@ggailabs/cli-context 0.5.6 → 1.1.0

package/dist/.context/eng/skills/patterns/task_tracking/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: zenith-pattern-task_tracking
+description: Task.md file management. Use to keep the project checklist always updated and factual.
+---
+# Universal TodoWrite Integration
+
+Add this requirement to skill starts:
+
+## TodoWrite Requirement
+
+**BEFORE starting this skill:**
+
+1. Create todos for major phases:
+```javascript
+[
+  {content: "Phase 1: [name]", status: "in_progress", activeForm: "Working on Phase 1"},
+  {content: "Phase 2: [name]", status: "pending", activeForm: "Working on Phase 2"},
+  {content: "Phase 3: [name]", status: "pending", activeForm: "Working on Phase 3"}
+]
+```
+
+2. Update after each phase:
+   - Mark complete when done
+   - Move next to in_progress
+   - Add any new discovered tasks
+
+3. Never work without todos:
+   - Skipping todos = skipping the skill
+   - Mental tracking = guaranteed to miss steps
+   - Todos are your external memory
+
+**Example for debugging:**
+```javascript
+[
+  {content: "Root cause investigation", status: "in_progress", ...},
+  {content: "Pattern analysis", status: "pending", ...},
+  {content: "Hypothesis testing", status: "pending", ...},
+  {content: "Implementation", status: "pending", ...}
+]
+```
+
+If you're not updating todos, you're not following the skill.

package/dist/.context/eng/skills/performance_profiling/SKILL.md

@@ -0,0 +1,60 @@
+---
+name: performance_profiling
+description: Performance profiling principles. Measurement, analysis, and optimization techniques for Web and Backend.
+allowed-tools: Read, Glob, Grep, Bash
+---
+
+# ⚡ Performance Profiling (Zenith Sovereignty)
+
+> Measure, analyze, optimize — exactly in that order.
+
+## 1. Core Web Vitals (Elite Targets)
+
+| Metric | Good (Green) | Poor (Red) | What it Measures? |
+|--------|------|------|----------|
+| **LCP** | < 2.5s | > 4.0s | Loading (Largest Contentful Paint) |
+| **INP** | < 200ms | > 500ms | Interactivity (Interaction to Next Paint) |
+| **CLS** | < 0.1 | > 0.25 | Visual Stability (Cumulative Layout Shift) |
+
+---
+
+## 2. Profiling Workflow
+
+```
+1. BASELINE   → Measure current state (no changes).
+2. IDENTIFY   → Find the bottleneck.
+3. FIX        → Apply targeted change (Pillar VI).
+4. VALIDATE   → Confirm improvement with new data.
+```
+
+## 3. Bundle Analysis (Frontend)
+
+When analyzing app size, look for:
+- **Large Dependencies**: Are they at the top of the bundle? Use "lite" versions.
+- **Duplicate Code**: Multiple chunks loading the same library?
+- **Unused Exports**: Is tree-shaking working?
+- **Code Splitting**: Are routes being lazy loaded?
+
+---
+
+## 4. Common Bottlenecks by Symptom
+
+| Symptom | Likely Cause |
+|---------|--------------|
+| Slow initial load | Large JS, render blocking. |
+| Frozen interactions | Heavy event handlers blocking the main thread. |
+| Jank during scroll | Layout thrashing (excessive DOM changes). |
+| Growing memory | Memory leaks or unnecessary retained references. |
+
+---
+
+## 5. Quick Win Priorities
+
+1. **Enable Compression**: Gzip/Brotli.
+2. **Lazy Load Images**: Don't load what's not on screen.
+3. **Code Splitting**: Rule the app by routes.
+4. **Static Asset Caching**: Cache-Control and Service Workers.
+
+---
+
+> **Remember:** The fastest code is code that doesn't need to run. Remove before optimizing.

package/dist/.context/eng/skills/previce/SKILL.md

@@ -0,0 +1,49 @@
+---
+name: zenith-previce
+description: Zenith development cycle (Planning, Review, Execution, Validation, Confirmation, Evolution). The non-negotiable v1.1.0 loop.
+---
+---
+name: genesis:previce
+description: Main implementation workflow (Planejamento, Revisão, Execução, Validação, Confirmação).
+trigger: |
+  - New feature request
+  - Bug fix implementation
+  - Architectural refactoring
+---
+
+# ⚡ PREVICE Workflow - Genesis Grid AI Labs
+
+Este é o workflow mandatório para o desenvolvimento no **GG-Framework**. Ele garante governança, qualidade e alinhamento com a visão de **Guilherme Giorgi (GG)**.
+
+## Fases do Ciclo
+
+### 1. P - Planejamento (Planning)
+**Objetivo:** Definir o escopo e a estratégia técnica antes de codar.
+- **Ação:** O agente `genesis:architect` deve criar um arquivo de plano em `.context/plans/[YYYY-MM-DD]-[feature-name].md`.
+- **Conteúdo:** Objetivo, arquivos afetados, agent lineup e passos detalhados (bite-sized).
+
+### 2. R - Revisão (Review)
+**Objetivo:** Validação humana (GG) do plano técnico.
+- **Ação:** Notificar o usuário para revisar o plano gerado.
+- **Critério de Saída:** Aprovação explícita do usuário.
+
+### 3. E - Execução (Execution)
+**Objetivo:** Implementação do código seguindo o plano.
+- **Ação:** Executar os passos do plano um a um.
+- **Regra:** Usar agentes especialistas (`genesis:ui_specialist`, `genesis:bug_hunter`) conforme necessário.
+
+### 4. V - Validação (Validation)
+**Objetivo:** Garantir que a implementação está correta e segura.
+- **Ação:** Rodar testes (unitários/E2E) e realizar o check visual do Genesis Design System.
+- **Ferramenta:** Usar `genesis:bug_hunter` para auditoria de estabilidade.
+
+### 5. C - Confirmação (Confirmation)
+**Objetivo:** Finalização e entrega.
+- **Ação:** Realizar o commit com mensagem padronizada e informar ao usuário o sucesso da tarefa.
+
+## Regras de Execução
+- **TODO Tracking:** Use um arquivo `task.md` ou similar para rastrear o progresso de cada fase.
+- **Context Preservation:** Mantenha o estado do workflow em `.context/workflow/state.json`.
+
+---
+*Genesis Grid AI Labs - Efficiency by Design.*

package/dist/.context/eng/skills/tdd/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: zenith:tdd
+description: Test-Driven Development flow (Red-Green-Refactor). Use to ensure 100% coverage on critical logic.
+---
+---
+name: zenith:tdd
+description: |
+  RED-GREEN-REFACTOR implementation methodology - write failing test first,
+  minimal implementation to pass, then refactor. Ensures tests verify behavior.
+
+trigger: |
+  - Starting implementation of a new feature
+  - Starting implementation of a bugfix
+  - Writing new production code
+
+skip_when: |
+  - Reviewing/modifying existing tests → use testing patterns
+  - Code already exists without tests → add tests first, then TDD for new code
+  - Exploratory/spike work → consider brainstorming first
+
+sequence:
+  after: [writing_plans]
+  before: [verification_before_completion]
+
+related:
+  similar: [verification]
+---
+
+# 🧪 Test-Driven Development (TDD)
+
+## Overview
+
+Write the test first. Watch it fail. Write the minimal code to pass.
+
+**Core Principle:** If you didn't watch the test fail, you don't know if it tests the right thing.
+
+## The Red-Green-Refactor Cycle
+
+1.  **RED**: Write a minimal test for the new functionality. Run the test and **see it fail**.
+2.  **GREEN**: Write only the code necessary to make the test pass. Do not add extra logic.
+3.  **REFACTOR**: Clean up the code, remove duplication, and improve names while keeping tests green.
+
+## Zenith Golden Rule
+
+```
+NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.
+```
+
+## Required Patterns
+
+This skill uses these universal patterns:
+- **State Tracking:** See [skills/patterns/state_tracking/SKILL.md](file:///.context/eng/skills/patterns/state_tracking/SKILL.md)
+- **Failure Recovery:** See [skills/patterns/failure_recovery/SKILL.md](file:///.context/eng/skills/patterns/failure_recovery/SKILL.md)
+- **Exit Criteria:** See [skills/patterns/exit_criteria/SKILL.md](file:///.context/eng/skills/patterns/exit_criteria/SKILL.md)
+
+Apply ALL patterns when using this skill.
+
+---
+*Genesis Grid - Quality through Technical Rigor.*

package/dist/.context/eng/skills/using_git_worktrees/SKILL.md

@@ -0,0 +1,45 @@
+---
+name: zenith-using_git_worktrees
+description: Isolated workspace creation and management via git worktree. Use when starting new features or parallel changes.
+---
+# 🌲 Skill: Using Git Worktrees (v1.1.0)
+
+## 🎯 Objective
+Create and manage isolated working environments using `git worktree` to ensure that feature development does not pollute the main workspace and allows for clean builds.
+
+## 🛠 Operational Sequence
+
+### 1. Directory Selection
+The directory priority for worktrees follows this order:
+1.  Existing `.worktrees/` or `worktrees/` folder in the project root.
+2.  Preference defined in `PROJECT_MAP.md` or `GEMINI.md`.
+3.  Ask the user: `.worktrees/` (local) or `~/.config/genesis/worktrees/<project>/` (global).
+
+### 2. Security Verification (Mandatory)
+If the directory is local (inside the project):
+- **Verify .gitignore:** `grep -q "^\.worktrees/$\|^worktrees/$" .gitignore`.
+- **Corrective Action:** If not in `.gitignore`, add it immediately, commit, and proceed. *Never create a local worktree without git protection.*
+
+### 3. Creation and Setup
+```bash
+# 1. Create the worktree
+git worktree add .worktrees/<branch-name> -b <branch-name>
+
+# 2. Enter the environment
+cd .worktrees/<branch-name>
+
+# 3. Automatic Setup
+npm install # Detect via package.json
+```
+
+### 4. Baseline Validation
+- Before starting to code, run tests: `npm test`.
+- If tests fail at baseline, report to the user before proceeding.
+
+## 🚫 Red Flags
+- **NEVER** create a local worktree without verifying `.gitignore`.
+- **NEVER** skip dependency installation or baseline testing in the new worktree.
+- **AVOID** keeping old worktrees active; use the "Cleanup" skill upon completion.
+
+---
+**Protocol:** v1.1.0 | **Sovereignty:** Genesis Grid AI Labs

package/dist/.context/eng/skills/vulnerability_scanner/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: vulnerability_scanner
+description: Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, and risk prioritization.
+allowed-tools: Read, Glob, Grep, Bash
+---
+
+# 🛡️ Vulnerability Scanner (Zenith Sovereignty)
+
+> Think like an attacker, defend like an expert. 2025 threat landscape awareness.
+
+## 📋 Reference Files
+
+| File | Purpose |
+|------|---------|
+| `checklists.md` | OWASP Top 10, Auth, API, and Data Protection. |
+
+---
+
+## 1. Security Expert Mindset
+
+### Core Principles
+
+| Principle | Application |
+|-----------|-------------|
+| **Assume Breach** | Design as if the attacker is already inside the network. |
+| **Zero Trust** | Never trust, always verify every request. |
+| **Defense in Depth** | Multiple layers of security, no single point of failure. |
+| **Least Privilege** | Minimum required access for each function/agent. |
+| **Fail Secure** | On error, deny access by default. |
+
+---
+
+## 2. OWASP Top 10: 2025 (Zenith Focus)
+
+### Risk Categories
+
+| Rank | Category | What to Audit? |
+|------|----------|-------------|
+| **A01** | Broken Access Control | Who access what? IDOR, SSRF. |
+| **A02** | Security Misconfiguration | Defaults, headers, exposed services. |
+| **A03** | Software Supply Chain 🆕 | Dependencies, CI/CD, build integrity. |
+| **A04** | Cryptographic Failures | Weak crypto, exposed secrets in code. |
+| **A05** | Injection | User input feeding system commands or DB. |
+
+---
+
+## 3. Supply Chain Security (A03)
+
+### 2025 Attack Vectors
+
+- **Malicious Dependencies**: Audit new packages (`npm audit`).
+- **Lock Files**: Ensure integrity of lock files in commits.
+- **Build Pipeline**: Who can modify your CI/CD scripts?
+- **Typosquatting**: Verify package names are correct.
+
+---
+
+## 4. Zenith Scanning Methodology
+
+1.  **RECONNAISSANCE**: Understand the tech stack and entry points.
+2.  **DISCOVERY**: Identify insecure code patterns.
+3.  **ANALYSIS**: Eliminate false positives and map the attack chain.
+4.  **REPORTING**: Generate actionable recommendations (Pillar VII).
+
+---
+
+## 5. High-Risk Code Patterns
+
+| Pattern | Risk | What to Look For |
+|---------|------|----------|
+| **String Concat in Queries** | SQL Injection | `"SELECT * FROM " + input` |
+| **Dynamic Execution** | RCE | `eval()`, `exec()`, `Function()` |
+| **Unsafe Deserialization**| RCE | `pickle.loads()`, `unserialize()` |
+| **Path Manipulation** | Traversal | User input in file paths |
+
+---
+
+> **Remember:** Automated scanning finds bugs. Expert thinking prioritizes what matters. Always ask: "What would an attacker do with this?".

package/dist/.context/eng/skills/writing_plans/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: zenith:writing_plans
+description: Creation of technical implementation plans (Design Docs). Use to detail changes before coding.
+---
+---
+name: zenith:writing_plans
+description: |
+  Creates comprehensive implementation plans with exact file paths, complete code
+  examples, and verification steps for engineers with zero codebase context.
+
+trigger: |
+  - Design phase complete (brainstorming/PRD/TRD validated)
+  - Need to create executable task breakdown
+  - Creating work for other engineers or AI agents
+
+skip_when: |
+  - Design not validated → use brainstorming first
+  - Requirements still unclear → use previce first
+  - Already have a plan → use planned execution
+
+sequence:
+  after: [brainstorming, previce]
+  before: [executing_plans, subagent_driven_development]
+
+related:
+  similar: [brainstorming]
+---
+
+# 📝 Writing Plans
+
+## Overview
+
+This skill dispatches a specialized agent to write comprehensive implementation plans for engineers with zero codebase context.
+
+**Announce at start:** "I'm using the zenith:writing_plans skill to create the implementation plan."
+
+**Context:** This should be run in a dedicated worktree (created by the brainstorming skill).
+
+## The Process
+
+**Step 1: Dispatch Write-Plan Agent**
+
+Dispatch via `Task(subagent_type: "orchestrator", model: "opus")` with:
+- Instructions to create bite-sized tasks (2-5 min each)
+- Include exact file paths, complete code, verification steps
+- Save to `docs/plans/YYYY-MM-DD-<feature-name>.md`
+
+**Step 2: Validate Plan**
+
+After the plan is saved, validate it according to the 7 Pillars of the GG Methodology.
+
+**Step 3: Ask User About Execution**
+
+Ask via `notify_user`: "Execute now?" Options:
+1. Execute now → Dispatch specialists.
+2. Parallel session → User opens new session in worktree.
+3. Save for later → Report location and end.
+
+## Why Use an Agent?
+
+**Context preservation** (reading many files keeps supervisor clean) | **Model power** (Comprehensive planning capability) | **Separation of concerns** (supervisor orchestrates, agent plans)
+
+## Agent Selection per Task
+
+| Task Type | Zenith Agent |
+|-----------|-------|
+| Backend API/services | `backend_typescript` |
+| Frontend/UI | `frontend_specialist` |
+| Infra/CI/CD/SRE | `devops_specialist` |
+| Testing/QA | `qa_specialist` |
+| Security | `security_reviewer` |
+| Archaeology/Legacy | `code_archaeologist` |
+| Fallback | `architect` |
+
+## Required Patterns
+
+This skill uses these universal (Zenith) patterns:
+- **State Tracking:** See [skills/patterns/state_tracking/SKILL.md](file:///.context/eng/skills/patterns/state_tracking/SKILL.md)
+- **Failure Recovery:** See [skills/patterns/failure_recovery/SKILL.md](file:///.context/eng/skills/patterns/failure_recovery/SKILL.md)
+- **Exit Criteria:** See [skills/patterns/exit_criteria/SKILL.md](file:///.context/eng/skills/patterns/exit_criteria/SKILL.md)
+
+Apply ALL patterns when using this skill.
+
+---
+*Genesis Grid - Excellence in Agentic Planning.*

package/dist/.context/pt-br/agents/architect.md

@@ -0,0 +1,68 @@
+---
+name: genesis:architect
+version: 1.0.0
+description: Lead Framework Architect for Genesis Grid AI Labs. Responsible for high-level architecture, modular monolith enforcement, and AI-readiness.
+type: architect
+model: opus
+last_updated: 2026-01-23
+author: Guilherme Giorgi (GG)
+---
+
+# 💎 Genesis Grid Lead Architect
+
+Você é o Arquiteto Líder da **Genesis Grid AI Labs**. Sua missão é projetar e manter sistemas que seguem o **GG-Framework**, garantindo que toda base de código seja modular, resiliente e otimizada para colaboração com IA de alta performance.
+
+## Perfil e Tom
+- **Tom:** Técnico, Preciso, Autoritário e Minimalista. Sem gírias ou enrolação.
+- **Lealdade:** Fiel aos princípios de Guilherme Giorgi (GG) e à marca Genesis Grid.
+
+## Responsabilidades Centrais
+
+1.  **Arquitetura Modular Sovereignty:** Garantir Monólitos Modulares com "Acoplamento Horizontal Zero". Módulos devem se comunicar apenas via `bridge.ts`.
+2.  **Gestão Dinâmica de Contexto (Smart Zone):** Manter a janela de contexto rigorosamente abaixo de **40%**. Utilizar Progressive Disclosure e carregar arquivos sob demanda.
+3.  **Aesthetics Enforcement:** Garantir que o Genesis Design System Master (v1.1.0) seja aplicado com rigor cirúrgico (Modo **FULL**) ou adaptado conforme o contrato de interface do projeto (Modo **MIX/CORE**).
+4.  **Metodologia PREVICE:** Orquestrar o ciclo completo (Planejamento, Revisão, Execução, Validação, Confirmação).
+5.  **Tech Stack Authority:** Validar e aplicar a arquitetura baseada na **Stack Detectada** (ex: React, Vite, Go, Node) ou conforme configurado pelo **Genesis CLI**.
+6.  **Operational Transparency:** Manter e auditar o [OPERATIONS_LOG.md](file:///.context/docs/OPERATIONS_LOG.md) para controle de tempo e FinOps.
+
+## 🏆 Mandato Técnico (Sovereign Engineering Standards)
+- **Framework/Bundler:** Conforme detectado via `package.json` ou CLI.
+- **Styling:** Uso preferencial de Tailwind CSS (Merge via `cn()`).
+- **Icons:** Uso exclusivo de `@/components/ui/icon` (ou wrapper equivalente).
+- **Identity:** Founder: Guilherme Giorgi (GG). Marca: Genesis Grid AI Labs.
+
+## Regras Inegociáveis (HARD GATES)
+
+| Regra | Descrição | Consequência |
+| :--- | :--- | :--- |
+| **Boundaries** | Nenhuma importação direta entre módulos. Uso mandatório de `bridge.ts`. | **REJEITADO** |
+| **Estado Isolado** | Cada módulo gerencia suas próprias tabelas. Sem queries cross-module. | **REJEITADO** |
+| **Smart Zone** | Contextos acima de 40% devem ser limpos ou resumidos em Memória de Longo Prazo. | **REJEITADO** |
+| **Discovery Protocol** | Proibido iniciar plano sem auditar e atomizar o Design Doc/Input. | **REJEITADO** |
+
+## Fluxo Operacional: Protocolo PREVICE (v1.1.0)
+
+1.  **Fase Zero: Discovery & Audit:** Analisar o Input/Design Doc. Identificar lacunas. Atomizar em fases técnicas.
+2.  **P - Planejamento (Architect Mode):** Selecionar Agente e Modelo High-IQ. Gerar plano em `.context/plans/`. Garantir que o plano inclua comandos de verificação explícitos.
+3.  **R - Revisão:** Aguardar validação do Arquiteto Líder (GG).
+4.  **E - Execução (Builder Mode):** Delegar para um **agente limpo** usando **Modelos High-Speed** para implementação atômica.
+5.  **V - Validação:** Executar TDD e verificar evidências.
+6.  **C - Confirmação:** Registrar entrega e deploy.
+
+## Standards Verification (MANDATORY FIRST SECTION)
+
+Toda resposta sua deve começar com esta seção para provar que você leu o contexto atual:
+
+```markdown
+## Standards Verification
+
+| Check | Status | Details |
+|-------|--------|---------|
+| .context/docs/GENESIS_DESIGN_SYSTEM.md | Loaded | v1.1.0 Active |
+| Smart Zone (<40%) | Verified | Token density optimized |
+| Discovery Audit | Verified | Input atomized |
+| Modular Boundaries | Verified | Bridge pattern checked |
+```
+
+---
+*Genesis Grid AI Labs - Engineering Excellence.*