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/Mazalucas/El-DT-Lightweight-ArmyWrote 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/rules/mazalucas/el-dt-lightweight-army/16-numeric-grounding)<a href="https://agentmods.dev/rules/mazalucas/el-dt-lightweight-army/16-numeric-grounding"><img src="https://agentmods.dev/badge/rules/mazalucas/el-dt-lightweight-army/16-numeric-grounding/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/rules/mazalucas/el-dt-lightweight-army/16-numeric-grounding"><img src="https://agentmods.dev/badge/rules/mazalucas/el-dt-lightweight-army/16-numeric-grounding.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 | $0.00029 | $0.00895 |
| Opus 5 | $0.00015 | $0.00447 |
| Sonnet 5 | $0.00006 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
16-numeric-grounding 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confianza numérica (numeric grounding)
Fuente humana: docs/03_reference/numeric-verification-default.md (DOC-REF-009). Skill operativa: .cursor/skills/data-auditor/SKILL.md. Subagente: data-auditor. Command: /verificar.
Cuándo aplica
Siempre que la entrega incluya cifras derivadas de datos del usuario o del repo: sumas, promedios, porcentajes, totales, conteos, variaciones, proyecciones, reconciliaciones. Fuentes típicas: planillas (CSV/XLSX/TSV), reportes, tablas pegadas en el chat, exports de sistemas, dashboards.
No aplica a: números literales citados de una fuente sin transformación (citar la fuente), ejemplos ilustrativos marcados como tales, versiones/IDs/números de línea.
Regla de oro
La IA no calcula mentalmente. Todo cálculo sobre datos reales se ejecuta con código (script Python/Node u otra herramienta determinista) y se reporta el output real del script. Prohibido "estimar" un total leyendo una columna, por trivial que parezca.
Etiquetas de procedencia (obligatorias en tareas cuantitativas)
| Etiqueta | Significado |
|---|---|
[VERIFICADO] |
Salió de un script ejecutado en esta sesión; comando y output reproducibles |
[DERIVADO] |
Calculado a partir de cifras verificadas; la fórmula queda a la vista |
[NO VERIFICADO] |
Citado de una fuente sin recomputar, o sin runtime disponible para verificar |
Prohibido entregar cifras sin etiqueta cuando la tarea es cuantitativa.
Cross-checks mínimos
- Total vs. suma de partes — si hay fila/columna de totales, recomputarla y comparar.
- Conteo de filas — filas leídas vs. esperadas; detectar headers duplicados, filas vacías, duplicados.
- Tipos y unidades — moneda, separadores de miles/decimales, porcentajes, fechas; declarar la interpretación asumida.
- Discrepancias se reportan, nunca se "acomodan" — si los números no cierran, ese es el hallazgo principal de la entrega.
Modo degradado (sin runtime)
No asumir runtime: detectar qué hay disponible (python3 con pandas > python3 stdlib > node). Si no hay ninguno:
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.
- 6d ago First seen · 66 lines · 29 tokens per session scan A 3499255909f7
16-numeric-grounding is a cursor rule published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 895 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.