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 | $0.00046 | $0.02175 |
| Sonnet 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 5d 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.
- 5d 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 (41 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 4,350 once invoked, about $0.0005 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
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.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
workspace-diff-review
Reviews the current workspace diff with a pre-landing mindset.
code-review-skill
Reviews code for bugs, inefficiencies, and adherence to best practices, providing actionable improvement suggestions.
workspace-change-risk-review
Inspects current workspace changes and highlights.
expert-panel-review
Run code, architecture, systems, or proposed changes through a panel of world-class engineering perspectives. Each panelist reads the ACTUAL source files before judging. Use this skill whenever the user asks to: review code quality, get expert opinions, assess architecture decisions, evaluate a refactor plan, critique…