Codebase Search

This is a routing layer that turns vague "where is this?" requests into one of six search strategies before you start reading files. It forces you to pick exact-text, symbol-indexed, structural, config-content, hosted-search, or graph-path mode, then narrows scope and reads only the winning matches. The evidence map template keeps answers compact instead of dumping raw grep output. Most valuable when the repo is large enough that wandering through random files costs more than spending thirty seconds picking the right search packet. It hands off to debugging once you've mapped the likely failure path, or to refactoring when you're ready to change things. The packet decision tree is the real value here, not the search commands themselves.

skills.sh installs: 182
GitHub stars: 22
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add akillness/oh-my-skills --skill codebase-search --agent claude-code

Installs into .claude/skills of the current project.

Files

Codebase Search

When to use this skill

The main job is repo navigation before edits.
The user needs to find definitions, call sites, entry points, config owners, tests, templates, content references, or likely impact surface.
The repo is large enough that random file reading will waste time.
The request is really "where does this live / what uses it / what should I inspect first?" even if the user never says "search".
The repo may be app code, infra/config, content/templates, or game tooling/assets, and the first step is still discovery.

Do not use this skill as the main workflow when:

The user already found the area and now needs root-cause diagnosis → use debugging or log-analysis.
The user wants a behavior-preserving cleanup or migration plan → use code-refactoring.
The user wants judgment on a concrete diff / PR → use code-review.
The user wants a persistent whole-repo or mixed-corpus structure map → use graphify.