How

Explain how a subsystem works by tracing executable entrypoints, types, state, dependencies, and tests. Use for $how, code walkthroughs, ownership questions, or architecture grounding before a change. Use $why for historical motivation.

Vaibtan Updated

File contents

How it works

Answer from executable evidence.

  1. Bound the question to a caller-visible behavior or ownership decision.
  2. Locate entrypoints, key types, state owners, external boundaries, and tests with repository search.
  3. Trace at least one concrete path from input to observable output. Read definitions and callers rather than inferring from names.
  4. Use a general exploration subagent only when the codebase slice is broad enough to benefit from independent tracing. Use explorer prompt for that brief.
  5. Check the trace against tests or a small runtime probe when practical.
  6. Explain the flow in the order it executes. Link files and lines, name uncertainty, and distinguish observed behavior from inference.

Use explainer prompt only for a separate synthesis pass on a genuinely complex trace. Do not add a second agent for a small walkthrough.

Vaibtan/pstack-skills-codex-port/tree/main/plugins/pstack/skills/how commit 91c594fbd9

Frequently asked questions

npx skillmds@latest add vaibtan/how