deepsearch
Thorough codebase search
Best for Codebase explorationWorks with GitHubLow risk
⌘source
- author
@Yeachan-Heo- language
- TypeScript
★24kstars
2kforks
Apr 19, 2026
✦overview.md
Key Features
- ·Thorough codebase search for queries, patterns, or concepts
- ·Multi-stage strategy: broad search, deep dive, and synthesis
- ·Identifies primary implementations and related files
- ·Maps usage patterns across the codebase
- ·Outputs comprehensive but concise findings with citations
Use Cases
- →Understanding where a specific concept or pattern is implemented in a large codebase
- →Tracing dependencies and connections between files during refactoring
- →Investigating how a particular functionality is used across different components
- →Documenting codebase structure and relationships for onboarding
Best for
- ✓Codebase exploration
- ✓Refactoring preparation
- ✓Architecture documentation
Not ideal for
- !Simple string searches
- !Real-time debugging
- !Performance profiling
FAQs
name
deepsearch
description
Thorough codebase search
Deep Search Mode
[DEEPSEARCH MODE ACTIVATED]
Objective
Perform thorough search of the codebase for the specified query, pattern, or concept.
Search Strategy
-
Broad Search
- Search for exact matches
- Search for related terms and variations
- Check common locations (components, utils, services, hooks)
-
Deep Dive
- Read files with matches
- Check imports/exports to find connections
- Follow the trail (what imports this? what does this import?)
-
Synthesize
- Map out where the concept is used
- Identify the main implementation
- Note related functionality
Output Format
- Primary Locations (main implementations)
- Related Files (dependencies, consumers)
- Usage Patterns (how it's used across the codebase)
- Key Insights (patterns, conventions, gotchas)
Focus on being comprehensive but concise. Cite file paths and line numbers.
$install
1-click copynpx skills add Yeachan-Heo/oh-my-codex --skill deepsearchSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.