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-referencia-roteamentogit 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-referencia-roteamento)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-referencia-roteamento"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-roteamento/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-referencia-roteamento"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-roteamento.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 154 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 | $0.00043 | $0.02895 |
| Opus 5.5 | $0.00017 | $0.01158 |
| Sonnet 5.5 | $0.00009 | $0.00579 |
| Haiku 4.5 | $0.00004 | $0.00290 |
Grade A, and why
ag-referencia-roteamento 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roteamento de Ferramentas — Decision Tree Expandida
Complementa
.claude/rules/prompt-protocol.mdcom arvore de decisao detalhada, heuristicas e exemplos. Invocar quando: (a) usuario pedir explicitamente, (b) Claude detectar 2+ rotas viaveis, (c) auditoria de escolha antes de executar tarefa critica.
Quando Invocar
- Ambiguidade real na rota (ex: "testa isso" — QAT? E2E? unit? manual via Playwright?)
- Pedido composto com multiplas frentes (decidir: serializar, paralelizar, ou delegar?)
- Usuario digitou
/ag-referencia-roteamento [intent]ou "qual o melhor comando para X" - Claude vai executar algo caro (deploy prod, team paralelo, refactor em N arquivos) e quer confirmar rota
Heuristicas Rapidas (decidir em 1 pergunta)
| Pergunta | Resposta → Ferramenta |
|---|---|
| Preciso de expertise de stack carregada no contexto? | /ag-referencia-nextjs, supabase, typescript, etc. |
| Preciso de quality gates (typecheck + lint + test + PR)? | Machine (/ag-1-construir, /ag-2-corrigir) |
| E 1 arquivo com mudanca obvia? | Edit direto |
| E N arquivos com mesmo pattern (bulk)? | Machine com bulk-change-safety aplicado |
| N frentes de escrita paralelas no mesmo repo? | /ag-team-safe com worktree obrigatorio |
| Exploracao read-only ampla? | Agent(Explore) em paralelo |
| Atalho para acao isolada sem pipeline? | Plugin (/commit, /deploy, /review-pr) |
| Incerto sobre classificacao? | /ag-0-orquestrador |
Arvore de Decisao por Intent
1. Construir algo (feature, bug, refactor, UI, integracao)
Intent = construir
├── Quick fix 1 arquivo, mudanca obvia?
│ └── Edit direto (sem agent)
├── Feature isolada, self-contained, sem pipeline?
│ └── /feature-dev (plugin)
├── Feature com spec + testes + review + PR?
│ └── /ag-1-construir [feature X]
├── Build + review concorrente (pair programming)?
│ └── /ag-1-construir --validado [feature X]
├── Multi-repo ou N frentes independentes?
│ └── /ag-team-safe (worktree por teammate)
└── Ambiguo → /ag-0-orquestrador
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 · 266 lines · 43 tokens per session scan A c0cc11d68881
ag-referencia-roteamento is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,895 once invoked, about $0.0002 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…