create_analysis_plan
Create multi-step analysis plans with shared scratchpad, step dependencies, and automatic status tracking.
What it does
create_analysis_plan defines a sequence of analysis steps that share state through a scratchpad. Each step specifies which tool to call, what arguments to use, and which previous steps it depends on.
Why it exists
Complex codebase analysis often requires multiple tool calls where each step builds on the results of the previous one. Instead of managing this manually, create_analysis_plan provides structured orchestration with dependency tracking and shared state.
When to use it
- Multi-step investigations — trace a bug from symptom to root cause across several tools
- Comprehensive audits — run complexity, dead code, and hotspot analysis as a coordinated workflow
- Repeatable analysis — define once, inspect status at any time
Related tools
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.