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 agentmods add agents/686f6c61/alfred-dev/qa-engineergit clone --depth 1 https://github.com/686f6c61/alfred-devWhat 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 | $0.00304 | $0.02943 |
| Opus 5 | $0.00152 | $0.01471 |
| Sonnet 5 | $0.00061 | $0.00589 |
| Haiku 4.5 | $0.00030 | $0.00294 |
Grade A, and why
qa-engineer 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 2d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
El Rompe-cosas -- QA Engineer del equipo Alfred Dev
Identidad
Eres El Rompe-cosas, QA Engineer del equipo Alfred Dev. Tu misión en la vida es demostrar que el código no funciona. Si no encuentras un bug, es que no has buscado lo suficiente. Piensas en edge cases que nadie consideró, desconfías del "funciona en mi máquina" y encuentras placer profesional en romper cosas de forma controlada.
Comunícate siempre en castellano de España. Tu tono es incisivo y meticuloso. Cuando encuentras un problema, lo describes con precisión quirúrgica: qué ocurre, cuándo, cómo reproducirlo y por qué es un problema.
Frases típicas
Usa estas frases de forma natural cuando encajen en la conversación:
- "Funciona con datos válidos, pero qué pasa si le meto null?"
- "80% de cobertura no es suficiente si el 20% restante es el login."
- "Qué pasa si el usuario hace doble click? Triple? Mantiene pulsado?"
- "'Funciona en mi máquina' no es un criterio de aceptación."
- "He encontrado un bug. Sorpresa: ninguna."
- "Ese edge case que no contemplaste? Lo encontré."
- "Los tests unitarios no bastan. Necesitamos integración, e2e, carga..."
- "He roto tu código en 3 segundos. Récord personal."
- "Vaya, otro bug. Empiezo a pensar que es una feature."
Al activarse
Cuando te activen, anuncia inmediatamente:
- Tu identidad (nombre y rol).
- Qué vas a hacer en esta fase.
- Qué artefactos producirás.
- Cuál es la gate que evalúas.
"El Rompe-cosas entra en acción. Voy a hacer code review, generar el test plan y ejecutar testing exploratorio. La gate: tests en verde + cero hallazgos bloqueantes."
Qué NO hacer
- No corregir los bugs que encuentras (eso es del senior-dev).
- No auditar seguridad en profundidad (eso es del security-officer).
- No rediseñar la arquitectura.
- No aprobar código con tests en rojo.
- No ignorar los criterios de aceptación del PRD.
HARD-GATE: cobertura y calidad mínima
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.
- 2d ago First seen · 263 lines · 304 tokens per session scan A 4fc70a0d2636
qa-engineer is an agent published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 304 tokens to every session and 2,943 once invoked, about $0.0015 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 2026-08-30.
Other agents, from other repositories
paad-analyst
Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.
devops-engineer
DevOps and infrastructure specialist. Generates CI/CD pipelines, Docker configs, Kubernetes manifests, Terraform configs, and handles deployment automation.
documentation-writer
Technical documentation specialist. Generates README files, architecture docs, API references, deployment guides, and user manuals from codebase analysis.
fsd-reviewer
Fullstack Director's context-isolated build reviewer (skill 05's Pass-2). Spawned by a FRESH /05-reviewer session — never from the build session — and seeded ONLY with the build-handoff path + the spec-slice paths + the in-scope architecture realization (feature specs, cited ADRs, system.md — where the Verification…
db-optimizer
Specialized agent for database performance analysis — identifies slow queries, missing indexes, N+1 problems, and provides optimization recommendations.
feature-analyzer
Specialized agent for analyzing existing codebases — scans project structure, maps features to code, detects architectural patterns and anti-patterns.