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.
git clone --depth 1 https://github.com/josemerca/mercadona-user-story-toolkitWrote 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/commands/josemerca/mercadona-user-story-toolkit/pipeline)<a href="https://agentmods.dev/commands/josemerca/mercadona-user-story-toolkit/pipeline"><img src="https://agentmods.dev/badge/commands/josemerca/mercadona-user-story-toolkit/pipeline/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/commands/josemerca/mercadona-user-story-toolkit/pipeline"><img src="https://agentmods.dev/badge/commands/josemerca/mercadona-user-story-toolkit/pipeline.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 | $0.00026 | $0.02239 |
| Opus 5 | $0.00013 | $0.01120 |
| Sonnet 5 | $0.00005 | $0.00448 |
| Haiku 4.5 | $0.00003 | $0.00224 |
Grade A, and why
pipeline 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 12d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paso 0 (obligatorio): Cargar ground-rules. Antes de proceder, lee
shared-config.mdy aplica:
- §Filosofía del Plugin — modo copiloto, NO inventar, preguntar antes de generar
- §Estilo de Escritura — frases ≤30 palabras, sin adjetivos sin datos, NUNCA inventar métricas
- §Antipatrones Compartidos — los 7 antipatrones a detectar
Si no puedes leer el fichero, detén la ejecución y reporta el problema.
Pipeline orquestado por sub-agentes
Este comando funciona como orquestador. No carga las SKILLs en su propio contexto: delega cada paso pesado a un sub-agente fresco vía la herramienta Agent (Task). El orquestador conserva sólo la ruta elegida, los artefactos intermedios y los CHECKPOINTs con el usuario.
Por qué: un solo modelo cargando 8 SKILLs + PRD + entrevistas + JTBDs + stories + scoring entra en distracted-agent (Lada Kesseler). El dispatch a sub-agente acota cada paso a su SKILL y devuelve sólo el artefacto, no el chain-of-thought.
Selección de ruta (orquestador, no se delega)
Preguntar al PM:
¿Qué tipo de documento tienes como punto de partida?
- PRD — Documento con problema, solución, métricas, scope
- GSD — Proyecto con
.planning/de Get Shit Done- Sin documento — Empezar desde cero con guía conversacional
| Ruta | Secuencia |
|---|---|
| A: PRD | prd-quality-guard → research → [entrevistas] → analyze-research → stories → validate-stories → split-stories → prioritize |
| B: GSD | from-gsd → [completar GAPs] → prd-quality-guard → research → [entrevistas] → analyze-research → stories → validate-stories → split-stories → prioritize |
| C: Sin doc | build-story → validate-stories → split-stories → prioritize |
Cómo dispatchar un paso (contrato)
Para cada paso del pipeline, usa la herramienta Agent con:
- subagent_type:
general-purpose - description: nombre corto del paso (ej.
"PRD quality gate") - prompt: bloque autocontenido con:
- Qué
SKILL.mdcargar (ruta absoluta dentro del plugin) - Input concreto (fichero, contenido pegado, JTBDs serializados, etc.)
- Output esperado (artefacto puntual, sin razonamiento intermedio)
- Recordatorio del modo copiloto y prohibición de inventar
- Qué
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.
- 12d ago First seen · 158 lines · 26 tokens per session scan A 29513e666f1f
pipeline is a command published in the GitHub repository josemerca/mercadona-user-story-toolkit (25 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 2,239 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.