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 skills/veigap/talksmith/desrobotizarnpx skills add veigap/talksmith --skill desrobotizargit clone --depth 1 https://github.com/veigap/talksmithWrote 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/veigap/talksmith/desrobotizar)<a href="https://agentmods.dev/skills/veigap/talksmith/desrobotizar"><img src="https://agentmods.dev/badge/skills/veigap/talksmith/desrobotizar.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 | $0.00078 | $0.02209 |
| Opus 5 | $0.00039 | $0.01104 |
| Sonnet 5 | $0.00016 | $0.00442 |
| Haiku 4.5 | $0.00008 | $0.00221 |
Grade A, and why
talksmith:desrobotizar 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desrobotizar
Elimina los patrones predecibles de la escritura de IA en español.
Reglas núcleo
-
Corta las frases de relleno. Elimina aperturas de carraspeo, muletillas de énfasis, jerga corporativa y los adverbios en -mente. Ver references/frases.md.
-
Rompe las estructuras formuláicas. Nada de contrastes binarios ("no es X, sino Y"), listados negativos, fragmentación dramática, preguntas retóricas con respuesta inmediata, falsa agencia. Ver references/estructuras.md.
-
Usa voz activa con sujeto humano. Nada de voz pasiva ("fue decidido") ni de pasiva refleja que esconde al actor ("se decidió que..."). Nada de objetos inanimados haciendo verbos humanos ("la queja se convierte en solución"). Alguien decide, alguien arregla: nómbralo.
-
Sé específico. Nada de declarativas vagas ("las implicancias son profundas"). Nombra la cosa concreta. Nada de extremos perezosos ("todo", "siempre", "nunca", "nadie") haciendo trabajo vago.
-
Pon al lector en la escena. Nada de narrador flotando a la distancia. "Vos"/"tú" le gana a "la gente". Lo concreto le gana a lo abstracto.
-
Varía el ritmo. Mezcla largos de oración. Dos ítems le ganan a tres. Termina los párrafos de formas distintas.
-
Confía en el lector. Afirma directo. Sin suavizar, sin justificar cada frase, sin llevarlo de la mano.
-
Corta lo citeable. Si una frase suena a cita de póster motivacional, reescríbela.
-
Domestica el gerundio. Un gerundio por oración como máximo, y solo si expresa simultaneidad real. Nada de "logrando así", "permitiendo que", "generando un impacto".
-
Corta los conectores académicos en cadena. "Sin embargo", "no obstante", "por otro lado", "asimismo", "además" abriendo párrafo tras párrafo delatan a la máquina. Que las ideas se conecten solas.
-
Nunca em-dashes (—). Para un inciso usa el guion medio común (-), y siempre en par: se abre y se cierra ("el equipo - el de ventas - lo pidió"). Un inciso abierto con guion no puede quedar colgando hasta el punto.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 111 lines · 78 tokens per session scan A 16f81f1c1bf8
talksmith:desrobotizar is a skill published in the GitHub repository veigap/talksmith (10 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 2,209 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…