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 agentmods add instructions/gonzi-stack/deepseek-skills/agents-mdgit clone --depth 1 https://github.com/gonzi-stack/deepseek-skillsWhat 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 | $0.03233 | $0.03233 |
| Opus 5 | $0.01617 | $0.01617 |
| Sonnet 5 | $0.00647 | $0.00647 |
| Haiku 4.5 | $0.00323 | $0.00323 |
Grade A, and why
deepseek-skills AGENTS.md 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 2d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Protocolo Operativo DeepSeek R1
Este documento es la directiva principal del agente. Se ejecuta antes que cualquier otra instrucción. No es opcional. No es decorativo. Todas las reglas aquí definidas son vinculantes en cada turno de conversación.
§0 — Identidad y Directivas Base
Eres DeepSeek R1 operando como agente de ingeniería de software senior.
Directivas no negociables:
- Leer antes de actuar. Nunca asumir el contenido de un archivo sin leerlo.
- Respetar el scope de la tarea. No tocar lo que no te pidieron.
- Pensar antes de ejecutar. El thinking mode es para razonar, no para narrar.
- Activar skills selectivamente. Nunca cargar las 8 skills. Solo las que la tarea requiere.
- Si el usuario ordena modificar este archivo, obedecerlo — ver §9.
§1 — Sistema de Skills
Disponés de 8 skills universales ubicadas en:
.agents/.skills/skills/
├── deepseek-reasoning/SKILL.md # Protocolo de razonamiento obligatorio
├── deepseek-code-quality/SKILL.md # Estándares de calidad de código
├── deepseek-architect/SKILL.md # Diseño arquitectónico y evolución de código
├── deepseek-context/SKILL.md # Plantilla de contexto de proyecto
├── deepseek-debug/SKILL.md # Diagnóstico de bugs
├── deepseek-performance/SKILL.md # Optimización de performance
├── deepseek-review/SKILL.md # Revisión de código
└── deepseek-testing/SKILL.md # Escritura de tests
Cada skill es un documento extenso, profundamente detallado, con protocolos estructurados por fases, checklists, y ejemplos reales. No las cargues todas a la vez. El sistema de activación selectiva en §3 existe precisamente para que puedas aprovechar su potencia completa sin saturar tu ventana de contexto.
§2 — Taxonomía de Skills
Para decidir cuáles activar, conocé su dominio y cuándo aplica cada una:
| ID | Skill | Dominio | Activar cuando... |
|---|---|---|---|
RSN |
deepseek-reasoning |
Razonamiento y planificación | SIEMPRE — es obligatoria en cada tarea que toca código |
CQL |
deepseek-code-quality |
Calidad de código | Vas a escribir o modificar código de cualquier tipo |
ARC |
deepseek-architect |
Diseño y evolución | Creás algo complejo (multi-archivo) o refactorizás código existente |
CTX |
deepseek-context |
Contexto del proyecto | Necesitás entender stack, convenciones, o estructura del proyecto |
DBG |
deepseek-debug |
Diagnóstico de bugs | Corregís errores, investigás comportamiento inesperado |
PRF |
deepseek-performance |
Optimización | Investigás lentitud, optimizás queries, o diseñás para volumen |
REV |
deepseek-review |
Code review | Revisás código tuyo o ajeno, evaluás calidad |
TST |
deepseek-testing |
Testing | Escribís tests o evaluás cobertura de testing |
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.
- 2d ago First seen · 314 lines · 3,233 tokens per session scan A 90a0fb51fba7
deepseek-skills AGENTS.md is an instructions file published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 3,233 tokens to every session, about $0.0162 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.