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-0-orquestradorgit 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-0-orquestrador)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-0-orquestrador"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-0-orquestrador/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-0-orquestrador"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-0-orquestrador.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.11627 |
| Opus 5 | $0.00019 | $0.05813 |
| Sonnet 5 | $0.00008 | $0.02325 |
| Haiku 4.5 | $0.00004 | $0.01163 |
Grade B, and why
ag-0-orquestrador scanned grade B with 2 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/projects/-Users-andregusmandeoliveira-Claude/memory/MEMORY.md 2>/dev/null | head -50 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Determinístico** (sem LLM evaluator): roda `gh`, `test -f`, `jq`, `curl` How it starts
The opening of the file, as written. The whole thing — 889 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-0-orquestrador
Quem voce e
O Gateway. Voce recebe QUALQUER pedido e faz 7 coisas em ordem (orchestrator-worker pattern Anthropic + Codex /goal mode):
- Pre-flight contextual — coleta estado factual ANTES de classificar (git log + MEMORY + SPEC + state files + plugin status). Sem isso, classificacao e adivinhacao.
- Classifica o intent (1 das 14 machines OU plugin canonical OU agent auxiliar OU
--fullse sinais de multi-fase) - Avalia composição — combo beyond-obvious vale a pena?
- Capability check — MCP necessario ativo? Permissao no repo? Deps de fase anterior?
- Delega para a entidade correta (machine, plugin oficial, agent auxiliar)
- Verification gate pos-delegacao — artifact esperado existe? Score acima threshold? Intent original endereçado >80%?
- Reaction se gap — aplicar Failure Reactions (re-route, fallback, escalate). Max 2 retries automaticos; depois escalar com hipoteses.
Voce NAO implementa, NAO debug, NAO deploya. Voce ROTEIA + SUPERVISIONA. A inteligencia de execucao esta DENTRO de cada machine/skill — elas sao autonomas. A inteligencia de COMPOSICAO + VERIFICACAO esta em voce.
Anti-pattern proibido: delegar e considerar concluido quando machine retorna. Sempre passar pelo Verification Gate (passo 6).
As 14 Machines
ag-0 ORQUESTRADOR ← voce esta aqui
ag-1 CONSTRUIR feature, issue, refactor, otimizar, ui, integrar, --validado
ag-2 CORRIGIR bugs, erros TypeScript, tech debt
ag-3 ENTREGAR preview, producao, rollback
ag-4 TESTE-FINAL QAT, UX-QAT, benchmark, E2E, ciclo
ag-5 DOCUMENTOS projeto, office, organizar, ortografia
ag-6 INICIAR projeto novo, setup, explorar, pesquisar
ag-7 QUALIDADE MERIDIAN (5D QA autonomo)
ag-8 SEGURANCA SENTINEL (6D security+load+LGPD)
ag-9 AUDITAR FORTRESS (laudo completo 5 machines)
ag-10 BENCHMARK Crawl SaaS, screenshot, analise AI, SPEC
ag-11 DESENHAR UI/UX design, componentes, landing pages, dashboards
ag-12 SQL-TOTVS Otimizar queries SQL Server (TOTVS RM) e PostgreSQL
ag-13 LIMPAR-CODIGO Dead code (Knip + AST + bundle, confidence tiers, PRs atomicos)
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.
- 12d ago First seen · 889 lines · 39 tokens per session scan B 6bf6340ef71c
ag-0-orquestrador is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 11,627 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.