user session state?'
- Codebase Onboarding: Help new team members quickly grasp the project structure by querying the index for a high-level overview of file responsibilities without reading every line of code.
- Documentation Maintenance: Use built-in commands like /aboutme-check and /aboutme-stale to identify undocumented files or outdated headers, ensuring the codebase remains searchable and well-organized.
- Architectural Auditing: Rapidly map out the distribution of features across a repository to evaluate modularity or plan for large-scale refactoring tasks.
| name | aboutme-index |
|---|---|
| description | Index-based file discovery using ABOUTME headers. Use INSTEAD of grep or Explore agent when searching for files by purpose or feature. Faster and more accurate than scanning code. Invoke this skill when user asks "which files handle X", "where is Y implemented", or when you need to find files related to a feature or task. |
ABOUTME Index
Read .claude/aboutme-index.json to find files by purpose instead of grep-searching.
Usage
- Read the index:
cat .claude/aboutme-index.json
- Filter by keyword using jq:
cat .claude/aboutme-index.json | jq 'to_entries[] | select(.value | test("auth|jwt"; "i"))'
- Read the relevant files.
Commands
| Command | Description |
|---|---|
/aboutme-check |
Find files missing ABOUTME headers |
/aboutme-rebuild |
Rebuild the entire index |
/aboutme-stale |
Check for stale headers |
cat .claude/aboutme-index.json |
Read the index directly |
Index Format
{
"app/src/auth.py": "JWT authentication module for AWS Cognito access tokens...",
"app/src/config.py": "Centralized configuration using Pydantic settings..."
}
The index is auto-rebuilt on session start and updated incrementally on file edits.