Impact Analysis Tools
Impact analysis tools help your AI assistant assess risk before making changes. They analyze what would break if you modify a symbol, find code with no callers, identify complexity hotspots, examine git history for change patterns, and surface technical debt.
change_impact
Section titled “change_impact”Analyze the impact of changing a symbol. Returns all symbols, modules, and entry points that would be affected by a modification, helping you understand the blast radius before making changes.
Parameters
Section titled “Parameters”| Name | Type | Required | Description |
|---|---|---|---|
fqn |
string | Yes | Fully qualified name of the symbol to analyze |
workspace_id |
string | No | Limit results to a specific workspace |
repo_id |
string | No | Limit results to a specific repository |
Example prompt
Section titled “Example prompt”“What would break if I change the User model?”
The assistant calls change_impact and returns a structured analysis of affected callers, downstream dependencies, and entry points that would need testing or updating.
dead_code_detector
Section titled “dead_code_detector”Find potentially dead code with no callers. Scans a module for functions, methods, and classes that are defined but never referenced from anywhere else in the codebase.
Parameters
Section titled “Parameters”| Name | Type | Required | Description |
|---|---|---|---|
module_path |
string | Yes | Path to the module or package to scan |
workspace_id |
string | No | Limit results to a specific workspace |
repo_id |
string | No | Limit results to a specific repository |
Example prompt
Section titled “Example prompt”“Find dead code in the utils package”
The assistant calls dead_code_detector and returns a list of symbols that have no incoming call edges or references, along with their file locations and definitions. Results are reviewed by the enrichment pipeline to reduce false positives.
complexity_hotspots
Section titled “complexity_hotspots”Find the most complex files and functions in your codebase. Returns a ranked list based on cyclomatic complexity, file size, and other structural metrics.
Parameters
Section titled “Parameters”| Name | Type | Required | Description |
|---|---|---|---|
workspace_id |
string | No | Limit results to a specific workspace |
repo_id |
string | No | Limit results to a specific repository |
limit |
integer | No | Maximum number of results (default: 20) |
Example prompt
Section titled “Example prompt”“What are the most complex functions in this repo?”
The assistant calls complexity_hotspots and returns a ranked list of functions and files sorted by complexity, helping you identify code that may benefit from refactoring or extra test coverage.
git_archaeology
Section titled “git_archaeology”Analyze git history for a file or symbol. Returns change frequency, contributor patterns, recent modifications, and historical context - helping you understand how code has evolved over time.
Parameters
Section titled “Parameters”| Name | Type | Required | Description |
|---|---|---|---|
file_path |
string | Yes | Path to the file to analyze |
workspace_id |
string | No | Limit results to a specific workspace |
repo_id |
string | No | Limit results to a specific repository |
Example prompt
Section titled “Example prompt”“Show me the history of the auth middleware”
The assistant calls git_archaeology and returns change frequency, number of contributors, recent commits, and ownership patterns for the file. Files with high churn and many authors often indicate areas that need attention.
tech_debt_index
Section titled “tech_debt_index”List technical debt items detected in your codebase. Surfaces TODO, FIXME, and HACK markers along with their context, severity classification, and file locations.
Parameters
Section titled “Parameters”| Name | Type | Required | Description |
|---|---|---|---|
workspace_id |
string | No | Limit results to a specific workspace |
repo_id |
string | No | Limit results to a specific repository |
severity |
string | No | Filter by severity: low, medium, or high |
limit |
integer | No | Maximum number of results (default: 50) |
Example prompt
Section titled “Example prompt”“Show me all high severity tech debt”
The assistant calls tech_debt_index with the severity filter and returns a prioritized list of technical debt items, each with its marker text, surrounding code context, file location, and enrichment-generated classification.