trace-flow

Trace end-to-end execution flows across call chains in a repository.

2|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Mybigwang/project-agent --skill trace-flow-mybigwang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace-flow
Source: https://github.com/Mybigwang/project-agent/tree/main/src/project_agent/skills/builtin/trace-flow
Command: npx skills add https://github.com/Mybigwang/project-agent --skill trace-flow-mybigwang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Trace-flow helps you understand how a request, command, or feature propagates through the codebase, making it easy to follow the exact call chain from start to finish.

Core Features & Use Cases

  • End-to-end execution path mapping: Identifies the entry point, key intermediate steps, and final outcome for a given flow.
  • Call relationships with concrete locations: Points to important files, functions, and classes, and explains how they invoke each other.
  • Branching and external influences: Explains conditional logic entry conditions and includes relevant external dependencies, configuration switches, and environment variables.

Quick Start

Ask the agent to trace a specific flow by providing it as the value for “流程” (args), for example: Trace the full execution path for “run --prompt summarize this repository”.

Frequently Asked Questions about trace-flow

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I trace an execution flow and call chain across a repository?

To trace an execution flow, you identify the entry point, key intermediate steps, and final outcome, then map the files, functions, and classes invoked. This reveals the exact call chain for a request propagating through the codebase.

What is the best way to debug code comprehension issues with branching call graphs?

Debugging branching call graphs requires mapping conditional logic entry conditions and external dependencies. Tracing the end-to-end execution flow highlights how functions invoke each other across different branches and configuration switches.

Can I map external dependencies and configuration variables during execution path mapping?

Yes, execution path mapping includes relevant external dependencies, configuration switches, and environment variables. It tracks how these external influences affect the call chain alongside the internal repository navigation.

How do I start tracing a specific command or feature request end to end?

To start tracing a specific command, provide the request or feature details as an argument. The agent will enumerate the start, key intermediate steps, and end points to map the full end-to-end execution path.

Does trace-flow work with architecture investigations across external dependencies?

Trace-flow works for architecture investigations by mapping call relationships and concrete locations across the repository. It applies to debugging and code comprehension across call chains that include external dependencies and branches.