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/spec-score)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/spec-score"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/spec-score/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/spec-score"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/spec-score.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 | $0.00102 | $0.02161 |
| Opus 5 | $0.00051 | $0.01081 |
| Sonnet 5 | $0.00020 | $0.00432 |
| Haiku 4.5 | $0.00010 | $0.00216 |
Grade A, and why
spec-score 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 5d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:spec-score
Objetivo
Evaluar la calidad de una especificación con una puntuación cuantitativa de 0 a 100, usando 8 métricas ponderadas. Compara contra los estándares IEEE 830 e ISO 29148. Produce un informe con radar chart descriptivo y tabla de desglose accionable.
Uso
/dc:spec-score # Evaluar spec del proyecto actual
/dc:spec-score @docs/specs/checkout/spec.md # Evaluar un archivo específico
/dc:spec-score --historia US-042 # Evaluar una historia de usuario
/dc:spec-score --umbral 80 # Cambiar umbral de aprobación
/dc:spec-score --comparar main # Comparar contra versión en main
/dc:spec-score --formato ejecutivo # Reporte simplificado para PMs
Las 8 Métricas
| # | Métrica | Peso | Descripción |
|---|---|---|---|
| 1 | Completitud | 15% | ¿Cubre todos los escenarios? ¿Tiene happy path + edge cases? |
| 2 | Medibilidad | 15% | ¿Los criterios de aceptación son verificables y cuantificables? |
| 3 | Ausencia de ambigüedad | 15% | ¿Usa lenguaje preciso? ¿Evita "rápido", "fácil", "adecuado"? |
| 4 | Testeabilidad | 15% | ¿Se puede escribir un test automatizado para cada criterio? |
| 5 | Consistencia | 12% | ¿Contradice otras specs del sistema? ¿Usa terminología uniforme? |
| 6 | Atomicidad | 12% | ¿Cada requisito expresa una sola cosa? ¿Sin requisitos compuestos? |
| 7 | Trazabilidad | 8% | ¿Tiene ID único? ¿Referencia al objetivo de negocio que lo origina? |
| 8 | Independencia | 8% | ¿Puede implementarse sin depender de specs aún no definidas? |
Umbrales de Calidad
| Rango | Nivel | Acción |
|---|---|---|
| 90-100 | Excelente | Lista para implementar |
| 80-89 | Buena | Revisar observaciones menores |
| 60-79 | Necesita trabajo | Corregir antes de implementar |
| 0-59 | Rechazada | Reescribir con /dc:especificar |
Comportamiento
-
Cargar spec del archivo o historia indicada
-
Evaluar cada métrica (0-100 por métrica):
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.
- 5d ago First seen · 190 lines · 0 tokens per session scan A af56e47ca58f
spec-score is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 102 tokens to every session and 2,161 once invoked, about $0.0005 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
review
Verify the build matched the plan. Automated checks + walkthrough with you.
test
Generate tests for completed phase code. Detects test framework and targets key files.
validate-phase
Post-build quality gate. Identifies test gaps and spawns nyquist-auditor to fill them.
verify-work
Validate built features through conversational UAT.
test
A command for running a project's automated tests, which are checks that software behaves as expected. It detects common project types and chooses a matching test command.
qa
A quality-assurance testing agent that checks whether software meets its stated acceptance requirements. It tests normal use, edge cases, failures, and regressions, then classifies the problems it finds.