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 skills add andregusman-raiz/a-gusman-claude --skill ag-referencia-cmuxgit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-referencia-cmux)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-referencia-cmux"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-cmux/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/andregusman-raiz/a-gusman-claude/ag-referencia-cmux"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-cmux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 174 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00078 | $0.05118 |
| Opus 5 | $0.00039 | $0.02559 |
| Sonnet 5 | $0.00016 | $0.01024 |
| Haiku 4.5 | $0.00008 | $0.00512 |
Grade A, and why
ag-referencia-cmux 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 8d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: cmux — Terminal Agent-First (Claude + Codex interativos)
Referencia profunda do cmux instalado nesta maquina + modelo operacional do Andre.
Fontes: docs oficiais (cmux.com), repo manaflow-ai/cmux, inspecao local do app v0.62.2 (2026-08-25) e memoria persistente de incidentes.
Identidade do produto (nao confundir):
- E o manaflow-ai/cmux (cmux.com), terminal nativo macOS em Swift + AppKit sobre
libghostty(le config de~/.config/ghostty/config). GPL-3.0. Bundle id legado:com.cmuxterm.app. - Local: app roda de
/Volumes/cmux/cmux.app(volume montado); binario CLIcmuxemContents/Resources/bin/— ja esta no PATH de todo pane. - NAO e o
coder/cmux(hoje "Xum", produto distinto com editor embutido) nem o pacote Python antigocmux. - Proposta: "primitiva, nao solucao" — infra para rodar N agentes de codigo (Claude Code, Codex, OpenCode, Gemini CLI, etc.) lado a lado, com sinalizacao de quem precisa de atencao e superficie programavel (CLI/socket).
Quando Ativar
- Missao envolve 2+ terminais/sessoes Claude ou Codex no cmux (coordenar, monitorar, resumir estado)
- Precisa mandar texto/tecla para outra sessao, fazer nudge em sessao travada, ou ler a tela de um pane
- Precisa abrir/fechar/organizar workspaces programaticamente para uma missao
- Recovery pos-crash/panic/update do cmux (restaurar sessoes Claude/Codex)
- Reportar progresso ao usuario via sidebar/notificacao nativa (
set-status,notify) - Automatizar o browser embutido do cmux ou usar o socket JSON-RPC
Modelo Mental (hierarquia de 4 niveis)
Window (janela macOS, sidebar propria)
└─ Workspace ("aba" da sidebar; unidade primaria = 1 projeto/branch)
└─ Pane (regiao de split dentro do workspace)
└─ Surface (aba dentro do pane; tem CMUX_SURFACE_ID proprio)
└─ Panel (conteudo real: terminal Ghostty OU browser embutido)
- Sidebar mostra por workspace: branch git, PR vinculado, cwd, portas escutando, ultima notificacao, status do agente (Running / Needs input / idle) e progresso.
- Pane de agente que precisa de atencao ganha ring azul + notificacao — e o sinal canonico de "precisa de voce", alimentado pelos hooks (abaixo).
- Estado persistido em
~/Library/Application Support/cmux/:cmux.sock— socket Unix de controle (JSON-RPC, ~146 metodos)last-socket-path— caminho do socket ativo (usar para localizar o socket via script)session-com.cmuxterm.app.json— snapshot de sessao (layout, cwd, titulos; autosave continuo)socket-control-password(0600) — token local de auth do socket. NUNCA imprimir; o CLI resolve auth sozinho (--password>CMUX_SOCKET_PASSWORD> arquivo).
- Docs falam
/tmp/cmux.sock; nesta maquina o socket vive no Application Support — sempre resolver vialast-socket-pathou envCMUX_SOCKET_PATH.
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.
- 8d ago First seen · 191 lines · 78 tokens per session scan A c21513b2b779
ag-referencia-cmux is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 5,118 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 2026-09-03.
Other skills, from other repositories
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
skit
Run, inspect, and manage entries in the user's skit library — their personal hub, manager, and launcher for scripts in many languages (Python, shell, JS/TS, and more), executables, command templates, and AI-agent prompts, with typed parameter forms, saved presets, and per-entry launch policy. Use when the user asks to…