This skill should be used when the user asks about their codebase, needs to find code locations, or wants to understand how their code works. Activates for questions about code structure, finding functions/classes, understanding implementations, or locating where to make changes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/augment-context-engine:codebase-retrievalThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When the user asks about their codebase, use the codebase-retrieval tool to find relevant code instead of guessing or asking the user to provide file paths.
When the user asks about their codebase, use the codebase-retrieval tool to find relevant code instead of guessing or asking the user to provide file paths.
Activate this skill when the user:
Create search queries based on the user's request:
Call codebase-retrieval with:
information_request: A natural language description of the code you're looking forGood query examples:
From the retrieval results:
Provide clear, actionable information:
npx claudepluginhub joshuarweaver/cascade-code-general-misc-2 --plugin augmentcode-context-engine-pluginInvestigates codebase to verify design assumptions, find patterns, locate features, confirm file locations/structure, and ground planning in reality before implementation.
Code-only search across the current repo and connected repos via context_search_code. Use this instead of context_research when you want code results without Slack, Jira, or doc noise mixed in. TRIGGER when: Grep/Glob/Read can't find a referenced class, function, or module (it may live in another connected repo); you need semantic code search rather than a literal pattern match; you want to find how something is implemented or used across repos; the user asks to "find", "locate", or "search for" code. DO NOT TRIGGER when: local Grep/Glob/Read can find what you need; you also need PR history, team decisions, Slack context, or issue tracker data — use context_research instead.
Semantic codebase search — use for exploring code, finding implementations, and answering questions about any project. Searches using natural language queries, identifier names, or file paths. Returns ranked results using embedding-based similarity, BM25 keyword matching, symbol matching, import graph analysis, and git recency. Use this as the default exploration tool instead of grep when you don't know the exact text to search for.