Borrowing it
Nothing to install: this file belongs to gonzi-stack/deepseek-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gonzi-stack/deepseek-skills/main/.agents/.skills/skills/deepseek-reasoning/SKILL.mdgit clone --depth 1 https://github.com/gonzi-stack/deepseek-skillsWrote 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/gonzi-stack/deepseek-skills/deepseek-reasoning)<a href="https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-reasoning"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-reasoning.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.02586 |
| Opus 5 | $0.00037 | $0.01293 |
| Sonnet 5 | $0.00015 | $0.00517 |
| Haiku 4.5 | $0.00007 | $0.00259 |
Grade A, and why
deepseek-reasoning 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Reasoning Protocol — Universal
Este documento es ejecutable, no decorativo. Cada sección es un checkpoint que debes completar mentalmente antes de avanzar. No puedes saltar checkpoints. No puedes escribir código antes de completar Phase 0, 1 y 2.
PHASE 0 — Task Intake (antes de leer cualquier archivo)
0.1 ¿Qué me están pidiendo exactamente?
Escribe en una oración la tarea concreta. Si no podés escribirla en una oración, la tarea es ambigua — pedí aclaración antes de continuar.
- Correcto: "Crear
src/services/payments.tscon una funciónprocessRefund." - Incorrecto: "Mejorar el sistema de pagos." → demasiado vago, pedir aclaración.
0.2 ¿Cuál es el output explícito esperado?
Lista los archivos que te pidieron crear o modificar. Estos son los únicos archivos que podés tocar.
Si la tarea no especifica archivos, dedúcelos de forma conservadora y confírmalos antes de actuar.
0.3 ¿Qué NO te pidieron pero te podría tentar tocar?
Identificá los archivos relacionados que podrían parecer que necesitan modificación. Escribilos bajo "FUERA DE SCOPE — NO TOCAR". Esta lista es un contrato.
Si durante la ejecución querés tocar uno de esos archivos, detente y reportá por qué en lugar de hacerlo.
Regla de oro del scope: Si la tarea dice "crear X", solo creás X. Si notás que Y necesita cambios para que X funcione, no modificás Y. Reportás: "Para que X funcione, Y necesita [descripción]. ¿Procedo?"
PHASE 1 — System Mapping (leer antes de planear)
1.1 Leer el proyecto antes de asumir nada
Antes de escribir una sola línea, entendé el proyecto:
- Leer el README o documentación principal si existe.
- Explorar la estructura de directorios — al menos 2 niveles de profundidad.
- Identificar el stack — lenguaje, framework, librerías principales, herramientas de build.
- Identificar los archivos de configuración críticos —
package.json,tsconfig.json,pyproject.toml,Makefile,.env.example, etc.
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 · 271 lines · 75 tokens per session scan A 7dc76a06edd0
deepseek-reasoning is a skill published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 2,586 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…