An Open Source Intelligent Codebase Visualizer for you and your agents for javascript, typescript, reactjs, nextjs, python, java, go and rust for easy PR review, fast Onboarding and deep architectural understanding
Command
Produce a thorough architecture document grounded in the graph — the kind of brief a raw LLM can't write because it's built from the codebase's real clusters, real edges, and precomputed business summaries. Arguments: none (cwd graph; pass a graphId to target another). Needs summaries for the richest output — follow…
Command
Explain recent work or a merge conflict in terms of functionality, covering the changed files — not just one. Argument: a time/ref spec — e.g. yesterday, 3 days, since main, HEAD5, .. , or nothing (= uncommitted working changes).
Command
Render the graph visually. Argument: [architecture|cluster|flow|deps] (default architecture). For cluster/flow, an optional second arg is a seed node id/name.
Command
Give a newcomer a real orientation to the codebase, scaled to its size and grounded in the graph. Argument: optional path to scope the explanation (file/folder); omitted = whole repo. Needs summaries for best results — follow the freshness/summarize-permission policy in SKILL.md first (structure-only still gives stack…
Command
Fast feature/code location. Argument: plus optional filters the user mentions (type, severity). Works on structure alone — no summarize permission needed.
Command
Check whether a change touches load-bearing code and warn before it's edited — covering every affected node. Argument: to check a target; with no argument, check the user's current uncommitted changes. Works on structure alone; richer with summaries.
Command
Answer "what breaks if I change X" and "what does X depend on". Argument: (a node name, node id, or file path). Works on structure alone — no summarize permission needed.
Command
Bootstrap so the other subcommands work. Arguments: none.
Command
Produce a complete, one-shot onboarding guide for a newcomer and save it to ONBOARDING.md at the repo root. Unlike /devlens explain (a quick in-chat orientation), this writes a durable, structured document a new engineer can read top to bottom and then start working. Arguments: none (cwd graph; graphId to target…
Command
Produce a thorough, prioritized security review covering the flagged nodes — not a sample. Argument: [low|medium|high] minimum severity (default low).
Command
Pull the right summary lens for a target without reading raw source, covering the relevant nodes. Arguments: [technical|functional|security] . Default kind: technical. Target optional (defaults to the repo's central nodes).
Command
Produce a thorough tech-debt report: the circular dependencies, the real coupling hotspots, and oversized modules. Arguments: none. Works on structure alone (richer with summaries — no summarize permission needed for structure).