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.
npx skills add MauricioPerera/KDD --skill kdd-definirgit clone --depth 1 https://github.com/MauricioPerera/KDDWrote 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/skills/mauricioperera/kdd/kdd-definir)<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-definir"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-definir/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/skills/mauricioperera/kdd/kdd-definir"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-definir.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 | $0.00096 | $0.01333 |
| Opus 5 | $0.00048 | $0.00666 |
| Sonnet 5 | $0.00019 | $0.00267 |
| Haiku 4.5 | $0.00010 | $0.00133 |
Grade A, and why
kdd-definir 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 11d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEFINIR (KDD): cerrar la definicion de un proyecto antes de PLAN
knowledge/metodologia-ejecucion.md arranca en PLAN, que asume que ya
existe un "pedido" convertible en tareas atomicas. Esta skill cubre el
paso anterior: cuando el proyecto todavia no esta elegido, o esta elegido
pero su forma (arquitectura, alcance, stack) todavia no cerro. Sin este
paso, un usuario sin idea clara termina escribiendo el primer task
contract sobre una base que cambia por debajo a las dos tareas.
Que produce
Un unico artefacto: DEFINITION.md en la raiz del proyecto (plantilla:
TEMPLATE-DEFINITION.md). Estructura fija (no se cambia salvo pedido
explicito del usuario):
- Que es — una frase.
- Arquitectura (si aplica) — componentes y como se comunican entre si; si hay un core reusable + interfaces/pieles, decirlo asi de explicito.
- Capacidades objetivo — sin fasear salvo que el usuario lo pida.
- Por que es un caso valido / motivacion real — que problema resuelve y para quien, no solo "sirve para probar el metodo".
- Fuera de alcance — explicito, en negativo (que decisiones NO se toman aca porque son de implementacion).
Reglas duras
- NUNCA escribas codigo de produccion, ni contratos CCDD, ni
specs/CONTRACT-NN-*.md. Eso es de otra fase, con otro proceso (oraculo congelado por tarea, delegacion a un agente efimero). - NUNCA inventes el proyecto por el usuario. Si no tiene idea, propone 2-3 candidatos CONCRETOS anclados en lo que sabes de sus intereses o restricciones reales -- nunca ideas genericas de relleno.
- Si el usuario menciona una restriccion real (ej. "esto es de un cliente, no lo puedo usar de ejemplo", "esto lo hice solo porque podia, no porque lo necesitaba") tratala como restriccion dura para el resto de la conversacion -- no la ignores ni la repitas.
- NUNCA asumas una decision de arquitectura o stack cuando hay mas de una opcion razonable con tradeoffs reales. Presenta las opciones CON el tradeoff concreto de cada una (que se gana, que se pierde o rompe), nunca una lista neutra sin postura.
- Cuando una pregunta del usuario revela una decision de arquitectura implicita (ej. "puedo agregar X tambien?"), explicitala como tal -- nombra la decision, muestra las consecuencias concretas de cada camino -- antes de que el usuario elija, no despues.
- Pregunta una decision genuina a la vez (o un batch corto si son independientes entre si) -- nunca un cuestionario largo de una vez.
- Cuando el usuario dice "cerremos la definicion" (o equivalente):
sintetiza TODO lo discutido en el
DEFINITION.md, sin agregar nada nuevo que no se haya hablado en la conversacion. Confirma que cerro antes de darlo por terminado.
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.
- 11d ago First seen · 100 lines · 96 tokens per session scan A 1b2e7db38271
kdd-definir is a skill published in the GitHub repository MauricioPerera/KDD (7 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,333 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 2026-08-31.
Other skills, from other repositories
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
trio-omnigent
Run the Cursor-backed Omnigent Trio loop from the current Claude/Codex UI session when the user explicitly says “Trio Omnigent”, “Omnigent Trio”, or invokes /trio-omnigent. Do not use for an ordinary native Trio request.
trio-bridge
Suggest background Trio work by scanning a project and writing deduplicated proposal cards into proposals/.
research-a-evolve
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and ...