codebase-explorerlisted

Conceptual code-reading for unfamiliar areas — trace a feature, follow a data flow, understand a domain. Use when the question is conceptual ("how does auth work?", "what happens when a user buys X?"); for symbol-precise queries (callers, blast radius, rename) use graph-explorer instead. The two are complementary — codebase-explorer reads code as prose; graph-explorer queries it as a graph.
kouroshez/coding-os · ★ 4 · AI & Automation · score 76

Install: claude install-skill kouroshez/coding-os

Explore the specified conceptual area of the codebase and produce a structured map. **Boundary with [graph-explorer](../graph-explorer/SKILL.md):** | Question shape | Use | |---|---| | "How does X work end-to-end?" | codebase-explorer | | "What happens when a user does Y?" | codebase-explorer | | "Where does this domain live?" | codebase-explorer | | "What calls function `foo`?" | graph-explorer (`cos_graph_references`) | | "What breaks if I rename `Bar`?" | graph-explorer (`cos_graph_rename_plan`) | | "Blast radius of changing `baz`?" | graph-explorer (`cos_graph_impact`) | codebase-explorer always *consults* graph-explorer for symbol-precise sub-questions during a conceptual walk — they compose, they don't compete. ## Process 1. **Graph gate** — If the query is an identifier-shaped symbol (`camelCase`, `snake_case`, `Class.method`, `TASK-NNN`, dotted path), try `cos_graph_query` first. It is faster + more accurate than grep for named symbols AND returns confidence-scored edges. Fall back to grep only if the graph returns zero hits (fresh repo, unindexed file) or the query is conceptual ("auth flow", "money handling"). 2. **Entry points** — Use Grep to find the main files related to the topic. 3. **Trace the flow** — Read key files, follow imports. When symbols cross file boundaries, prefer `cos_graph_context(uid, depth=1)` over chasing imports by hand — it returns the neighbourhood in a single MCP call. 4. **Dependencies** — Identify what this ar