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-team-terminaisgit 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-team-terminais)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-team-terminais"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-team-terminais/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-team-terminais"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-team-terminais.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 40 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 | $0.00086 | $0.02555 |
| Opus 5 | $0.00043 | $0.01277 |
| Sonnet 5 | $0.00017 | $0.00511 |
| Haiku 4.5 | $0.00009 | $0.00255 |
Grade A, and why
ag-team-terminais 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 9d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-team-terminais — N terminais Claude, 1 repo, objetivos distintos
Problema que resolve
ListAgents/SendMessage ja permitem que sessoes Claude locais conversem, e worktree ja isola escrita paralela. O que NAO existe e protocolo: quem faz o que, onde cada um escreve, como se reportam e como o trabalho integra no final. Esta skill codifica esse protocolo. Zero codigo novo — apenas disciplina sobre ferramentas nativas + um manifesto em arquivo.
Quando usar / quando NAO usar
| Cenario | Rota |
|---|---|
| 2+ terminais interativos, mesmo repo, objetivos distintos | esta skill |
| N teammates dentro de UMA sessao | /ag-team-safe |
| Plano multi-PR serial | /ag-0-orquestrador |
| Fan-out de subagents descartaveis (decompor+cobrir) | Workflow |
| 1 feature / 1 fix, 1 PR | /ag-1-construir ou /ag-2-corrigir |
Conceitos
- Coordenador — a sessao que roda
init. Dono do manifesto e da integracao; read-only no working tree principal (excecao unica: commits de integracao). Por default NAO executa objetivo; com--coord-executaassume um papel em worktree proprio (util com 2 terminais). - Worker — sessao que roda
join. Trabalha EXCLUSIVAMENTE no proprio worktree. - Manifesto — fonte unica de verdade; sobrevive a morte/compaction de qualquer sessao.
Path:
~/Claude/docs/ai-state/team/<repo-nome>-<slug>/manifest.md(template emtemplates/manifest.mddesta skill). Fica FORA dos working trees de proposito: arquivo gitignorado dentro do repo tem uma copia POR worktree — nao e compartilhado. Formato deliberadamente distinto do orq-goal-schema (goal de orquestrador ja travou Stop de sessao paralela via orq-goal-guard — este manifesto nao pode pattern-matchar aquele schema). - Canal — SendMessage e nudge efemero; o manifesto e o estado. Sessao busy so processa mensagem ao fim do proprio turno — NUNCA bloquear esperando resposta.
- Claim atomico — reivindicar papel =
mkdir <team-dir>/claims/<papel>(mkdir e atomico no APFS; se falhar, o papel ja tem dono).
What ships with it
1 file 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.
- 9d ago First seen · 165 lines · 86 tokens per session scan A 57b278d0a816
ag-team-terminais is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 2,555 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
implement-issue
Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.
get-up-to-speed
Reviews the latest git history, branch state, Linear ticket, and open work to build a concise situational summary. Use when picking up work after another agent, resuming a session, or onboarding to a branch mid-flight.
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
github
Interact with GitHub using the gh CLI. Use for issues, PRs, CI runs, releases, and advanced API queries.
glab
Interact with GitLab using the glab CLI. Use for issues, merge requests, CI pipelines, and advanced API queries.