start-vibing 1.1.2 → 1.1.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "start-vibing",
-  "version": "1.1.2",
+  "version": "1.1.3",
   "description": "Setup Claude Code agents, skills, and hooks in your project. Smart copy that preserves your custom domains and configurations.",
   "type": "module",
   "bin": {

package/template/.claude/CLAUDE.md

@@ -1,168 +1,129 @@
-# Claude Development System - Agent Context
-
-This file provides context for all agents. For user-facing rules, see `/CLAUDE.md`.
-
----
-
-## System Architecture
-
-```
-.claude/
-├── agents/          # 11 specialized agents (READ before acting)
-├── skills/          # 8 skill systems with cache
-├── config/          # Project-specific configuration
-├── commands/        # Slash commands
-└── hooks/           # Security hooks
-```
-
----
-
-## Configuration Files
-
-Project-specific settings are in `.claude/config/`:
-
-| File                   | Purpose                              |
-| ---------------------- | ------------------------------------ |
-| `project-config.json`  | Stack, structure, commands           |
-| `domain-mapping.json`  | File patterns to domains             |
-| `quality-gates.json`   | Quality check commands               |
-| `testing-config.json`  | Test framework and conventions       |
-| `security-rules.json`  | Security audit rules                 |
-
-**RULE:** Agents MUST read config files before acting. Do NOT hardcode project specifics.
-
----
-
-## Agent → Skill Mapping
-
-| Agent            | Primary Skill      | Secondary                        |
-| ---------------- | ------------------ | -------------------------------- |
-| analyzer         | codebase-knowledge | -                                |
-| research         | research-cache     | codebase-knowledge               |
-| documenter       | docs-tracker       | codebase-knowledge               |
-| tester           | test-coverage      | -                                |
-| ui-ux-reviewer   | ui-ux-audit        | -                                |
-| security-auditor | security-scan      | -                                |
-| quality-checker  | quality-gate       | -                                |
-| final-validator  | final-check        | ALL                              |
-| commit-manager   | workflow-state     | docs-tracker, codebase-knowledge |
-| domain-updater   | codebase-knowledge | docs-tracker                     |
-
----
-
-## Execution Protocol
-
-### Before ANY implementation:
-
-1. **Start task** via `workflow-manager.py start-task --type [feature|fix|refactor] --description "..."`
-2. **Read config** from `.claude/config/` for project specifics
-3. Read relevant skill SKILL.md file
-4. Check skill cache for existing data
-5. Research if needed (web search)
-6. **Approve files** via `workflow-manager.py approve-files --files "path/to/file.ts"`
-
-### After implementation:
-
-1. Update skill cache with changes
-2. Run quality gates + record results
-3. Security audit (if auth/data involved)
-4. Final validation
-5. **Mark workflow ready** via `workflow-manager.py final-validation --result approved --ready-to-commit true`
-6. **Update domains** via domain-updater agent (BEFORE commit, keeps git clean)
-7. **Commit + complete task** via commit-manager agent (FINAL step, runs complete-task)
-
----
-
-## Workflow State Tracking
-
-Location: `.claude/workflow-state.json`
-
-### CLI Commands (MANDATORY)
-
-```bash
-# 1. Start task (MUST be first)
-python .claude/hooks/workflow-manager.py start-task --type feature --description "..."
-
-# 2. After analyzer approves, register files
-python .claude/hooks/workflow-manager.py approve-files --files "src/*.ts"
-
-# 3. After each agent
-python .claude/hooks/workflow-manager.py agent-executed --agent [name] --result approved
-
-# 4. After quality gates
-python .claude/hooks/workflow-manager.py quality-gate --gate [typecheck|lint|build] --passed true
-
-# 5. Final validation
-python .claude/hooks/workflow-manager.py final-validation --result approved --ready-to-commit true
-
-# 6. After commit
-python .claude/hooks/workflow-manager.py complete-task --commit-hash [hash]
-```
-
-### Hooks Enforcement
-
-- **PreToolUse**: Blocks file edits if task not started or file not approved
-- **PostToolUse**: Auto-tracks all file modifications
-- **Stop**: Blocks session end if workflow incomplete
-- **Husky**: Blocks commit if validation failed
-
----
-
-## VETO Power Agents
-
-These agents CAN and MUST stop the flow if rules are violated:
-
-| Agent                | Blocks When                                        |
-| -------------------- | -------------------------------------------------- |
-| **security-auditor** | User ID from request, sensitive data, no validation |
-| **final-validator**  | Any rule violated, tests failing, docs missing      |
-
----
-
-## Quality Requirements
-
-All implementations MUST:
-
-- [ ] Pass typecheck (command from config)
-- [ ] Pass lint (command from config)
-- [ ] Pass unit tests (command from config)
-- [ ] Pass E2E tests (command from config)
-- [ ] Pass build (command from config)
-- [ ] Have E2E tests with real auth
-- [ ] Have documentation in `docs/`
-- [ ] Be security audited
-- [ ] Be committed with conventional commits
-- [ ] Have domains updated with session learnings
-
----
-
-## Domain Updater Agent
-
-The **domain-updater** runs BEFORE commit-manager to ensure git stays clean.
-
-### Purpose
-
-- Document **problems encountered** during the session
-- Record **solutions** applied to fix issues
-- Add **prevention tips** for future sessions
-- Update **attention points** with new learnings
-- Keep domain knowledge **current and accurate**
-
-### Trigger
-
-Runs automatically:
-1. After final-validator approves in any workflow
-2. BEFORE commit-manager (so changes are included in commit)
-3. Stop hook blocks session end until domain-updater executes (if files were modified)
-
-### Workflow Order
-
-```
-final-validator → domain-updater → commit-manager → complete-task
-                       ↑                    ↑
-              (updates domains)    (commits all + archives)
-```
-
-### Configuration
-
-Reads domain patterns from `.claude/config/domain-mapping.json`
+# Claude Development System - Agent Context
+
+This file provides context for all agents. For user-facing rules, see `/CLAUDE.md`.
+
+---
+
+## System Architecture
+
+```
+.claude/
+├── agents/          # 11 specialized agents (READ before acting)
+├── skills/          # 8 skill systems with cache
+├── config/          # Project-specific configuration
+├── commands/        # Slash commands
+└── hooks/           # Security hooks
+```
+
+---
+
+## Configuration Files
+
+Project-specific settings are in `.claude/config/`:
+
+| File                   | Purpose                              |
+| ---------------------- | ------------------------------------ |
+| `project-config.json`  | Stack, structure, commands           |
+| `domain-mapping.json`  | File patterns to domains             |
+| `quality-gates.json`   | Quality check commands               |
+| `testing-config.json`  | Test framework and conventions       |
+| `security-rules.json`  | Security audit rules                 |
+
+**RULE:** Agents MUST read config files before acting. Do NOT hardcode project specifics.
+
+---
+
+## Agent → Skill Mapping
+
+| Agent            | Primary Skill      | Secondary                        |
+| ---------------- | ------------------ | -------------------------------- |
+| analyzer         | codebase-knowledge | -                                |
+| research         | research-cache     | codebase-knowledge               |
+| documenter       | docs-tracker       | codebase-knowledge               |
+| tester           | test-coverage      | -                                |
+| ui-ux-reviewer   | ui-ux-audit        | -                                |
+| security-auditor | security-scan      | -                                |
+| quality-checker  | quality-gate       | -                                |
+| final-validator  | final-check        | ALL                              |
+| commit-manager   | workflow-state     | docs-tracker, codebase-knowledge |
+| domain-updater   | codebase-knowledge | docs-tracker                     |
+
+---
+
+## Execution Protocol
+
+### Before ANY implementation:
+1. **Read config** from `.claude/config/` for project specifics
+2. Read relevant skill SKILL.md file
+3. Check skill cache for existing data
+4. Research if needed (web search)
+
+### After implementation:
+
+1. Update skill cache with changes
+2. Run quality gates + record results
+3. Security audit (if auth/data involved)
+4. Final validation
+5. **Update domains** via domain-updater agent (BEFORE commit, keeps git clean)
+6. **Commit** via commit-manager agent (FINAL step)
+
+---
+
+## VETO Power Agents
+
+These agents CAN and MUST stop the flow if rules are violated:
+
+| Agent                | Blocks When                                        |
+| -------------------- | -------------------------------------------------- |
+| **security-auditor** | User ID from request, sensitive data, no validation |
+| **final-validator**  | Any rule violated, tests failing, docs missing      |
+
+---
+
+## Quality Requirements
+
+All implementations MUST:
+
+- [ ] Pass typecheck (command from config)
+- [ ] Pass lint (command from config)
+- [ ] Pass unit tests (command from config)
+- [ ] Pass E2E tests (command from config)
+- [ ] Pass build (command from config)
+- [ ] Have E2E tests with real auth
+- [ ] Have documentation in `docs/`
+- [ ] Be security audited
+- [ ] Be committed with conventional commits
+- [ ] Have domains updated with session learnings
+
+---
+
+## Domain Updater Agent
+
+The **domain-updater** runs BEFORE commit-manager to ensure git stays clean.
+
+### Purpose
+
+- Document **problems encountered** during the session
+- Record **solutions** applied to fix issues
+- Add **prevention tips** for future sessions
+- Update **attention points** with new learnings
+- Keep domain knowledge **current and accurate**
+
+### Trigger
+
+Runs automatically:
+1. After final-validator approves in any workflow
+2. BEFORE commit-manager (so changes are included in commit)
+3. Stop hook blocks session end until domain-updater executes (if files were modified)
+
+### Workflow Order
+
+```
+final-validator → domain-updater → commit-manager → complete-task
+                       ↑                    ↑
+              (updates domains)    (commits all + archives)
+```
+
+### Configuration
+
+Reads domain patterns from `.claude/config/domain-mapping.json`

package/template/.claude/README.md

@@ -1,55 +1,76 @@
-# Configuracao de Agentes - AI Builder
+# Claude Development System
 
-Este diretorio contem a configuracao completa do sistema de agentes
-para o fluxo de desenvolvimento do AI Builder.
+This directory contains the complete agent configuration for an automated development workflow.
 
 ---
 
-## Estrutura
+## Structure
 
 ```
 .claude/
-├── CLAUDE.md              # Contexto geral para agentes
-├── settings.json          # Configuracoes globais
-├── README.md              # Este arquivo
+├── CLAUDE.md              # Agent context
+├── settings.json          # Global settings
+├── README.md              # This file
 │
-├── agents/                # Subagentes especializados
-│   ├── orchestrator.md    # Coordena o fluxo
-│   ├── analyzer.md        # Analisa impacto
-│   ├── documenter.md      # Cria documentacao
-│   ├── tester.md          # Cria e executa testes
-│   ├── security-auditor.md # Audita seguranca
-│   ├── ui-ux-reviewer.md  # Revisa UI/UX
-│   ├── quality-checker.md # Verifica qualidade
-│   └── final-validator.md # Validacao final
+├── agents/                # Specialized subagents
+│   ├── orchestrator.md    # Coordinates flow
+│   ├── analyzer.md        # Analyzes impact
+│   ├── research.md        # Researches best practices
+│   ├── documenter.md      # Creates documentation
+│   ├── tester.md          # Creates and runs tests
+│   ├── security-auditor.md # Security audits
+│   ├── ui-ux-reviewer.md  # UI/UX reviews
+│   ├── quality-checker.md # Quality checks
+│   ├── final-validator.md # Final validation
+│   ├── domain-updater.md  # Updates domain knowledge
+│   └── commit-manager.md  # Manages commits
 │
-├── hooks/                 # Hooks de seguranca
-│   └── security-check.js  # Bloqueia acoes perigosas
+├── skills/                # Skill systems with cache
+│   ├── codebase-knowledge/
+│   ├── research-cache/
+│   ├── docs-tracker/
+│   ├── test-coverage/
+│   ├── security-scan/
+│   ├── ui-ux-audit/
+│   ├── quality-gate/
+│   ├── final-check/
+│   └── workflow-state/
 │
-└── commands/              # Slash commands customizados
-    ├── feature.md         # /feature - nova feature
-    ├── fix.md             # /fix - corrigir bug
-    ├── validate.md        # /validate - validacao completa
-    └── research.md        # /research - pesquisar topico
+├── config/                # Project-specific configuration
+│   ├── project-config.json
+│   ├── domain-mapping.json
+│   ├── quality-gates.json
+│   ├── testing-config.json
+│   └── security-rules.json
+│
+├── hooks/                 # Automation hooks
+│   ├── user-prompt-submit.py
+│   └── security-check.js
+│
+└── commands/              # Slash commands
+    ├── feature.md
+    ├── fix.md
+    ├── validate.md
+    └── research.md
 ```
 
 ---
 
-## Agentes
+## Agents
 
-### Hierarquia
+### Hierarchy
 
 ```
                     ┌─────────────────┐
                     │  ORCHESTRATOR   │
-                    │  (coordenador)  │
+                    │  (coordinator)  │
                     └────────┬────────┘
                              │
         ┌────────────────────┼────────────────────┐
         │                    │                    │
    ┌────▼────┐          ┌────▼────┐          ┌────▼────┐
    │ANALYZER │          │ TESTER  │          │ UI/UX   │
-   │(impacto)│          │(testes) │          │REVIEWER │
+   │(impact) │          │ (tests) │          │REVIEWER │
    └─────────┘          └─────────┘          └─────────┘
         │                    │                    │
    ┌────▼────┐          ┌────▼────┐          ┌────▼────┐
@@ -60,149 +81,137 @@ para o fluxo de desenvolvimento do AI Builder.
                     ┌────────▼────────┐
                     │ FINAL VALIDATOR │
                     │  (veto power)   │
+                    └────────┬────────┘
+                             │
+                    ┌────────▼────────┐
+                    │ DOMAIN UPDATER  │
+                    │ (updates docs)  │
+                    └────────┬────────┘
+                             │
+                    ┌────────▼────────┐
+                    │ COMMIT MANAGER  │
+                    │    (final)      │
                     └─────────────────┘
 ```
 
-### Funcoes
-
-| Agente           | Funcao                           | Pesquisa?                               | Pode Vetar? |
-| ---------------- | -------------------------------- | --------------------------------------- | ----------- |
-| orchestrator     | Coordena fluxo, delega tarefas   | **SIM** - best practices gerais         | Nao         |
-| analyzer         | Analisa impacto de mudancas      | **SIM** - arquitetura, migracoes        | Nao         |
-| documenter       | Cria/atualiza documentacao       | **SIM** - padroes de docs               | Nao         |
-| tester           | Cria e executa testes            | **SIM** - padroes de teste, edge cases  | Nao         |
-| security-auditor | Valida seguranca                 | **SIM** - OWASP, CVEs, vulnerabilidades | **SIM**     |
-| ui-ux-reviewer   | Pesquisa competidores, valida UI | **SIM** - competidores, UX, WCAG        | Nao         |
-| quality-checker  | Roda typecheck/lint/build        | **SIM** - solucoes para erros           | Nao         |
-| final-validator  | Checklist final completo         | **SIM** - valida que outros pesquisaram | **SIM**     |
-
-### TODOS os Agentes Pesquisam
-
-Cada agente tem a obrigacao de pesquisar best practices antes de agir:
-
-```
-orchestrator    → Pesquisa padroes de arquitetura e implementacao
-analyzer        → Pesquisa riscos e migracoes
-documenter      → Pesquisa padroes de documentacao
-tester          → Pesquisa edge cases e padroes de teste
-security-auditor → Pesquisa OWASP, CVEs, vulnerabilidades conhecidas
-ui-ux-reviewer  → Pesquisa competidores, UX patterns, WCAG
-quality-checker → Pesquisa solucoes para erros encontrados
-final-validator → Valida que TODOS os outros pesquisaram
-```
+### Functions
+
+| Agent            | Function                    | Can Veto? |
+| ---------------- | --------------------------- | --------- |
+| orchestrator     | Coordinates flow            | No        |
+| analyzer         | Analyzes change impact      | No        |
+| research         | Researches best practices   | No        |
+| documenter       | Creates documentation       | No        |
+| tester           | Creates and runs tests      | No        |
+| security-auditor | Validates security          | **YES**   |
+| ui-ux-reviewer   | Reviews UI/UX               | No        |
+| quality-checker  | Runs quality gates          | No        |
+| final-validator  | Final validation checklist  | **YES**   |
+| domain-updater   | Updates domain knowledge    | No        |
+| commit-manager   | Creates commits             | No        |
 
 ---
 
-## Fluxos
+## Workflows
 
-### Feature Completa (default_flow)
+### Feature (default_flow)
 
 ```
-1. analyzer         → Analisa impacto
-2. ui-ux-reviewer   → Pesquisa competidores (se UI)
-3. documenter       → Documenta fluxo
-4. [IMPLEMENTACAO]
-5. tester           → Cria testes
-6. security-auditor → Valida seguranca
-7. quality-checker  → typecheck + lint + build
-8. final-validator  → Checklist final
-9. [COMMIT]
+1. analyzer         → Analyzes impact
+2. research         → Researches best practices
+3. ui-ux-reviewer   → Research competitors (if UI)
+4. documenter       → Documents flow
+5. [IMPLEMENTATION]
+6. tester           → Creates tests
+7. security-auditor → Validates security
+8. quality-checker  → typecheck + lint + build
+9. final-validator  → Final checklist
+10. domain-updater  → Updates domain docs
+11. commit-manager  → Creates commit
 ```
 
 ### Bug Fix (bug_fix_flow)
 
 ```
-1. analyzer         → Identifica causa raiz
-2. [IMPLEMENTACAO]
-3. tester           → Cria teste de regressao
-4. security-auditor → Valida que fix nao introduz vuln
-5. quality-checker  → typecheck + lint + build
-6. final-validator  → Checklist adaptado
-7. [COMMIT]
+1. analyzer         → Identifies root cause
+2. research         → Researches solutions
+3. [IMPLEMENTATION]
+4. tester           → Creates regression test
+5. security-auditor → Validates fix doesn't introduce vuln
+6. quality-checker  → typecheck + lint + build
+7. final-validator  → Adapted checklist
+8. domain-updater   → Updates domain docs
+9. commit-manager   → Creates commit
 ```
 
 ### Refactor (refactor_flow)
 
 ```
-1. analyzer         → Mapeia dependencias
-2. [IMPLEMENTACAO]
-3. tester           → Atualiza testes
-4. security-auditor → Valida seguranca
+1. analyzer         → Maps dependencies
+2. [IMPLEMENTATION]
+3. tester           → Updates tests
+4. security-auditor → Validates security
 5. quality-checker  → typecheck + lint + build
-6. final-validator  → Checklist adaptado
-7. [COMMIT]
+6. final-validator  → Adapted checklist
+7. domain-updater   → Updates domain docs
+8. commit-manager   → Creates commit
 ```
 
 ### Config/Chore (config_flow)
 
 ```
-1. quality-checker  → Apenas qualidade
-2. [COMMIT]
+1. quality-checker  → Quality only
+2. domain-updater   → Updates domain docs
+3. commit-manager   → Creates commit
 ```
 
 ---
 
-## Comandos
+## Commands
 
-| Comando     | Descricao           | Uso                       |
-| ----------- | ------------------- | ------------------------- |
-| `/feature`  | Inicia nova feature | `/feature [descricao]`    |
-| `/fix`      | Corrige bug         | `/fix [descricao do bug]` |
-| `/validate` | Validacao completa  | `/validate`               |
-| `/research` | Pesquisa topico     | `/research [topico]`      |
+| Command     | Description         | Usage                  |
+| ----------- | ------------------- | ---------------------- |
+| `/feature`  | Start new feature   | `/feature [desc]`      |
+| `/fix`      | Fix a bug           | `/fix [bug desc]`      |
+| `/validate` | Full validation     | `/validate`            |
+| `/research` | Research topic      | `/research [topic]`    |
 
 ---
 
-## Hooks
+## Configuration
 
-### security-check.js
+Project-specific settings are in `.claude/config/`:
 
-Executado ANTES de cada tool call. Bloqueia:
+- `project-config.json` - Stack, structure, commands
+- `domain-mapping.json` - File patterns to domains
+- `quality-gates.json` - Quality check commands
+- `testing-config.json` - Test framework config
+- `security-rules.json` - Security audit rules
 
-- Comandos destrutivos (`rm -rf`, `sudo`, etc)
-- Codigo inseguro (`eval()`, `innerHTML`, etc)
-- Dados sensiveis hardcoded (passwords, API keys)
-- Violacoes de regras do projeto (userId do request, z.any(), etc)
+**IMPORTANT:** Agents read from config files. Update these when adapting to a new project.
 
 ---
 
-## Como Usar
-
-### No Claude Code (Interativo)
-
-Os agentes sao carregados automaticamente quando voce abre o projeto.
-O orchestrator coordena o fluxo baseado no tipo de tarefa.
-
-### Com Claude Agent SDK (Programatico)
-
-```python
-from claude_agent_sdk import ClaudeSDKClient
-
-client = ClaudeSDKClient(
-    setting_sources=["project"]  # Carrega .claude/settings.json
-)
+## Hooks
 
-result = await client.query("Implementar feature X")
-```
+### user-prompt-submit.py
 
----
+Runs BEFORE each prompt. Provides:
+- Agent recommendations based on task
+- Workflow guidance
+- Enforcement reminders
 
-## Regras Garantidas pelos Agentes
+### security-check.js
 
-1. **Seguranca** - security-auditor valida TODAS as regras
-2. **Testes** - tester garante cobertura adequada
-3. **Documentacao** - documenter cria docs obrigatorias
-4. **UI/UX** - ui-ux-reviewer pesquisa competidores
-5. **Qualidade** - quality-checker roda verificacoes
-6. **Conformidade** - final-validator valida TUDO antes do commit
+Blocks dangerous operations:
+- Destructive commands (`rm -rf`, `sudo`, etc)
+- Insecure code patterns
+- Hardcoded sensitive data
 
 ---
 
-## Atualizacao
-
-Ao adicionar novas regras ao projeto:
+## Getting Started
 
-1. Atualizar `/claude.md` com a regra
-2. Atualizar agente relevante em `.claude/agents/`
-3. Atualizar `final-validator.md` com novo item no checklist
-4. Se necessario, adicionar pattern em `hooks/security-check.js`
+1. Configure `.claude/config/project-config.json` for your project
+2. Update `.claude/config/domain-mapping.json` with your domains
+3. Agents will automatically coordinate based on task type