bps-kit 1.3.1 → 1.4.1

package/.bps-kit.json

@@ -1,6 +1,6 @@
 {
   "mode": "normal",
   "vscode": false,
-  "version": "1.3.0",
-  "installedAt": "2026-03-11T00:38:59.884Z"
+  "version": "1.3.1",
+  "installedAt": "2026-03-11T00:51:23.317Z"
 }

package/CHANGELOG.md

@@ -5,6 +5,33 @@ Todas as mudanças notáveis ​​neste projeto serão documentadas neste arqui
 O formato é baseado no [Keep a Changelog](https://keepachangelog.com/pt-BR/1.0.0/), 
 e este projeto adere ao [Versionamento Semântico](https://semver.org/lang/pt-BR/).
 
+## [1.4.1] - 2026-03-11
+### Corrigido
+- **`automation-specialist.md`**: Arquivo faltando em `src/agents/` — criado e sincronizado com `templates/`.
+- **`debugger.md`**: Frontmatter incompleto em `src/` e `templates/` — adicionados campos `tools` e `model: inherit` faltantes.
+- **`frontend-specialist.md`**: Dois skills (`design-md`, `enhance-prompt`) faltando em `src/` — sincronizado com template.
+- **`setup-brain.md`** em `src/`: Passo 6 ainda continha a versão antiga (editava GEMINI.md) — sincronizado com a versão corrigida do template.
+- **`AGENTS.md`**: Coluna "Skills (frontmatter)" corrigida para 20/22 agentes — agora reflete exatamente o frontmatter `skills:` real de cada agente (removido `clean-code` genérico, adicionados skills específicos por domínio).
+- **`orchestrate.md`**: Tabela de agentes listava apenas 16 agentes — atualizada para todos os 22, incluindo `qa-automation-engineer`, `site-builder`, `automation-specialist`, `code-archaeologist`, `product-manager`, `product-owner`. Checklist de domínios expandida com 4 novos domínios.
+- **`ARCHITECTURE.md`**: Corrigidas contagens (20→22 agentes, 12→15 workflows), tabela de agentes atualizada com skills reais, workflows `/automate`, `/build-site` e `/recall` adicionados, Quick Reference atualizado.
+- **`copy_templates.js`**: Adicionado step de cópia do `AGENTS.md` ao pipeline (com fallback de aviso). `NORMAL_SKILLS` expandida com `design-md`, `enhance-prompt`, `react-components` e 7 skills `n8n-*`. `EXTRA_SKILLS` expandida com `stitch-loop`.
+- **`.agents/rules/AGENTS.md`**: Criado como fonte para o pipeline `copy_templates.js`.
+
+## [1.4.0] - 2026-03-11
+### Adicionado
+- **AGENTS.md**: Novo arquivo de regras dedicado ao routing de agentes, extraído do `GEMINI.md`. Contém a tabela Keyword→Agent completa com 22 agentes mapeados, regras de boundary enforcement e file type ownership. Distribuído automaticamente em `.agents/rules/AGENTS.md` (Antigravity) e `.github/AGENTS.md` (VS Code Copilot via `--vscode`).
+- **`convert_to_vscode.js`**: Suporte nativo ao `AGENTS.md` — o arquivo é convertido e copiado para `.github/AGENTS.md` com os mesmos path replacements do `GEMINI.md` (skills, vault, agents, scripts, frontmatter trigger).
+
+### Corrigido
+- **GEMINI.md**: 5 causas raiz que forçavam `Agent: orchestrator | Skill: none` como default foram eliminadas:
+  - `Auto-Selection Protocol` genérico substituído por referência à tabela concreta do `AGENTS.md`.
+  - Step 2 do checklist aponta explicitamente para `AGENTS.md` com instrução `NUNCA default orchestrator`.
+  - `PRE-FLIGHT OBRIGATÓRIO` reposicionado para pós-roteamento (passos 1-7) com revalidação anti-orchestrator.
+  - Step 5 agora carrega skills do frontmatter `skills:` do agente além do Intent Map.
+  - Gemini Mode `edit` não mais hardcoded para `orchestrator` — redireciona para Keyword→Agent table.
+  - Seção `Core Rule — Skills First` redundante removida (liberando espaço).
+- `GEMINI.md` reduzido de 279 → 182 linhas (−35%) sem perda de informação.
+
 ## [1.2.0] - 2026-03-09
 ### Adicionado
 - Novo template `ARCHITECTURE.md` distribuído junto ao kit, mapeando os 20 agentes com suas skills, skills organizadas por tier (basic/normal/extra), 12 workflows e scripts de validação disponíveis. Referenciado obrigatoriamente pelo `GEMINI.md` no startup da sessão.

package/README.md

@@ -43,7 +43,8 @@ npx bps-kit@latest --upgrade
 Se você adicionou a flag `--vscode`, a arquitetura compilada será organicamente moldada para as regras da nuvem do GitHub (`.github/`):
 - O manifesto base e as Workflows irão habitar o `.github/copilot-instructions.md`.
 - As Skills ativas receberão glob patterns específicos (`applyTo: "**/*"`) protegendo seu ciclo de vida.
-- As famosas 20 Personas se fundirão em um único registro local `.github/AGENTS.md`.
+- As 22 Personas são mapeadas individualmente em `.github/agents/*.agent.md` — com frontmatter Copilot nativo.
+- O manifesto de routing de agentes (Keyword→Agent) é exportado para `.github/AGENTS.md`.
 - A gigantesca Vault contendo +1000 skills inativas será armazenada inteligentemente em isolamento (`.copilot-vault/`), salvando permanentemente seu limite de Chat no VS Code de travar.
 
 ### 🪄 Autocalibragem de Base de Código (Workflow Analyzer)

package/bin/convert_to_vscode.js

@@ -26,6 +26,7 @@ async function convertToVsCode(destAgents, destBase) {
         content = content.replace(/\.?\/?\.agents\/skills\//g, '.copilot-skills/');
         content = content.replace(/\.?\/?\.agents\/vault\//g, '.copilot-vault/');
         content = content.replace(/\.?\/?\.agents\/rules\/GEMINI\.md/g, '.github/copilot-instructions.md');
+        content = content.replace(/\.?\/?\.agents\/rules\/AGENTS\.md/g, '.github/AGENTS.md');
         content = content.replace(/\.?\/?\.agents\/VAULT_INDEX\.md/g, '.github/VAULT_INDEX.md');
         content = content.replace(/\.?\/?\.agents\/ARCHITECTURE\.md/g, '.github/ARCHITECTURE.md');
         content = content.replace(/\.?\/?\.agents\/agents\//g, '.github/agents/');
@@ -40,6 +41,22 @@ async function convertToVsCode(destAgents, destBase) {
         await fs.writeFile(path.join(gitHubDir, 'copilot-instructions.md'), content);
     }
 
+    // 1.1 Converter AGENTS.md (routing rules) com os mesmos path replacements
+    const agentsMdPath = path.join(destAgents, 'rules', 'AGENTS.md');
+    if (await fs.pathExists(agentsMdPath)) {
+        let content = await fs.readFile(agentsMdPath, 'utf8');
+        content = content.replace(/\.?\/?\.agents\/skills\//g, '.copilot-skills/');
+        content = content.replace(/\.?\/?\.agents\/vault\//g, '.copilot-vault/');
+        content = content.replace(/\.?\/?\.agents\/rules\/GEMINI\.md/g, '.github/copilot-instructions.md');
+        content = content.replace(/\.?\/?\.agents\/rules\/AGENTS\.md/g, '.github/AGENTS.md');
+        content = content.replace(/\.?\/?\.agents\/VAULT_INDEX\.md/g, '.github/VAULT_INDEX.md');
+        content = content.replace(/\.?\/?\.agents\/ARCHITECTURE\.md/g, '.github/ARCHITECTURE.md');
+        content = content.replace(/\.?\/?\.agents\/agents\//g, '.github/agents/');
+        content = content.replace(/\.?\/?\.agents\/scripts\//g, '.github/scripts/');
+        content = content.replace(/trigger:\s*always_on/g, 'applyTo: "**/*"');
+        await fs.writeFile(path.join(gitHubDir, 'AGENTS.md'), content);
+    }
+
     // 2. Mover as skills ativas inteiras (em vez de achatar) para preservar scripts em python embutidos e sub documentações!
     // Importante: NÃO alocamos em .github/skills pois o Copilot engole todos os Markdowns de lá e causa sobrecarga de +60 referências!
     const skillsDest = path.join(destAgents, 'skills');

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bps-kit",
-  "version": "1.3.1",
+  "version": "1.4.1",
   "description": "BPS Kit - The Ultimate Antigravity Brain",
   "bin": {
     "bps-kit": "./bin/cli.js"
@@ -26,4 +26,4 @@
     "fs-extra": "^11.2.0",
     "ora": "^5.4.1"
   }
-}
+}

package/templates/agents-template/ARCHITECTURE.md

@@ -39,28 +39,28 @@ Specialist AI personas for different domains.
 
 | Agent                    | Focus                      | Skills Used                                              |
 | ------------------------ | -------------------------- | -------------------------------------------------------- |
-| `orchestrator`           | Multi-agent coordination   | clean-code, behavioral-modes, plan-writing               |
-| `project-planner`        | Discovery, task planning   | brainstorming, plan-writing                              |
-| `frontend-specialist`    | Web UI/UX                  | frontend-design, react-patterns, tailwind-patterns       |
-| `backend-specialist`     | API, business logic        | api-patterns, database-design                            |
-| `database-architect`     | Schema, SQL                | database-design, prisma-expert                           |
+| `orchestrator`           | Multi-agent coordination   | parallel-agents, behavioral-modes, plan-writing, architecture |
+| `project-planner`        | Discovery, task planning   | app-builder, plan-writing, brainstorming                 |
+| `frontend-specialist`    | Web UI/UX                  | nextjs-react-expert, tailwind-patterns, frontend-design, design-md, enhance-prompt |
+| `backend-specialist`     | API, business logic        | nodejs-best-practices, api-patterns, database-design, mcp-builder |
+| `database-architect`     | Schema, SQL                | database-design                                          |
 | `mobile-developer`       | iOS, Android, RN           | mobile-design                                            |
-| `game-developer`         | Game logic, mechanics      | —                                                        |
-| `devops-engineer`        | CI/CD, Docker              | docker-expert                                            |
-| `security-auditor`       | Security compliance        | vulnerability-scanner                                    |
-| `penetration-tester`     | Offensive security         | vulnerability-scanner                                    |
-| `test-engineer`          | Testing strategies         | testing-patterns, test-driven-development                |
+| `game-developer`         | Game logic, mechanics      | game-development (12 sub-skills)                         |
+| `devops-engineer`        | CI/CD, Docker              | deployment-procedures, server-management                 |
+| `security-auditor`       | Security compliance        | vulnerability-scanner, red-team-tactics                   |
+| `penetration-tester`     | Offensive security         | vulnerability-scanner, red-team-tactics                   |
+| `test-engineer`          | Testing strategies         | testing-patterns, tdd-workflow, webapp-testing            |
 | `debugger`               | Root cause analysis        | systematic-debugging                                     |
 | `performance-optimizer`  | Speed, Web Vitals          | performance-profiling                                    |
-| `seo-specialist`         | Ranking, visibility        | seo-fundamentals                                         |
-| `documentation-writer`   | Manuals, docs              | —                                                        |
+| `seo-specialist`         | Ranking, visibility        | seo-fundamentals, geo-fundamentals                       |
+| `documentation-writer`   | Manuals, docs              | documentation-templates                                  |
 | `product-manager`        | Requirements, user stories | plan-writing, brainstorming                              |
 | `product-owner`          | Strategy, backlog, MVP     | plan-writing, brainstorming                              |
-| `qa-automation-engineer` | E2E testing, CI pipelines  | testing-patterns                                         |
-| `code-archaeologist`     | Legacy code, refactoring   | clean-code                                               |
-| `explorer-agent`         | Codebase analysis          | —                                                        |
-| `site-builder`           | Landing pages, websites    | frontend-design, scroll-experience, enhance-prompt       |
-| `automation-specialist`  | n8n workflow automation    | n8n-mcp-tools-expert, n8n-workflow-patterns, n8n-expression-syntax |
+| `qa-automation-engineer` | E2E testing, CI pipelines  | webapp-testing, testing-patterns                          |
+| `code-archaeologist`     | Legacy code, refactoring   | refactoring-patterns, code-review-checklist               |
+| `explorer-agent`         | Codebase analysis          | architecture, plan-writing, brainstorming                 |
+| `site-builder`           | Landing pages, websites    | scroll-experience, tailwind-patterns, frontend-design, design-md, enhance-prompt |
+| `automation-specialist`  | n8n workflow automation    | n8n-mcp-tools-expert, n8n-workflow-patterns               |
 
 ---
 
@@ -119,13 +119,6 @@ Skills availability depends on the installed profile (`basic`, `normal`, or `ext
 | `test-driven-development` | TDD workflow                   |
 | `testing-patterns`        | Jest, Vitest, strategies       |
 | `vercel-deployment`       | Vercel deploy workflows        |
-| `n8n-mcp-tools-expert`    | n8n MCP tool selection & usage |
-| `n8n-workflow-patterns`   | n8n architectural patterns     |
-| `n8n-expression-syntax`   | n8n expression `{{$json.*}}`   |
-| `n8n-node-configuration`  | n8n node operation config      |
-| `n8n-validation-expert`   | n8n validation error fixing    |
-| `n8n-code-javascript`     | n8n Code node (JavaScript)     |
-| `n8n-code-python`         | n8n Code node (Python)         |
 
 ### Extra Profile (adds ~27 more skills)
 
@@ -167,8 +160,9 @@ Slash command procedures. Invoke with `/command`.
 
 | Command          | Description                     |
 | ---------------- | ------------------------------- |
+| `/automate`      | n8n workflow automation builder  |
 | `/brainstorm`    | Socratic discovery              |
-| `/build-site`    | Full website creation workflow  |
+| `/build-site`    | Cinematic landing page builder  |
 | `/create`        | Create new features             |
 | `/debug`         | Debug issues                    |
 | `/deploy`        | Deploy application              |
@@ -176,12 +170,11 @@ Slash command procedures. Invoke with `/command`.
 | `/orchestrate`   | Multi-agent coordination        |
 | `/plan`          | Task breakdown                  |
 | `/preview`       | Preview changes                 |
-| `/recall`        | Re-anchor AI to rules           |
+| `/recall`        | Re-anchor AI on rules           |
 | `/setup-brain`   | Initialize agent memory/context |
 | `/status`        | Check project status            |
 | `/test`          | Run tests                       |
 | `/ui-ux-pro-max` | Full UI/UX design workflow      |
-| `/automate`      | n8n workflow automation builder |
 
 ---
 
@@ -225,7 +218,7 @@ Scripts are embedded within skills at `.agents/skills/<skill>/scripts/`:
 | ------------------- | ----------------------------- |
 | **Total Agents**    | 22                            |
 | **Basic Skills**    | 11                            |
-| **Normal Skills**   | ~49                           |
+| **Normal Skills**   | ~42                           |
 | **Extra Skills**    | ~69                           |
 | **Vault Skills**    | 1200+                         |
 | **Total Workflows** | 15                            |
@@ -234,15 +227,15 @@ Scripts are embedded within skills at `.agents/skills/<skill>/scripts/`:
 
 ## 🔗 Quick Reference
 
-| Need     | Agent                 | Skills                                |
-| -------- | --------------------- | ------------------------------------- |
-| Web App  | `frontend-specialist` | frontend-design, react-patterns       |
-| API      | `backend-specialist`  | api-patterns, backend-dev-guidelines  |
-| Mobile   | `mobile-developer`    | mobile-design                         |
-| Database | `database-architect`  | database-design, prisma-expert        |
-| Security | `security-auditor`    | vulnerability-scanner                 |
-| Testing  | `test-engineer`       | testing-patterns, test-driven-development |
-| Debug    | `debugger`            | systematic-debugging                  |
-| Plan     | `project-planner`     | brainstorming, plan-writing           |
-| Deploy   | `devops-engineer`     | docker-expert, vercel-deployment      |
+| Need     | Agent                 | Skills                                    |
+| -------- | --------------------- | ----------------------------------------- |
+| Web App  | `frontend-specialist` | nextjs-react-expert, tailwind-patterns, frontend-design |
+| API      | `backend-specialist`  | api-patterns, nodejs-best-practices       |
+| Mobile   | `mobile-developer`    | mobile-design                             |
+| Database | `database-architect`  | database-design                           |
+| Security | `security-auditor`    | vulnerability-scanner, red-team-tactics   |
+| Testing  | `test-engineer`       | testing-patterns, tdd-workflow            |
+| Debug    | `debugger`            | systematic-debugging                      |
+| Plan     | `project-planner`     | brainstorming, plan-writing               |
+| Deploy   | `devops-engineer`     | deployment-procedures, server-management  |
 | Automate | `automation-specialist` | n8n-mcp-tools-expert, n8n-workflow-patterns |

package/templates/agents-template/agents/debugger.md

@@ -1,6 +1,8 @@
 ---
 name: debugger
 description: Expert in systematic debugging, root cause analysis, and crash investigation. Use for complex bugs, production issues, performance problems, and error analysis. Triggers on bug, error, crash, not working, broken, investigate, fix.
+tools: Read, Grep, Glob, Bash, Edit, Write
+model: inherit
 skills: clean-code, systematic-debugging
 ---
 

package/templates/agents-template/rules/AGENTS.md

@@ -0,0 +1,81 @@
+---
+trigger: always_on
+---
+
+# AGENTS.md — Agent Routing & Boundary Rules
+
+> Este arquivo define COMO rotear requests para o agente correto e suas regras de fronteira.
+
+---
+
+## 🔴 REGRA #1: orchestrator NÃO é default
+
+> **orchestrator = SOMENTE quando 2+ domínios distintos precisam trabalhar juntos.**
+> Se o request cabe em 1 agente → use esse agente diretamente.
+
+---
+
+## 🗺️ Keyword → Agent (primeira correspondência)
+
+| Keywords no request | Agent | Skills (frontmatter) |
+|---|---|---|
+| component, react, ui, ux, css, tailwind, frontend, hook, state | `frontend-specialist` | nextjs-react-expert, web-design-guidelines, tailwind-patterns, frontend-design, design-md, enhance-prompt |
+| landing page, site, website, hero, parallax, one-pager | `site-builder` | scroll-experience, tailwind-patterns, react-patterns, frontend-design, design-md, enhance-prompt, react-components |
+| backend, server, api, endpoint, auth, express, fastapi, hono | `backend-specialist` | nodejs-best-practices, api-patterns, database-design, mcp-builder |
+| schema, SQL, migration, prisma, drizzle, database design | `database-architect` | database-design |
+| bug, error, crash, not working, broken, fix, investigate | `debugger` | systematic-debugging |
+| test, testing, coverage, TDD, E2E, jest, vitest | `test-engineer` | testing-patterns, tdd-workflow, webapp-testing, code-review-checklist |
+| mobile, iOS, Android, React Native, Flutter, Expo | `mobile-developer` | mobile-design |
+| security, vulnerability, audit, OWASP | `security-auditor` | vulnerability-scanner, red-team-tactics, api-patterns |
+| pentest, red team, exploit | `penetration-tester` | vulnerability-scanner, red-team-tactics, api-patterns |
+| deploy, CI/CD, Docker, infrastructure, PM2 | `devops-engineer` | deployment-procedures, server-management |
+| performance, speed, Web Vitals, optimize, profiling | `performance-optimizer` | performance-profiling |
+| SEO, meta tags, ranking, sitemap | `seo-specialist` | seo-fundamentals, geo-fundamentals |
+| plan, roadmap, task breakdown, milestones | `project-planner` | app-builder, plan-writing, brainstorming |
+| requirements, user stories, backlog | `product-manager` | plan-writing, brainstorming |
+| MVP, strategy, product vision | `product-owner` | plan-writing, brainstorming |
+| game, unity, godot, phaser, multiplayer | `game-developer` | game-development (12 sub-skills) |
+| n8n, webhook, automation, workflow automation | `automation-specialist` | n8n-mcp-tools-expert, n8n-workflow-patterns, n8n-expression-syntax, n8n-node-configuration, n8n-validation-expert |
+| docs, README, documentation, manual | `documentation-writer` | documentation-templates |
+| legacy code, refactor, tech debt | `code-archaeologist` | refactoring-patterns, code-review-checklist |
+| codebase analysis, map, discovery, explore | `explorer-agent` | architecture, plan-writing, brainstorming, systematic-debugging |
+| E2E automation, CI pipeline, QA pipeline | `qa-automation-engineer` | webapp-testing, testing-patterns, web-design-guidelines |
+| coordinate, orchestrate, 2+ domains simultâneos | `orchestrator` | parallel-agents, behavioral-modes, plan-writing, brainstorming, architecture |
+
+### Protocolo de Uso
+
+1. **Match keywords** do request na tabela acima (primeira correspondência)
+2. **Ler** `.agents/agents/{agent}.md` → carregar skills do frontmatter `skills:`
+3. **Anunciar**: `🤖 **Applying knowledge of @[agent-name]...**`
+4. **Carregar skills**: Ler cada SKILL.md listada no frontmatter
+5. **Anunciar**: `📖 Using skill: [nome]` — para CADA skill carregada
+6. **Se Agent=orchestrator** → revalidar: o request REALMENTE precisa de 2+ agentes?
+
+---
+
+## 🔴 Agent Boundary Enforcement
+
+**Cada agente DEVE ficar no seu domínio. Cross-domain = VIOLAÇÃO.**
+
+| Agent | ✅ CAN Do | ❌ CANNOT Do |
+|-------|----------|-------------|
+| `frontend-specialist` | Components, UI, styles, hooks | Test files, API routes, DB |
+| `backend-specialist` | API, server logic, DB queries | UI components, styles |
+| `test-engineer` | Test files, mocks, coverage | Production code |
+| `mobile-developer` | RN/Flutter, mobile UX | Web components |
+| `database-architect` | Schema, migrations, queries | UI, API logic |
+| `security-auditor` | Audit, vulnerabilities | Feature code, UI |
+| `devops-engineer` | CI/CD, deployment, infra | Application code |
+| `debugger` | Bug fixes, root cause | New features |
+| `explorer-agent` | Codebase discovery | Write operations |
+
+### File Type Ownership
+
+| File Pattern | Owner Agent |
+|---|---|
+| `**/*.test.{ts,tsx,js}`, `**/__tests__/**` | `test-engineer` |
+| `**/components/**` | `frontend-specialist` |
+| `**/api/**`, `**/server/**` | `backend-specialist` |
+| `**/prisma/**`, `**/drizzle/**` | `database-architect` |
+
+> Se um agente precisa escrever fora do seu domínio → INVOCAR o agente correto para aquele arquivo.

package/templates/agents-template/rules/GEMINI.md

@@ -18,10 +18,10 @@ trigger: always_on
 ANTES de escrever QUALQUER código ou resposta:
 
 □ 1. CLASSIFICAR o request (QUESTION / SIMPLE / COMPLEX / DESIGN)
-□ 2. ROTEAR o agente correto (frontend-specialist / backend-specialist / etc)
+□ 2. ROTEAR via AGENTS.md — Keyword→Agent table (NUNCA default orchestrator)
 □ 3. ANUNCIAR: 🤖 **Applying knowledge of `@[agent-name]`...**
 □ 4. LER o arquivo .md do agente (ex: .agents/agents/frontend-specialist.md)
-□ 5. IDENTIFICAR skills relevantes no Intent → Skill Routing Map
+□ 5. CARREGAR skills do frontmatter `skills:` do agente (+ Intent Map p/ extras)
 □ 6. LER cada SKILL.md relevante
 □ 7. ANUNCIAR: 📖 Using skill: [nome] — para CADA skill usada
 □ 8. SOCRATIC GATE: Se build/feature → PERGUNTAR mínimo 3 questões estratégicas
@@ -35,7 +35,7 @@ ANTES de escrever QUALQUER código ou resposta:
 - **📖 SKILLS FIRST**: Se não anunciou `📖 Using skill:` → VOLTE e releia este bloco.
 - **⚠️ SEM SKILL**: Se nenhuma skill for relevante, diga: `⚠️ No skill used — responding from base knowledge.`
 - **🛑 NUNCA** pule o Socratic Gate em requests de build/feature/create.
-- **📣 PRE-FLIGHT OBRIGATÓRIO**: Antes de CADA resposta que não seja QUESTION, produza na primeira linha: `⚙️ Agent: [nome] | Skill: [nome ou none] | 🇧🇷 PT-BR` — isso é seu re-check forçado a cada turno.
+- **📣 PRE-FLIGHT OBRIGATÓRIO**: Após rotear agente+skill (passos 1-7), confirme: `⚙️ Agent: [nome] | Skill: [nome ou none] | 🇧🇷 PT-BR` — se Agent=orchestrator, revalide: é MESMO multi-domínio?
 - **🆘 /recall TRIGGER**: Se o usuário digitar `/recall` → PARE tudo, releia este arquivo imediatamente, e responda: `✅ Re-ancorado. Agent=[X] | Skill=[X] | PT-BR=SIM` antes de continuar.
 
 ---
@@ -69,9 +69,6 @@ Agent activated → Check frontmatter "skills:" → Read SKILL.md (INDEX) → Re
 - **Active skills**: in `.agents/skills/` — see `ARCHITECTURE.md` for full list
 - **Vault skills** (~1200+): in `.agents/vault/` — discoverable via index
 
-### Core Rule — Skills First
-After invoking any skill, explicitly say: '📖 Using skill: [skill-name]' before proceeding. If no skill was used, say: '⚠️ No skill used — responding from base knowledge.'
-
 ### Routing Flow
 1. Check if an **active skill** covers the request → use it directly
 2. If not → open `.agents/VAULT_INDEX.md` to find a vault skill
@@ -121,26 +118,10 @@ After invoking any skill, explicitly say: '📖 Using skill: [skill-name]' befor
 
 ## 🤖 INTELLIGENT AGENT ROUTING (STEP 2 - AUTO)
 
-### Auto-Selection Protocol
-1. **Analyze (Silent)**: Detect domains from user request.
-2. **Select Agent(s)**: Choose the most appropriate specialist(s).
-3. **Inform User**: State which expertise is being applied.
-4. **Apply**: Generate response using the selected agent's persona and rules.
-
-### Response Format (MANDATORY)
-```markdown
-🤖 **Applying knowledge of `@[agent-name]`...**
-[Continue with specialized response]
-```
-
-### Agent Routing Checklist (Before ANY code/design)
+> 🔴 **Leia `.agents/rules/AGENTS.md` para a tabela Keyword→Agent completa.**
+> Regra absoluta: orchestrator = SOMENTE multi-domínio (2+ agentes). NUNCA como default.
 
-| Step | Check | If Unchecked |
-|------|-------|--------------|
-| 1 | Identified correct agent? | → STOP. Analyze domain first. |
-| 2 | Read agent's `.md` file? | → STOP. Open `.agents/agents/{agent}.md` |
-| 3 | Announced agent? | → STOP. Add announcement. |
-| 4 | Loaded required skills? | → STOP. Check `skills:` field. |
+**Protocolo:** Match keywords → Ler agent `.md` → Carregar skills do frontmatter → Anunciar ambos.
 
 ---
 
@@ -230,7 +211,7 @@ Before coding, answer: (1) Goal of agent/skill? (2) Principles to apply? (3) How
 |---|---|---|
 | **plan** | `project-planner` | 4-phase. NO CODE before Phase 4. |
 | **ask** | - | Focus on understanding. |
-| **edit** | `orchestrator` | Execute. Check {task-slug}.md first. |
+| **edit** | Keyword→Agent table | Route especialista. orchestrator só se 2+ domains. |
 
 ---
 

package/templates/agents-template/workflows/orchestrate.md

@@ -82,7 +82,7 @@ Do you approve? (Y/N)
 
 > ✅ After user approval, invoke multiple agents in PARALLEL.
 
-## Available Agents (17 total)
+## Available Agents (22 total)
 
 | Agent | Domain | Use When |
 |-------|--------|----------|
@@ -94,6 +94,7 @@ Do you approve? (Y/N)
 | `security-auditor` | Security | Vulnerabilities, Auth |
 | `penetration-tester` | Security | Active testing |
 | `test-engineer` | Testing | Unit, E2E, Coverage |
+| `qa-automation-engineer` | QA | CI pipelines, E2E automation |
 | `devops-engineer` | Ops | CI/CD, Docker, Deploy |
 | `mobile-developer` | Mobile | React Native, Flutter |
 | `performance-optimizer` | Speed | Lighthouse, Profiling |
@@ -101,6 +102,11 @@ Do you approve? (Y/N)
 | `documentation-writer` | Docs | README, API docs |
 | `debugger` | Debug | Error analysis |
 | `game-developer` | Games | Unity, Godot |
+| `site-builder` | Sites | Landing pages, cinematic UX |
+| `automation-specialist` | Automation | n8n workflows, webhooks |
+| `code-archaeologist` | Legacy | Refactoring, tech debt |
+| `product-manager` | Product | Requirements, user stories |
+| `product-owner` | Strategy | MVP, backlog, vision |
 | `orchestrator` | Meta | Coordination |
 
 ---
@@ -114,12 +120,16 @@ Identify ALL domains this task touches:
 □ Backend/API  → backend-specialist
 □ Frontend/UI  → frontend-specialist
 □ Database     → database-architect
-□ Testing      → test-engineer
+□ Testing      → test-engineer, qa-automation-engineer
 □ DevOps       → devops-engineer
 □ Mobile       → mobile-developer
 □ Performance  → performance-optimizer
 □ SEO          → seo-specialist
 □ Planning     → project-planner
+□ Sites        → site-builder
+□ Automation   → automation-specialist
+□ Legacy/Debt  → code-archaeologist
+□ Games        → game-developer
 ```
 
 ### Step 2: Phase Detection

package/templates/agents-template/workflows/setup-brain.md

@@ -36,35 +36,12 @@ Este workflow permite que eu (o seu agente Antigravity) faça uma varredura comp
      - Ativar: copiar de `./.agents/vault/{skill}` → `./.agents/skills/{skill}`
    - Confirme o total final de skills ativas após os movimentos.
 
-6. **Atualização da Rule File (OBRIGATÓRIO após mover skills)**:
-   - Detecte qual formato está instalado no repositório:
-     - **VS Code / Copilot**: Rule File = `.github/copilot-instructions.md`
-     - **Antigravity padrão (Cursor/Windsurf)**: Rule File = `.agents/rules/GEMINI.md`
-   - Após mover as skills, edite a Rule File atualizando TODOS os trechos que referenciam nomes de skills:
-
-   **a) `Skill Auto-Routing System` → contagem de active skills:**
-   ```
-   - **Active skills** (~N): in `./.agents/skills/` (ou `./.copilot-skills/` no VS Code)
-   ```
-   Substituir N pelo número real de skills ativas após a otimização.
-
-   **b) `Intent → Skill Routing Map`:**
-   - Remover todas as linhas de intent que apontam para skills que foram movidas para o vault.
-   - Adicionar/ajustar entradas baseadas nas novas skills ativas e na stack detectada.
-   - Exemplo: se `tailwind-patterns` foi para o vault, remover da linha `UI/component`.
-
-   **c) `Project Type Routing` (TIER 1):**
-   - Atualizar a tabela de agentes/skills para refletir o tipo real de projeto detectado.
-   - Adicionar nota `> 🔴 Este projeto é [tipo detectado]. Não usar agentes de [tipos irrelevantes].`
-
-   **d) `Final Checklist` (TIER 1):**
-   - Remover linhas de scripts que dependem de skills agora no vault (ex: `ux_audit.py → frontend-design`).
-   - Manter apenas scripts cujas skills dependentes ainda estejam ativas.
-
-   **e) `QUICK REFERENCE`:**
-   - Atualizar `Masters` e `Key Skills` para refletir os agentes/skills relevantes ao projeto.
+6. **Atualização do ARCHITECTURE.md (OBRIGATÓRIO após mover skills)**:
+   - Atualize SOMENTE a tabela de skills no `ARCHITECTURE.md` para refletir quais skills estão ativas vs vault.
+   - **🔴 NÃO EDITE os arquivos de regras (GEMINI.md, AGENTS.md, copilot-instructions.md).** Esses arquivos contêm routing genérico que funciona para qualquer stack — o Intent Map e a Keyword→Agent table são universais e não devem ser alterados pelo setup-brain.
 
 ### Critérios de Sucesso
 - **Precisão**: Apenas skills de altíssimo valor agregado (diretamente conectadas com a stack) serão movidas. Não encha o contexto em vão. Você foi programado para manter seu Token footprint baixo.
-- A Rule File deve estar 100% sincronizada com as skills ativas — zero referências a skills no vault.
+- O `ARCHITECTURE.md` deve refletir as skills ativas atualizadas.
+- **🔴 PROIBIDO**: Editar GEMINI.md, AGENTS.md, ou copilot-instructions.md. O routing é genérico por design.
 - Encerre rodando uma mensagem informando o resultado "Cérebro Calibrado e Otimizado para este ecossistema."