From Codebase Index
Searches local codebase semantically for context before web lookup. Uses codebase_peek for fast discovery, codebase_search for full implementation details, plus call_graph and find_similar.
How this skill is triggered — by the user, by Claude, or both
Slash command
/codebase-index:codebase-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when you need local repository knowledge before web lookup.
Use this skill when you need local repository knowledge before web lookup.
codebase_peek(query, ...) to find likely locations quickly with metadata-only results.codebase_search(query, ...) when you need full code context.call_graph(name, direction) when you need callers/callees after locating a symbol.find_similar(code) for duplicate patterns and refactor planning.implementation_lookup(query) when you need the authoritative definition location.If results are weak, run index_status (check readiness) and index_codebase.
codebase_peek for discovery (fastest, cheap tokens).codebase_search for exact implementation review.find_similar for pattern matching and duplication.call_graph and call_graph_path for execution flow.index_codebase (force/estimate/verbose) for first-time or stale indexes.index_status, index_health_check, index_metrics, index_logs for operational checks.codebase_peek("payment processing flow")codebase_search("payment processing flow")call_graph("chargeCard", "callees")find_similar("function validate(data)")implementation_lookup("validate")grep for exact identifiers and tiny, deterministic lookups.websearch only when local tools return no results and docs are likely missing.codebase_peek before codebase_search to avoid high token usage.npx claudepluginhub helweg/opencode-codebase-index --plugin codebase-indexSemantic 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.
Provides semantic code search and index management via the ccc CLI. Automatically initializes and refreshes the codebase index for relevant file retrieval.
Searches codebases semantically with natural language queries to find implementations by concept (e.g., 'where is X', 'how does Y work'). Returns file paths, lines, and snippets.