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/doncheli/don-cheli-sddWrote 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/doncheli/don-cheli-sdd/detectar-ambiguedad)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/detectar-ambiguedad"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/detectar-ambiguedad/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/doncheli/don-cheli-sdd/detectar-ambiguedad"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/detectar-ambiguedad.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 | $0.00016 | $0.00800 |
| Opus 5 | $0.00008 | $0.00400 |
| Sonnet 5 | $0.00003 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
detectar-ambiguedad 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:detectar-ambiguedad
Objetivo
Escanear specs en busca de ambigüedades, contradicciones, requisitos implícitos y campos faltantes. Va más allá de la clarificación básica — es un análisis exhaustivo de la calidad de la spec.
Basado en la práctica de MELI: "La ambigüedad es el bottleneck #1 del AI coding."
Uso
/dc:detectar-ambiguedad @specs/features/<dominio>/<Feature>.feature
/dc:detectar-ambiguedad --todos # Escanear todas las specs activas
Qué Detecta
1. Ambigüedades Lingüísticas
- Pronombres sin referente claro ("esto se envía", "eso se valida")
- Cuantificadores vagos ("algunos", "varios", "muchos")
- Verbos pasivos sin sujeto ("será procesado", "se debe validar")
2. Contradicciones Internas
- Escenario A dice "email obligatorio", Escenario B no lo valida
- Plan dice "async", tasks dice "sync"
- Schema dice
NOT NULL, spec no tiene escenario de validación
3. Requisitos Implícitos No Documentados
- "El usuario se registra" → ¿Qué pasa con confirmación por email?
- "Se guarda en BD" → ¿Qué campos son obligatorios?
- "Se envía notificación" → ¿A quién? ¿Cuándo? ¿Cómo?
4. Gaps de Cobertura
- Happy path sin sad path correspondiente
- Campos en DBML sin validación en Gherkin
- Endpoints sin manejo de errores
Output
=== Análisis de Ambigüedad ===
Feature: GestionarPedidos.feature
Score de Claridad: 72/100
## 🔴 Contradicciones (3)
1. Línea 15: "el pedido se crea" vs Línea 42: "el pedido requiere aprobación"
→ ¿Se crea directo o necesita aprobación?
2. Línea 23: campo "estado" acepta "activo" vs DBML: enum no incluye "activo"
3. Escenario 3 y Escenario 7 usan distinto formato de fecha
## 🟡 Ambigüedades (5)
1. Línea 8: "se notifica al usuario" → ¿email? ¿push? ¿in-app?
2. Línea 31: "se valida el pago" → ¿qué proveedor? ¿qué criterios?
3. Línea 45: "datos del cliente" → ¿cuáles exactamente?
4. Línea 52: "en tiempo razonable" → ¿cuánto es razonable?
5. Línea 67: "se procesa" → ¿quién? ¿cuándo? ¿cómo?
## 🟢 Requisitos Implícitos Detectados (2)
1. No hay escenario para cancelar pedido después de pago
2. No hay manejo de timeout en validación de pago
## Recomendaciones
- Resolver contradicciones ANTES de avanzar a fase Plan
- Score mínimo recomendado: 85/100
- Score actual: 72/100 → NO AVANZAR
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.
- 7d ago First seen · 82 lines · 16 tokens per session scan A 03dfdcd2927f
detectar-ambiguedad is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 800 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 2026-09-03.
Other commands, from other repositories
forensics
Post-mortem investigation for failed or stuck workflows. Analyzes git history and planning artifacts.
audit-fix
Run audit, prioritize findings, auto-fix via quick tasks, test, and commit.
debug
Systematic debugging with hypothesis testing. Persistent across sessions.
scan
Analyze an existing codebase. Maps structure, architecture, conventions, and concerns.
optimize
Suggest concrete performance improvements for the given file or directory.
fix-issue
A command that takes a GitHub Issue—a tracked bug, request, or question—and guides its fix from investigation through testing and submission. TDD means writing a failing test first, then changing the code until the test passes.