Symbols Workflow comparison

get_context_bundle

Returns a symbol plus its imports, siblings, and types. Everything needed to understand a symbol in context without reading the full file.

−30%
Token reduction
grep -l + Read full file
Native baseline
1 vs 2
Calls (CS vs native)
1,503 vs 2,154
Tokens (CS vs native)

What it does

Returns a symbol plus everything needed to understand it in context: its imports, its siblings (other symbols in the same file), and the types it uses. One call replaces get_symbol + search_text + get_file_outline.

Benchmark

The token reduction is modest (−30%) compared to other tools because the native alternative (grep to find file + read full file) is already reasonably efficient for single-file context.

The real value is structure: instead of a raw file dump, you get a parsed, organized context that clearly separates the symbol from its dependencies.

When to use

  • Working with an unfamiliar symbol and need its full surrounding context
  • Understanding a function’s imports and related types
  • Replacing the pattern of get_symbol + multiple follow-up searches

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.