Project overview: files, functions, classes, languages, subsystems, pipelines. Start here.

Look up any function by name. Returns signature, location, callers, callees, language.

Call graph for a function: who calls it and what it calls.

Search everything: functions, classes, sections, constants.

Get info about a file: functions, classes, sections, language.

Read source code of a function (by name) or file region (by path + line range).

Deep dive into a subsystem: files, top functions, languages.

Trace a named pipeline or pattern (parse, validate, handle, compile, etc.).

Data flow: upstream callers and downstream callees for a function.

Depth-limited call chain trace from a function.

Most connected functions (highest fan-in + fan-out).

Architecture: subsystems, cross-subsystem dependencies, language mix.

Blast radius: if you change this function, what breaks? Affected callers, subsystems, risk level.

Auto-generate Mermaid or D2 architecture diagrams. Target: "architecture", subsystem name, or function name.

Find dead code: functions with zero callers, grouped by subsystem, with LOC waste estimate.

Detect near-duplicate functions using token similarity. Finds copy-paste code.

Cyclomatic + cognitive complexity analysis. Per-function detail or top-N ranking.

Track complexity changes over recent git history. Shows which commits touched complex code.

Semantic search: find functions by meaning, not just name. "handle authentication" finds verify_token, check_session, etc.

Multi-repo federated search: query across multiple codebases at once.

Ask a natural language question about the codebase. Auto-routes to the right analysis tool.

Git-aware graph diff: changed functions, blast radius, risk level between any two refs.

Auto-generate PR review context: changes, blast radius, new cross-subsystem edges, complexity delta, risk.

Correlate OpenTelemetry/Jaeger traces with static call graph. Find hot production paths and cold code.