Agent skill · ar9av
code-understand
Build a ranked, citation-backed focus map of a codebase — the files and symbols an architecture actually hangs on — using CodeGraph when available and a dependency-free builtin (regex AST extraction + `rg` cross-file references) otherwise. Use this any time you (the coding agent) need to orient in an unfamiliar or large codebase before making a change: the user says "help me understand this codebase", "what's load-bearing here", "what would break if I change X", "who calls this", "map out this project's architecture", or you're about to touch code you haven't read yet and want to know what matters before scanning everything by hand. This is the same extractor `wiki-update` Step 3b uses internally — this skill exposes it directly so any agent session can call it on demand, not just during a wiki sync.
What it needs
About 3k tokens when loaded.
What this skill does
Code Understand — On-Demand Architecture Focus Map You are about to work in a codebase you don't fully know yet. Instead of grepping around or reading files at random, ask the local extractor for a focus map: the ranked symbols the architecture hangs on, each with a file:line citation and evidence type. Read only what it points at — this is a map, not a substitute for reading the actual code it cites. When to reach for this Before editing an unfamiliar module — see what calls it and what it calls before changing its shape. The user asks "how does X work", "what's the impact of changing Y", "who else uses this function" for a codebase, not the wiki. You're about to do a large refactor and want a ranked list of load-bearing files instead of reading the whole tree. You already have a diff or a set of changed files and want to know their blast radius before finishing the change. Not for: summarizing what a project does for the wiki (that's wiki-update Step 3b, which calls this same command as part of a bigger sync flow) — use this skill directly only when you need the focus map for your own immediate work, not to persist knowledge. Running it --project — defaults to the current directory. No --changed/--since — seeds from every tracked file (full-project scan). --changed <file> (repeatable) — seed from specific files you already know are relevant (e.g. files in the diff you're about to make). --since <sha> — seed from everything changed since a git ref (e.g. --since HEAD~5 or a base branch). --backend — auto (default) uses CodeGraph when installed, falls back to the builtin extractor otherwise; force builtin for the dependency-free path, or codegraph to require the enhanced backend (fails loudly if it's not installed rather than silently degrading). --max-symbols — cap the focus map size (default 50); keep this small for a quick orientation pass, raise it for a thorough one. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills ar9av/code-understand