← Prompts
Skill / Understand AGENTS.md (harvested) · jantimon/web-performance-debugger (MIT)

Driving wpd from an agent

# Driving wpd from an agent For an agent consuming `wpd`. wpd finds and investigates; it does not grade, rank, or recommend. It hands you typed, measurement-tagged numbers and a clean exit code; the

# Driving wpd from an agent

For an agent consuming `wpd`. wpd finds and investigates; it does not grade, rank, or recommend. It
hands you typed, measurement-tagged numbers and a clean exit code; the judgment stays with you.

## The loop

1. **Record.** `wpd record <module> [flags]` writes a recording plus siblings. One `record` is one
   capture pass.
2. **Query.** Read the recording through the `query` verbs. **Never read the recording file directly**
   -- it can be many MB. Drill instead:

```
query spans <file>              # overview: one row per span, one shape across chrome/firefox/node
  -> query span <file> <kind:label>   # one span's full anatomy
       -> query get <file> <id>       # one raw event (stack + args); needs --deep or firefox
```

- Every verb takes `latest` in place of `<file>` (a cwd-keyed pointer, never resolved by mtime).
- Span identity is **kind + label**. A bare label that matches more than one kind is a collision;
  qualify it (`run`, `step:first increment`, `measure:hydrate`).
- `query spans --label X` with no match is a **filter**: it reports the empty result and exits 0.
  `query span X` with no match is a **lookup**: it exits 1. Pick the verb for the branch you want.
- Other verbs: `query cpu` (hot functions + rollup), `query frame <id>` (one function's callers and
  callees), `query blame --forced` (forced-layout read sites), `query events` (the raw log).

Sign in to view the full prompt.

Sign In

Classification

Skill Capability with explicit trigger pattern
Skill Understand
Explain or analyze
Scope Project
This codebase
Manual Manually placed / Persistent