From Napkin
Uses a configured Codebase Memory graph for code discovery, architecture orientation, symbol lookup, dependency tracing, and impact analysis. Falls back to local exploration when graph is unavailable.
How this skill is triggered — by the user, by Claude, or both
Slash command
/napkin:codebase-memory-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use the configured Codebase Memory graph as a discovery accelerator, not as the sole source of truth. Confirm graph-derived conclusions with source snippets or local files before editing code or making strong claims.
Use the configured Codebase Memory graph as a discovery accelerator, not as the sole source of truth. Confirm graph-derived conclusions with source snippets or local files before editing code or making strong claims.
list_projects when available and use the exact indexed project name. If the repository is not indexed, continue with local exploration or ask before calling index_repository when graph access is important.index_status or detect_changes when available. After a branch switch, assume the index may be stale until checked. If freshness cannot be established, disclose that limitation and verify locally.get_architecture once for orientation in an unfamiliar repository or subsystem. Do not repeat it for narrow follow-up questions.search_graph for definitions, implementations, routes, classes, interfaces, callers, and related symbols. Prefer a natural-language query for discovery and a name or qualified-name pattern for known symbols. Narrow by label or path, set a result limit, and paginate or reduce scope when the response reports more results.search_code or normal repository search for literal strings, configuration keys, test identifiers, error messages, and non-code files. Do not turn a precise text lookup into a broad graph query.get_code_snippet with the returned qualified name. If source snippets are unavailable, open the local file before relying on the result.trace_path for callers, callees, dependency paths, data flow, cross-service paths, and impact analysis. Include tests only when test coverage is part of the question.get_graph_schema before query_graph. Reserve custom queries for multi-hop or aggregate questions that simpler tools cannot answer, and apply LIMIT or the tool's row limit.delete_project, ingest traces, update ADRs, or index a repository unless the user explicitly requested or approved the action; announce it before execution.npx claudepluginhub ani1797/forge --plugin copilot-sdkAST-based code graph for sub-millisecond symbol lookup, dependency analysis, and blast radius via codebase-memory-mcp. Use before reading files to reduce token usage.
Explores codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Activates when users ask about code structure, feature locations, or architecture.
Builds and queries a per-repo SQLite graph of code symbols and relationships for fast, targeted file:line retrieval without grepping or reading whole files.