Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Quinoto-Tech/QuinotoSpecnpx agentmods add skills/quinoto-tech/quinotospec/quinotospec-create-proposalWrote 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/quinoto-tech/quinotospec/quinotospec-create-proposal)<a href="https://agentmods.dev/skills/quinoto-tech/quinotospec/quinotospec-create-proposal"><img src="https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-create-proposal/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/quinoto-tech/quinotospec/quinotospec-create-proposal"><img src="https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-create-proposal.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 | $0.00011 | $0.03459 |
| Opus 5 | $0.00005 | $0.01729 |
| Sonnet 5 | $0.00002 | $0.00692 |
| Haiku 4.5 | $0.00001 | $0.00346 |
Grade A, and why
quinotospec-create-proposal 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 3d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Create Proposal
Analiza exhaustivamente la información del Discovery (.quinoto-spec/discovery/), poniendo atención especial a 01-stack-profile.md para adaptar la arquitectura y el código al stack del proyecto, y a 08-product-and-agreements.md para alinear la propuesta con la visión de producto y los acuerdos de trabajo (DoR/DoD). También revisa otras propuestas existentes en .quinoto-spec/proposals/ para asegurar consistencia global y detectar posibles conflictos o solapamientos de alcance (mismos archivos, dominios o flujos afectados); si detectas alguno, documéntalo al inicio de la propuesta bajo **⚠️ Conflictos Detectados:**.
El objetivo es generar una Propuesta Técnica específica para: "{{PROPOSAL_DESCRIPTION}}".
Flags:
--party [agents]: Ejecuta Party Mode con los agentes especificados ANTES de generar la propuesta. El debate multi-agente enriquece la propuesta con perspectivas cruzadas. Si no se especifican agentes, se auto-seleccionan los mas relevantes segun el tema.--party-output <path>: Donde guardar la transcripcion del Party Mode (default:.quinoto-spec/proposals/{{DATE_PREFIX}}-{{PROPOSAL_SLUG}}/party-analysis.md)
PROPOSAL_NAME: deriva un nombre a partir de PROPOSAL_DESCRIPTION. Debe estar en español o inglés técnico, en Title Case, descriptivo y conciso (ej. Rewards Stabilization, Payment Timeout Fix, Refactor Auth Layer).
PROPOSAL_SLUG: derivar de PROPOSAL_NAME en lowercase con palabras separadas por guión (ej. rewards-stabilization, payment-timeout-fix).
DATE_PREFIX: fecha actual en formato YYYYMMDD.
Tu objetivo es generar una Propuesta Técnica específica para este tema, INTEGRADA con el resto del sistema.
Paso Previo — Validación de Acuerdos de Producto (BLOQUEANTE):
- Lee
.quinoto-spec/discovery/08-product-and-agreements.md. - Si el archivo NO existe, contiene únicamente los títulos/placeholders originales, o está vacío de contenido sustantivo → DETÉN LA EJECUCIÓN INMEDIATAMENTE. No avances a los pasos siguientes ni generes ningún archivo.
- Notifica al usuario exactamente:
"No puedo crear la propuesta porque no se han definido los Acuerdos de Producto (DoR/DoD) en
.quinoto-spec/discovery/08-product-and-agreements.md. Por favor complétalo primero (o indícame explícitamente que quieres continuar sin ellos como excepción documentada)." - Solo continúa al Paso 0 si el archivo tiene Definition of Ready (DoR) y Definition of Done (DoD) definidas con contenido real, o si el usuario confirmó explícitamente un override tras la advertencia anterior (en ese caso, documentar la excepción en
proposal.mdbajo**⚠️ Excepción DoR/DoD:**con el motivo dado por el usuario).
Paso Previo (opcional) — Gate de Mimir (evitar duplicar decisiones):
Si existe .quinoto-spec/mimir/index.json (generado por quinotospec-mimir), ejecuta:
python3 agent-dist/skills/quinotospec-mimir/search.py --root . "{{PROPOSAL_DESCRIPTION}}" --cite
Si el resultado top1 tiene score > 2.5 y cita una decisión previa (proposal.md o delta-specs/) potencialmente contradictoria o redundante con {{PROPOSAL_DESCRIPTION}}, advierte al usuario antes de continuar:
"⚠️ Decisión similar encontrada: {{PREFIX}} — {{cita textual}} ({{file:line}}). ¿Querés continuar con una propuesta nueva o preferís un MODIFIED sobre la decisión existente?"
No es bloqueante — si no hay índice (--check falla o el archivo no existe), continúa sin advertencia. El usuario puede confirmar que la propuesta nueva es intencional y seguir adelante.
Paso 0 — Party Mode (opcional, solo si --party):
Si el usuario paso el flag --party, ejecuta Party Mode ANTES de generar la propuesta:
- Resolver agentes:
- Si
--partyincluye lista de agentes (ej.--party architect,security-auditor), usar esos. - Si
--partyse paso sin agentes, auto-seleccionar 2-4 agentes basado enPROPOSAL_DESCRIPTION:- Propuestas de arquitectura → architect, devops-engineer, performance-optimizer
- Propuestas de seguridad → security-auditor, architect, devops-engineer
- Propuestas de refactor → refactor-specialist, test-writer, code-reviewer
- Propuestas de features → architect, test-writer, security-auditor
- Sin clasificar → architect, security-auditor, test-writer (default)
- Si
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.
- 3d ago Changed · +19 lines a94db4d5e324
- 12d ago First seen · 177 lines · 11 tokens per session scan A db25bed8c08b
quinotospec-create-proposal is a skill published in the GitHub repository Quinoto-Tech/QuinotoSpec (20 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 3,459 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 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
aws-sdk-java-v2-core
Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…