Navigation Structured output

get_repo_outline

Directories with file counts, symbol distribution by kind, top-level module summary.

find + directory counting
Native baseline
786 vs 841
Tokens (CS vs native)

What it does

Aggregates the repository into a high-level view: directories with file counts, symbol distribution by kind (functions, classes, types), and top-level module summary. One level above get_file_tree.

Benchmark

Near-parity on token count (~786 vs ~841), but structured output with semantic categorization vs raw file list. Best used at session start alongside get_file_tree for comprehensive orientation.

Related tools

get_file_tree get_file_outline suggest_queries

Benchmark note

This benchmark compares CodeSift against the closest practical native workflow an agent would use for the same task. For some tools, that baseline is a direct shell equivalent such as rg or find. For AST-aware, graph-aware, and LSP-backed tools, the baseline is a multi-step workflow rather than a strictly identical command. Results should be read as agent-workflow comparisons: token cost, call count, and practical context efficiency.