Subagents

| Agent | Scope | Purpose | Tools | |---|---|---|---| | qa-catalog:route-discoverer | plugin | Static route discovery + rich metadata (auth, roles, guards, HTTP methods, dynamic params, layout chain, feature flags). | Read, Grep, Glob, Bash | | qa-page-analyzer | project | Browser-driving deep element inventory per route. Each spawn starts its own browser process — true isolation, no shared state between parallel runs. | inherits all except Write, Edit, MultiEdit, and destructive Bash patterns | | qa-catalog:test-author | plugin | Pure markdown — converts page analysis into task files using the enforced template. | Read, Write, Edit, Glob | | qa-test-runner | project | Browser-driving execution of one task → date-stamped result.md with embedded screenshots. Designed for parallel fan-out, one isolated browser per runner. | inherits all except destructive Bash patterns | | qa-catalog:catalog-reconciler | plugin | Plans add/update/delete for catalog.json from the drift report. | Read, Grep, Glob |

All agents are model: inherit — they use whatever model your session is on. No model is hardcoded.

Token efficiency (by design)

Heavy work is isolated so it never floods the main conversation:

Each browser agent runs in its own context window and returns only a one-line JSON summary.
Verbose verification is offloaded to the verify-result.mjs / catalog-diff.mjs Node scripts — a hook, not the model, does the parsing.
The deterministic qa-test-runner uses effort: medium so extended-thinking tokens aren’t spent re-deriving a pre-authored task — multiplied across every parallel runner. Reasoning-heavy analysis (qa-page-analyzer) keeps effort: high.
Slash skills use disable-model-invocation: true, so their descriptions stay out of context until you invoke them.