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 improve-codebase-architecturegit 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/improve-codebase-architecture)<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/improve-codebase-architecture/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/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/improve-codebase-architecture.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 | $0.00093 | $0.04350 |
| Opus 5.5 | $0.00037 | $0.01740 |
| Sonnet 5.5 | $0.00019 | $0.00870 |
| Haiku 4.5 | $0.00009 | $0.00435 |
Grade A, and why
improve-codebase-architecture 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melhorar a arquitetura do codigo
Encontrar oportunidades reais de tornar o sistema compreensivel, coeso, testavel e facil de evoluir. Nao confundir mais camadas, arquivos ou padroes com melhor arquitetura.
Principios
- Ler
CONTEXT.md, ADRs e documentos do dominio antes de opinar. Declarar quando eles nao existirem. - Seguir o fluxo real: interface ou entrada, caso de uso, dominio, persistencia e integracoes.
- Separar fatos, inferencias e hipoteses. Nao apresentar hiptese como diagnostico.
- Avaliar produto e negocio junto com engenharia: risco operacional, velocidade de entrega, entendimento do time e custo de mudanca futura.
- Explicitar os trade-offs de cada recomendacao: beneficio, custo de implementacao, custo de adiamento, risco de regressao e o que se deixa de priorizar ao executa-la.
- Oferecer insights acionaveis, nao apenas diagnosticos: apontar a decisao que o time precisa tomar, o sinal que confirma ou invalida a proposta e a menor experiencia reversivel para reduzir a incerteza.
- Nao criar abstracoes apenas para dividir arquivos ou mover
ifs. Uma extracao precisa dar dono claro a uma regra e esconder detalhes dos chamadores.
Procurar evidencia de
- Regras de dominio repetidas ou vazando entre tela, controlador, caso de uso, repositorio e chamadores.
- Servicos de aplicacao que deixaram de orquestrar e passaram a concentrar regras, mapeamentos e decisoes de varios conceitos.
- Modulos rasos, acoplamento excessivo ou testes presos a detalhes internos.
- Mudancas simples que exigem alteracoes em muitos pontos sem razao de dominio.
- Contratos, permissoes, mensagens ou validacoes divergentes entre fronteiras.
Usar SOLID como lente, nao como lista de padroes. Servicos de aplicacao coordenam dependencias, transacoes e efeitos externos; invariantes e decisoes de negocio pertencem ao conceito que as sustenta.
Processo
- Delimitar o fluxo e o resultado de negocio analisados.
- Mapear responsabilidades, chamadores e dependencias relevantes. Registrar somente arquivos e modulos com relacao causal com a friccao.
- Validar a leitura com testes, buscas por chamadas, contratos ou comportamento observavel quando possivel.
- Para cada candidato, explicar friccao, dono ausente, mudanca minima, ganho verificavel, risco, custo, trade-offs e motivo para fazer agora ou adiar.
- Distinguir a visao de arquitetura da visao de produto. A primeira explica responsabilidades, dependencias, contratos, testes e evolucao tecnica. A segunda explica usuario ou operacao afetados, resultado de negocio, tempo de entrega, risco operacional e custo de oportunidade. Nao repetir a mesma frase nas duas secoes.
What ships with it
3 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 · 299 lines · 93 tokens per session scan A 0ecc184f2116
improve-codebase-architecture is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (62 stars, last pushed 5d ago), licensed Apache-2.0. It adds 93 tokens to every session and 4,350 once invoked, about $0.0004 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 2026-09-03.
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.