Borrowing it
Nothing to install: this file belongs to 0xAI-Builders/comandos. 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/0xAI-Builders/comandos/main/.claude/skills/comandos-remoto-y-escritorio/SKILL.mdgit clone --depth 1 https://github.com/0xAI-Builders/comandosWrote 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/0xai-builders/comandos/comandos-remoto-y-escritorio)<a href="https://agentmods.dev/skills/0xai-builders/comandos/comandos-remoto-y-escritorio"><img src="https://agentmods.dev/badge/skills/0xai-builders/comandos/comandos-remoto-y-escritorio/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/0xai-builders/comandos/comandos-remoto-y-escritorio"><img src="https://agentmods.dev/badge/skills/0xai-builders/comandos/comandos-remoto-y-escritorio.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01807 |
| Opus 5.5 | $0.00000 | $0.00723 |
| Sonnet 5.5 | $0.00000 | $0.00361 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
comandos-remoto-y-escritorio scanned grade A with 1 finding 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 28d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Y comprueba que el WebKit sirve la versión nueva (`curl -s http://127.0.0.1:4777/ | grep -o 'archivo.js?v=[0-9]*'`). How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComandOS: todo cambio va en remoto y en escritorio
Jesús usa ComandOS de dos formas y espera lo mismo en las dos:
- Escritorio:
bin/cc-app, una ventana GTK. A la izquierda un WebKit carga el tablero (http://127.0.0.1:4777/?app=1,inApp()es verdadero); a la derecha y debajo hay terminales VTE nativas contmux attach, con cabecera de pane y marcos pintados por cc-app (_attach_model_bar,_pane_frames,_refresh_tab_models). - Remoto: el mismo
dash/index.htmlen un navegador (móvil o la Mac) servido porbin/cc-dash;WEBTERMes verdadero y las terminales son ttyd en iframes que cargandash/term.htmlpor/term(cabecera y marcos de pane hechos en web,lib/terminal_panes.py).
Un cambio que solo existe en una versión se siente como un bug en la otra: Jesús lo ha pedido explícitamente («cualquier modificación sea siempre en remoto y en desktop»). Por eso, antes de cerrar cualquier tarea, cada cambio tiene que estar hecho y comprobado en ambas, o tener escrito por qué una de las dos no aplica.
1. Ubica la pieza en cada versión
Busca primero dónde vive hoy lo que vas a cambiar, en las dos versiones. Mapa de partes que ya divergen (léelo como pistas, verifica en el código porque cambia rápido):
| Parte | Escritorio (cc-app) | Remoto (navegador) |
|---|---|---|
| Barra de comandos | dash/command-sidebar.js dentro del WebKit |
el mismo módulo |
| Terminal de la barra | VTE nativa bajo el WebKit (_side_paned, _side_term_show; la web avisa con {sidebarTerm: …}) |
iframe ttyd (sidebarTermMount, .mini) |
| Terminales de sesión | VTE + tmux attach (open_tab, make_term) |
ttyd + dash/term.html |
| Cabecera y marcos de pane | _pane_frames, _reposition_pills en cc-app |
capa #pane-chrome en term.html |
| Modal de Cadenas | ventana GTK modal (open_chain_modal, ?panel=chains) |
backdrop web (chain-builder.js) |
| Botones de la cabecera | HEADER_ACTIONS por el puente centro |
handlers web |
| Copiar | puente tmux → portapapeles (lib/tmux_clipboard.py) + selección VTE |
selección de xterm.js / navegador |
| Foco y destino de comandos | /active-tab que publica cc-app + sidebarTermFocused |
remotePaneFocus en la web |
| Tema | apply_theme en cc-app + tokens CSS |
tokens CSS (data-theme) |
| Esconder panel izquierdo | botón panel-left en la tira de pestañas |
(pendiente si no existe: dilo) |
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.
- 28d ago First seen · 100 lines · 0 tokens per session scan A 36d1124e04fd
comandos-remoto-y-escritorio is a skill published in the GitHub repository 0xAI-Builders/comandos (6 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,807 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
accessible-web-animation-builder
Create performant web animations with proper accessibility and timing.
factory-render-verify
Render-and-measure receipts for any HTML page your factory builds — the render half of the design quality gate. Engineer runs it to screenshot every screen size and MEASURE what a source read or a single screenshot only guesses at: horizontal overflow, computed type sizes, tap-target sizes, safe-area presence, mono…
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
product-ui
Use this skill when UI design and UI implementation should happen together. It turns product context into usable frontend screens, components, layout decisions, design-system choices, accessibility rules, and visual polish.
codebase-context-extractor
This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.
skill-creator
Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.