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/LeandroPG19/MemorysWrote 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/leandropg19/memorys/governance)<a href="https://agentmods.dev/rules/leandropg19/memorys/governance"><img src="https://agentmods.dev/badge/rules/leandropg19/memorys/governance/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/leandropg19/memorys/governance"><img src="https://agentmods.dev/badge/rules/leandropg19/memorys/governance.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 | $0.00897 | $0.00897 |
| Opus 5.5 | $0.00359 | $0.00359 |
| Sonnet 5.5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
governance 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 22d 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.
Gobernanza (MemoryIndustry)
0. Antes de tocar nada
- Memoria:
cuba_faro/cuba_expediente(MCPcuba_*; aliasmemory_*). - Leer lo que ya existe. Buscar el handler, el contrato o el guion antes de escribir uno nuevo.
- Prueba de sobre-ingeniería (§1). Si no pasa, se recorta antes de escribir.
1. Sobre-ingeniería: lo que NO se escribe
¿Qué se podría borrar y el programa seguiría haciendo lo pedido? Eso no se escribe.
- Una abstracción con un solo llamante es una capa.
- Cero configuración para lo que nunca varía.
- Cero dependencia nueva si std lo resuelve en veinte líneas.
- Cero fichero nuevo si cabe donde ya vive lo parecido.
- Cero manejo de errores especulativo.
- Cero código para un futuro hipotético.
- Cero refactor de paso.
- Cero envoltorio que solo renombra.
Comentarios: el PORQUÉ se queda
Este repo no es «cero comentarios». Los comentarios de migraciones, gate, RLS y contratos son load-bearing: un SHA y un include_str! los leen.
- Un comentario que dice QUÉ hace la línea sobra. Se renombra.
- Lo que merece comentario es el PORQUÉ: la decisión rara, el bug que obliga, el número medido.
- Cero código comentado. Cero TODO sin dueño.
- Un comentario que contradice al código es peor que ninguno.
- No aplicar
rust.mdcgenérico ni «cero comentarios en.rs» de Mapupita-Rust.
2. El CI es la puerta
Un comando replica el CI: ./scripts/merge-gate.sh (alias ./scripts/como-el-ci.sh todo).
scripts/quality-gate.shes el segundo juez (CRAP/mutación del diff). Se encadena; no sustituye al SIL.- Nada se declara mergeable sin haber corrido el SIL en este turno.
- El gate imprime lo que NO mira.
- Un test saltado no es un test verde.
- Un verificador que no puede fallar no es una comprobación.
3. Identidad y stack
- Mapupita / Leandro — MCP, memoria de agentes, Rust.
- Hablar en español; código, commits, PRs y docs de producto en inglés (salvo comentarios de lección en el gate).
- Stack de este árbol: Rust edición 2024, PostgreSQL 18 + pgvector, MCP
cuba_*. - Doctrina: integridad transaccional, tipos estrictos, errores manejados. Aquí el daño no es físico de planta: es un agente que recuerda mal o filtra el tenant.
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.
- 22d ago First seen · 82 lines · 897 tokens per session scan A a7f0dd1a9fbb
governance is a cursor rule published in the GitHub repository LeandroPG19/Memorys (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 897 tokens to every session, about $0.0036 per session on Opus 5.5. 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 2026-09-24.
Other cursor rules, from other repositories
frontend-css
Cursor rule "frontend-css" from tomasz-tomczyk/crit, covering css rules, responsive & touch and selectors.
review-pr-against-issue
Workflow for reviewing a PR against the GitHub issue it claims to fix, including fetching PRs when gh CLI can't reach github.com.
grug-brained-dev_avoid-abstractions
Don't create abstractions until you have multiple concrete examples.
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.