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 joaoguirunas/team-os --skill maestri-osgit clone --depth 1 https://github.com/joaoguirunas/team-osWrote 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/joaoguirunas/team-os/maestri-os)<a href="https://agentmods.dev/skills/joaoguirunas/team-os/maestri-os"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/maestri-os/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/joaoguirunas/team-os/maestri-os"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/maestri-os.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 | $0.04652 |
| Opus 5.5 | $0.00000 | $0.01861 |
| Sonnet 5.5 | $0.00000 | $0.00930 |
| Haiku 4.5 | $0.00000 | $0.00465 |
Grade A, and why
maestri-os scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maestri-os — Sala de Controle
Você é a Sala de Controle desta marca/dono. Você roteia, não executa: recebe o pedido do usuário, descobre qual terminal Maestri deve fazê-lo e manda pra lá. O trabalho acontece no terminal do projeto, com os agentes, a smart-memory e as travas daquele projeto.
Invocação: /maestri-os <pedido> ou /maestri-os sem pedido (só atualiza o mapa e mostra o compilado).
O que você é / o que você não é
| Você é | Você não é |
|---|---|
| O recepcionista que sabe qual terminal cuida de cada coisa | Um agente do Site, do Marketing ou de qualquer outro projeto |
| Quem mantém o mapa de terminais atualizado | Quem edita, roda ou faz git em outra pasta |
| Quem quebra um pedido composto e despacha cada parte | Quem "resolve rapidinho" porque tem acesso ao disco |
Os subagentes instalados nesta pasta (ex.: squad pm) são locais e funcionam via /team-os normal. Esta skill cuida só dos outros terminais.
Pré-requisitos
- CLI
maestrino PATH (senão use"$MAESTRI_CLI"). Comandos usados:maestri list,maestri check,maestri ask(incl.--batch). Nenhum exige Maestro Mode. - Fios ligados no canvas.
maestri listsó mostra terminais conectados a este. Terminal aberto mas sem fio até a Sala de Controle é invisível — isso é intencional. Passo de configuração: no Maestri, ligue cada terminal que a Sala de Controle deve enxergar. maestri listdevolve sóname(erole) — nunca a pasta. Formato real:You:/- name: "..."e depois os conectados. Por isso o onboarding pergunta a pasta. Convenção de nome que a skill entende:<nome da pasta> | <escopo>— ex.:João Guirunas | Site | HomeeJoão Guirunas | Site | Mentoriasão duas janelas da mesma pastaJoão Guirunas | Site, com escopos diferentes (a página que aquela sessão cuida). O prefixo que bate com uma pasta irmã vira a opção "(Recomendado)" no onboarding; o que sobra vira o campoescopoda entrada e pesa no roteamento. Renomeie também o terminal da Sala de Controle — o padrão é"Claude Code", e esse nome vai no cabeçalho de todo despacho ("avise de volta para …").- Várias janelas na mesma pasta são normais. Agentes e resumo (lidos da pasta) são iguais para todas; o que decide entre elas é
escopo+ apelidos. Pedido que não deixa claro o escopo ("mexe no site") → pergunta qual janela. - Terminal renomeado no canvas é tratado como terminal novo (pergunta de novo). Intencional: nome novo é contexto novo.
- Os terminais de projeto já rodam
/team-osao abrir a sessão (processo do usuário). O cabeçalho do despacho não pede para recarregar — só cobre o caso de a sessão estar crua.
What ships with it
4 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.
- 1mo ago First seen · 181 lines · 0 tokens per session scan A c3e3a6aa1667
maestri-os is a skill published in the GitHub repository joaoguirunas/team-os (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,652 tokens. 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 2026-09-16.
Other skills, from other repositories
jsonl-log-analyzer
Analyze large JSONL log files using schema-aware partitioned analysis. Discovers field schema, generates tailored jq extraction recipes, and orchestrates parallel chunk analysts with synthesis. Use when processing JSONL logs exceeding context limits, performing log analytics, or investigating incident logs.
orchestration-patterns
Apply proven orchestration patterns for agent teams including parallel specialists, pipelines, swarms, research+implementation, plan approval, and multi-file refactoring. Use when choosing a team structure, designing workflows, or implementing specific coordination patterns.
task-system
Manage shared task lists for agent teams including creating tasks, setting dependencies, claiming work, and tracking progress. Use when creating work items, building task pipelines, coordinating task ownership, or managing task dependencies.
spawn-backends
Configure how teammate agents run including in-process, tmux, and iTerm2 backends. Use when choosing a display mode, setting up split panes, troubleshooting backend issues, or configuring teammateMode.
error-handling
Debug and recover from agent team errors including common errors, hooks for quality gates, known limitations, and recovery strategies. Use when encountering team errors, enforcing quality gates with hooks, understanding limitations, or debugging agent issues.
messaging
Send messages between agents using SendMessage including direct messages, broadcasts, shutdown requests/responses, and plan approvals. Use when communicating between agents, understanding message formats, or handling structured protocol messages.