Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cruzs85/opencode-multiagente-local-37-iterations --skill qa-decision-enginegit clone --depth 1 https://github.com/cruzs85/opencode-multiagente-local-37-iterationsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/qa-decision-engine)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/qa-decision-engine"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/qa-decision-engine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/qa-decision-engine"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/qa-decision-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.02011 |
| Opus 5 | $0.00024 | $0.01006 |
| Sonnet 5 | $0.00010 | $0.00402 |
| Haiku 4.5 | $0.00005 | $0.00201 |
Grade A, and why
qa-decision-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OBJETIVO
Proveer un árbol de decisión determinístico que qa-validator sigue para:
- Clasificar el cambio realizado (basado en archivos modificados)
- Determinar si requiere unit tests, E2E tests, ambos o ninguno
- Determinar si los tests existen, deben crearse o modificarse
- Seleccionar y cargar las skills apropiadas
ÁRBOL DE DECISIÓN PRINCIPAL
PASO 0: Build exitoso?
NO → Delegar a @code-writer con el error exacto (archivo, línea, mensaje).
Máx 2 intentos. NO auto-invocarse con task().
Si persiste → escalar a @decomposer.
SÍ → Continuar
PASO 1: Clasificar el cambio según archivos modificados
PASO 2: Para CADA tipo de test requerido:
- Verificar existencia
- Si no existe → Crear (delegar a @code-writer)
- Si existe → Ejecutar
- Si falla → Diagnosticar (distinguir fallo del test vs fallo de impl.)
- Máx 2 iteraciones por tipo de test
PASO 3: Reportar resultados consolidados
CLASIFICACIÓN DEL CAMBIO
Método de clasificación
Leer los archivos modificados (usando git diff --name-only o leyendo los archivos que se acaban de crear/modificar) y clasificar según estas reglas:
| Patrón en archivos modificados | Clasificación | Tests requeridos |
|---|---|---|
*.html, *.scss, *.css (solo plantilla/estilos) |
[solo-plantilla] |
Solo build ✓ |
*.service.ts, *.pipe.ts, *.directive.ts, *.guard.ts |
[servicio-lógica] |
Unit tests |
*.component.ts + *.html (cambios UI) |
[componente-visual] |
Unit tests + E2E |
canvas, requestAnimationFrame, game-loop en archivos |
[game-loop-canvas] |
Unit tests + E2E |
*.config.ts, *.json, *.env, angular.json |
[config/infra] |
Solo build ✓ |
*.routes.ts, app.routes.ts, router-related |
[ruteo-navegación] |
E2E tests |
*.store.ts, state, signal() en servicios |
[data-flow] |
Unit tests |
| No se puede clasificar (default) | [no-clasificado] |
Unit tests + E2E (conservador) |
| Sin cambios (lectura/no-op) | [sin-cambio] |
Solo build ✓ |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 189 lines · 48 tokens per session scan A 8d06bf70cc69
qa-decision-engine is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,011 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest. Covers unit tests, UI tests, async testing, test architecture.
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
prd-auto-test-loop
A testing workflow driven by a product requirements document (PRD), which describes what a software version should do. It turns acceptance criteria into unit, integration, and end-to-end tests, then records the plan and results.
test-automation-expert
Comprehensive test automation specialist covering unit, integration, and E2E testing strategies. Expert in Jest, Vitest, Playwright, Cypress, pytest, and modern testing frameworks. Guides test pyramid design, coverage optimization, flaky test detection, and CI/CD integration. Activate on 'test strategy', 'unit tests'…