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-okf-ccdd-hybridgit 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-okf-ccdd-hybrid)<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-okf-ccdd-hybrid"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-okf-ccdd-hybrid/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-okf-ccdd-hybrid"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-okf-ccdd-hybrid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.01666 |
| Opus 5 | $0.00062 | $0.00833 |
| Sonnet 5 | $0.00025 | $0.00333 |
| Haiku 4.5 | $0.00012 | $0.00167 |
Grade A, and why
kdd-okf-ccdd-hybrid 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 12d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge-Driven Development (KDD): OKF + CCDD
Esta skill establece las reglas obligatorias al definir tareas de desarrollo utilizando la metodología híbrida. El objetivo es que los contratos no sean documentos aislados, sino nodos vivos de la base de conocimiento OKF que controlan determinísticamente a los agentes efímeros.
1. El Contrato es un Nodo OKF
Todo Task Contract CCDD que se escriba (p.ej. implementar_login.md) debe comenzar estrictamente con un Frontmatter YAML válido.
2. Fusión de Metadatos (Frontmatter)
El Frontmatter debe unificar los campos requeridos por ambas metodologías:
- OKF Fields:
type(debe ser'Task Contract'),title,description,tags. - CCDD Fields:
task,intent,target,signature,test_command,budget,tests,tests_sha256,deps_allowed.
Ejemplo:
---
type: 'Task Contract'
title: 'Implementar verify_user'
description: 'Función pura para validación de ID.'
tags: ['ccdd', 'auth']
task: verify_user
intent: "Implementar la validación..."
target: verify_user.py
signature: "def verify_user(id: str) -> bool:"
test_command: "python -m unittest verify_test.py"
budget:
max_cyclomatic_complexity: 4
tests: "verify_test.py"
tests_sha256: "a1b2c3d4e5f6..."
---
3. Contexto Interconectado (Enlaces OKF)
Para proveer el contexto del negocio y diseño a los agentes efímeros sin abrumarlos, está prohibido duplicar reglas de negocio de manera verbosa en el contrato.
En lugar de eso, en secciones como ## Intent, ## Interface, o ## Constraints, se DEBE usar un enlace de Markdown relativo hacia los nodos de OKF relevantes (arquitectura, modelos de datos).
- DO: "Validar formato contra
knowledge/data_models/users_table.md" - DON'T: "La tabla de usuarios tiene un uuid, un email, un password, y una fecha de creación, y su ID es un string de 36 caracteres..."
4. Validación Continua Obligatoria (dos niveles)
Antes de dar un contrato por terminado o pasárselo a un agente efímero, debes validarlo. La referencia canónica completa (niveles 1 y 2, gate multi-lenguaje, export para el gate) está en knowledge/validacion.md — esta skill no la duplica. Resumen: nivel 1 (obligatorio) = python scripts/validate_contracts.py knowledge/contracts (incluye el sello tests_sha256; sellar con --hash) + python scripts/validate_specs.py specs + python scripts/validate_okf.py knowledge (estructura/frontmatter de nodos OKF) + python scripts/lint_ascii.py scripts + python scripts/validate_rules.py <dir> (rule contracts, capa opcional) + python scripts/validate_skills.py skills .agents/skills (skills de agente, capa opcional) + python scripts/validate_changelog.py (coherencia CHANGELOG↔reportes, capa opcional) + python scripts/validate_ux_page.py examples/ux-page (UX/accesibilidad mecanica sobre paginas HTML autocontenidas, capa opcional) + python scripts/validate_diagrams.py <dir> (diagramas Mermaid flowchart verificados contra un .diagram-contract.json declarativo, capa opcional) + python scripts/validate_test_commands.py <contracts_dir> <repo_root> (corre el test_command real de cada contrato y falla si algun exit code no es 0, Nivel 1 obligatorio) + python scripts/scan_secrets.py <dir> (escaneo determinista de credenciales filtradas por prefijo de proveedor conocido, capa opcional) + test_command en verde, local y en CI (matriz dual-OS, suite 2x); nivel 2 (opcional) = gate CCDD vía MCP ccdd-complexity (lint_task_contract, run_integration_gate). Sin gate disponible, el nivel 1 basta para considerar el contrato válido.
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.
- 12d ago First seen · 68 lines · 123 tokens per session scan A 2ca34b55e83a
kdd-okf-ccdd-hybrid is a skill published in the GitHub repository MauricioPerera/KDD (8 stars, last pushed 3d ago), licensed MIT. It adds 123 tokens to every session and 1,666 once invoked, about $0.0006 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-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.
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.
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 ...