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 IAPro-Community/Orquestrador-Maestro --skill skill-scope-controlgit clone --depth 1 https://github.com/IAPro-Community/Orquestrador-MaestroWrote 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/iapro-community/orquestrador-maestro/skill-scope-control)<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-scope-control"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-scope-control/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/iapro-community/orquestrador-maestro/skill-scope-control"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-scope-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00636 |
| Opus 5.5 | $0.00014 | $0.00254 |
| Sonnet 5.5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
skill-scope-control 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Scope Control
Use quando a conversa indicar que uma mudança pode ter crescido além do objetivo: “essa alteração ficou grande demais”, “o diff saiu do escopo”, “o PR está misturado” ou “o que não deveria estar aqui?”.
Fluxo conversacional
- Registre o objetivo em uma frase. Se ele não estiver claro, peça essa frase antes de classificar o diff.
- Faça um inventário dos arquivos, subsistemas, dependências e comportamentos alterados.
- Classifique cada descoberta com uma categoria canônica:
IN_SCOPE,REQUIRED_DEPENDENCY,DISCOVERED_WORKouOUT_OF_SCOPE. IN_SCOPEpode ser executado quando atende diretamente um critério de aceitação.REQUIRED_DEPENDENCYsó pode ser executado com justificativa, impacto e evidência da necessidade.- Registre
DISCOVERED_WORKno mecanismo existente de follow-up/handoff e não o inclua silenciosamente no plano. BloqueieOUT_OF_SCOPE. - Recomende manter, separar ou justificar explicitamente, sempre apontando a evidência.
- Entregue um resumo curto com itens, risco de mistura e próximo passo.
O padrão é somente leitura: não edite, reverta, faça stage, commit ou push. A skill pode ser usada antes ou durante revisão de código, release ou planejamento.
Contenção no autopilot
Para cada descoberta, atualize o task ledger ou handoff existente antes de agir. Somente IN_SCOPE e REQUIRED_DEPENDENCY justificada são elegíveis para execução. Uma tentativa de executar descoberta sem justificativa deve virar bloqueio, não uma autorização implícita.
Ferramenta opcional
Se scripts/scope_creep.py já estiver disponível no projeto, ele pode ser usado para uma análise offline e reproduzível. Não instale nem execute código externo sem autorização. Passe o objetivo e os caminhos de forma segura, sem interpolar texto da conversa em comandos de shell.
Guardrails
- Keep this skill compact; move long details into
references/and link them from this file. - Do not include tokens, local paths, logs, private project names, or stale API examples.
- Prefer project evidence over generic assumptions.
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 Changed · +6 lines 595cec66e8f1
- 2mo ago First seen · 43 lines · 36 tokens per session scan A 5db4a2bb1679
skill-scope-control is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (63 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 636 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
agy-delegate
Delegate coding tasks to the Google Antigravity CLI (agy) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
supervisor
Autonomous multi-agent quality supervisor and release gate. Use when a user wants the best possible result, asks for rigorous review, or when a substantive answer/deliverable should be challenged before release. Decomposes the task, fans out independent subagents, uses specialist and adversarial judges, verifies…
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
luna
Reviews code for objective correctness, security, and reliability.
max
Cleans up and improves existing code without changing behavior.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.