antigravity-ai-kit 2.1.0 → 3.0.1

package/.agent/README.md

@@ -24,10 +24,10 @@ This loads your session context and activates the orchestrator.
 ├── rules.md                # Core governance & identity
 ├── session-state.json      # Machine-readable state
 │
-├── agents/                 # 15 specialized agents
-├── commands/               # 20 slash commands
-├── skills/                 # 14 capability extensions
-├── workflows/              # 8 slash command workflows
+├── agents/                 # 19 specialized agents
+├── commands/               # 31 slash commands
+├── skills/                 # 31 capability extensions
+├── workflows/              # 14 slash command workflows
 ├── hooks/                  # Event-driven automation
 ├── rules/                  # Modular governance
 ├── contexts/               # Mode switching

package/.agent/agents/README.md

@@ -1,7 +1,7 @@
 # Antigravity AI Kit — Agents
 
 > **Purpose**: Specialized sub-agents for task delegation
-> **Count**: 15 Core Agents
+> **Count**: 19 Core Agents
 
 ---
 
@@ -26,6 +26,8 @@ Agents are specialized personas that handle delegated tasks with focused experti
 | 🔍 **Code Reviewer**        | `code-reviewer.md`        | Quality & security review       |
 | 🧪 **TDD Guide**            | `tdd-guide.md`            | Test-driven development         |
 | 🔧 **Build Error Resolver** | `build-error-resolver.md` | Rapid build fixes               |
+| 🖥️ **Backend Specialist**   | `backend-specialist.md`   | Node.js, NestJS, API design     |
+| 🎨 **Frontend Specialist**  | `frontend-specialist.md`  | React, Next.js, UI architecture |
 
 ### Quality & Security Agents
 
@@ -37,20 +39,22 @@ Agents are specialized personas that handle delegated tasks with focused experti
 
 ### Infrastructure Agents
 
-| Agent                     | File                    | Purpose                       |
-| :------------------------ | :---------------------- | :---------------------------- |
-| 📱 **Mobile Developer**   | `mobile-developer.md`   | React Native/Expo development |
-| 🗄️ **Database Architect** | `database-architect.md` | Schema design, queries        |
-| 🚀 **DevOps Engineer**    | `devops-engineer.md`    | CI/CD, deployment             |
+| Agent                        | File                       | Purpose                       |
+| :--------------------------- | :------------------------- | :---------------------------- |
+| 📱 **Mobile Developer**      | `mobile-developer.md`      | React Native/Expo development |
+| 🗄️ **Database Architect**    | `database-architect.md`    | Schema design, queries        |
+| 🚀 **DevOps Engineer**       | `devops-engineer.md`       | CI/CD, deployment             |
+| 🛡️ **Reliability Engineer**  | `reliability-engineer.md`  | SRE, production readiness     |
 
 ### Maintenance & Discovery Agents
 
-| Agent                   | File                  | Purpose            |
-| :---------------------- | :-------------------- | :----------------- |
-| 🧹 **Refactor Cleaner** | `refactor-cleaner.md` | Dead code cleanup  |
-| 📚 **Doc Updater**      | `doc-updater.md`      | Documentation sync |
-| 🧠 **Knowledge Agent**  | `knowledge-agent.md`  | RAG retrieval      |
-| 🔭 **Explorer Agent**   | `explorer-agent.md`   | Codebase discovery |
+| Agent                      | File                     | Purpose                     |
+| :------------------------- | :----------------------- | :-------------------------- |
+| 🧹 **Refactor Cleaner**    | `refactor-cleaner.md`    | Dead code cleanup           |
+| 📚 **Doc Updater**         | `doc-updater.md`         | Documentation sync          |
+| 🧠 **Knowledge Agent**     | `knowledge-agent.md`     | RAG retrieval               |
+| 🔭 **Explorer Agent**      | `explorer-agent.md`      | Codebase discovery          |
+| 📊 **Sprint Orchestrator** | `sprint-orchestrator.md` | Sprint planning & velocity  |
 
 ---
 

package/.agent/agents/architect.md

@@ -5,6 +5,7 @@ model: opus
 authority: design-authority
 reports-to: alignment-engine
 integration: 3-role-architecture
+relatedWorkflows: [orchestrate]
 ---
 
 # Antigravity AI Kit — Architect Agent

package/.agent/agents/backend-specialist.md

@@ -1,3 +1,14 @@
+---
+name: backend-specialist
+description: "Node.js backend architecture, API design, middleware patterns specialist"
+domain: backend
+triggers: [backend, api, server, nodejs, nestjs, express, middleware]
+model: opus
+authority: backend-code
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Backend Specialist Agent
 
 > **Domain**: Node.js backend architecture, API design, middleware patterns, error handling, logging, service layer patterns  

package/.agent/agents/code-reviewer.md

@@ -4,6 +4,7 @@ description: Expert code review specialist ensuring high standards of quality an
 model: opus
 authority: approval-gate
 reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
 ---
 
 # Antigravity AI Kit — Code Reviewer Agent

package/.agent/agents/database-architect.md

@@ -1,3 +1,14 @@
+---
+name: database-architect
+description: "Database design, schema optimization, and query performance specialist"
+domain: database
+triggers: [database, sql, postgresql, schema, migration, query]
+model: opus
+authority: schema-level
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Database Architect
 
 > **Platform**: Antigravity AI Kit

package/.agent/agents/devops-engineer.md

@@ -1,3 +1,14 @@
+---
+name: devops-engineer
+description: "CI/CD, deployment, infrastructure, and monitoring specialist"
+domain: devops
+triggers: [deploy, ci, cd, docker, kubernetes, pipeline]
+model: opus
+authority: infrastructure
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # DevOps Engineer
 
 > **Platform**: Antigravity AI Kit

package/.agent/agents/e2e-runner.md

@@ -4,6 +4,7 @@ description: End-to-end testing specialist using Playwright for comprehensive us
 model: opus
 authority: test-execution
 reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
 ---
 
 # Antigravity AI Kit — E2E Runner Agent

package/.agent/agents/explorer-agent.md

@@ -1,3 +1,14 @@
+---
+name: explorer-agent
+description: "Codebase discovery, architectural analysis, and onboarding specialist"
+domain: discovery
+triggers: [explore, discover, analyze, map, onboard]
+model: opus
+authority: read-only
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Explorer Agent
 
 > **Platform**: Antigravity AI Kit

package/.agent/agents/frontend-specialist.md

@@ -1,3 +1,14 @@
+---
+name: frontend-specialist
+description: "Frontend architecture, React/Next.js patterns, component design specialist"
+domain: frontend
+triggers: [frontend, component, css, react, nextjs, ui, ux]
+model: opus
+authority: frontend-code
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Frontend Specialist Agent
 
 > **Domain**: Frontend architecture, React/Next.js patterns, component design, CSS architecture, accessibility, responsive design  

package/.agent/agents/mobile-developer.md

@@ -1,3 +1,14 @@
+---
+name: mobile-developer
+description: "React Native/Expo mobile development specialist"
+domain: mobile
+triggers: [mobile, react native, expo, ios, android]
+model: opus
+authority: mobile-code
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Mobile Developer
 
 > **Platform**: Antigravity AI Kit

package/.agent/agents/performance-optimizer.md

@@ -1,3 +1,14 @@
+---
+name: performance-optimizer
+description: "Performance profiling, Core Web Vitals, and optimization specialist"
+domain: performance
+triggers: [slow, optimize, speed, bundle, lighthouse, web vitals]
+model: opus
+authority: performance-advisory
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Performance Optimizer
 
 > **Platform**: Antigravity AI Kit

package/.agent/agents/planner.md

@@ -4,6 +4,7 @@ description: Expert planning specialist for feature implementation. Use for comp
 model: opus
 authority: read-only-analysis
 reports-to: alignment-engine
+relatedWorkflows: [plan, orchestrate]
 ---
 
 # Antigravity AI Kit — Planner Agent

package/.agent/agents/refactor-cleaner.md

@@ -4,6 +4,7 @@ description: Dead code cleanup and refactoring specialist. Identifies and remove
 model: opus
 authority: cleanup-only
 reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
 ---
 
 # Antigravity AI Kit — Refactor Cleaner Agent

package/.agent/agents/reliability-engineer.md

@@ -1,3 +1,14 @@
+---
+name: reliability-engineer
+description: "Operational reliability, CI/CD health, and production readiness specialist"
+domain: reliability
+triggers: [reliability, uptime, monitoring, sre, sla, slo, incident]
+model: opus
+authority: reliability-advisory
+reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
+---
+
 # Reliability Engineer Agent
 
 > **Domain**: Operational reliability, CI/CD health, dependency management, production readiness, error budgets, resilience patterns  

package/.agent/agents/security-reviewer.md

@@ -4,6 +4,7 @@ description: Security vulnerability analysis and comprehensive security audit sp
 model: opus
 authority: security-audit
 reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
 ---
 
 # Antigravity AI Kit — Security Reviewer Agent

package/.agent/agents/sprint-orchestrator.md

@@ -1,3 +1,13 @@
+---
+name: sprint-orchestrator
+description: "Sprint planning, velocity tracking, and autonomous task prioritization specialist"
+domain: planning
+triggers: [sprint, velocity, backlog, milestone, retrospective, prioritize]
+model: opus
+authority: sprint-management
+reports-to: alignment-engine
+---
+
 # Sprint Orchestrator Agent
 
 > **Domain**: Sprint planning, velocity tracking, backlog management, retrospective analysis, autonomous task prioritization  

package/.agent/agents/tdd-guide.md

@@ -4,6 +4,7 @@ description: Test-Driven Development specialist enforcing write-tests-first meth
 model: opus
 authority: tdd-enforcement
 reports-to: alignment-engine
+relatedWorkflows: [orchestrate]
 ---
 
 # Antigravity AI Kit — TDD Guide Agent

package/.agent/commands/code-review.md

@@ -2,6 +2,7 @@
 name: code-review
 description: Perform comprehensive code review on files or directories
 invokes: code-reviewer
+workflow: review
 ---
 
 # /code-review

package/.agent/commands/debug.md

@@ -1,5 +1,6 @@
 ---
 description: Debug issues systematically
+workflow: debug
 ---
 
 # /debug Command

package/.agent/commands/deploy.md

@@ -1,5 +1,6 @@
 ---
 description: Deploy application to target environment
+workflow: deploy
 ---
 
 # /deploy Command

package/.agent/commands/help.md

@@ -1,31 +1,252 @@
----
-description: Get help on available commands
----
-
-# /help Command
-
-Show available commands and usage.
-
-## Usage
-
-```
-/help                  # List all commands
-/help <command>        # Detail on specific command
-```
-
-## Examples
-
-```
-/help
-/help plan
-/help verify
-```
-
-## Categories
-
-- **Core**: /plan, /implement, /verify, /status
-- **Development**: /build, /fix, /debug, /refactor
-- **Documentation**: /doc, /adr, /changelog
-- **Git**: /git, /pr, /checkpoint
-- **Quality**: /code-review, /tdd, /security-scan
-- **Workflow**: /cook, /scout, /research
+---
+description: Comprehensive reference for all Antigravity AI Kit capabilities
+---
+
+# /help Command
+
+Your complete guide to the Antigravity AI Kit. Type `/help` for a quick overview, or drill down into specific categories.
+
+## Usage
+
+```
+/help                  # Quick overview of all capabilities
+/help commands         # All 31 slash commands with descriptions
+/help workflows        # All 14 workflows with descriptions
+/help agents           # All 19 AI agents with domains
+/help skills           # All 31 skill modules
+/help rules            # Governance rules
+/help checklists       # Quality gate checklists
+/help cli              # Terminal CLI commands (ag-kit)
+/help <command-name>   # Detail on a specific command (e.g., /help plan)
+```
+
+---
+
+## Quick Overview
+
+**Antigravity AI Kit v3.0.0** — Trust-Grade AI Development Framework
+
+| Category | Count | Description |
+|:---------|:------|:------------|
+| ⌨️ Commands | 31 | Slash commands for every development task |
+| 🔄 Workflows | 14 | Multi-step development lifecycles |
+| 🤖 Agents | 19 | Specialized AI roles for delegation |
+| 🛠️ Skills | 31 | Domain knowledge modules |
+| ⚖️ Rules | 4 | Immutable governance constraints |
+| ✅ Checklists | 3 | Quality gate checklists |
+| ⚙️ Runtime | 21 | Engine modules (governance, reputation, self-healing) |
+
+### Getting Started
+
+```
+/status           → Check your session and project health
+/plan             → Create an implementation plan
+/create           → Build a new feature from scratch
+/review           → Run quality gates before committing
+```
+
+### Recommended Workflow
+
+```
+/brainstorm  →  /plan  →  /create  →  /test  →  /review  →  /deploy
+```
+
+---
+
+## Commands (31)
+
+### Core Workflow
+
+| Command | Description |
+|:--------|:------------|
+| `/plan` | Create structured implementation plan with task breakdown |
+| `/implement` | Execute an approved plan step by step |
+| `/verify` | Run all quality gates (lint, types, tests, security, build) |
+| `/status` | Check project health, session state, and capabilities |
+
+### Feature Development
+
+| Command | Description |
+|:--------|:------------|
+| `/build` | Build a new feature from scratch |
+| `/fix` | Fix linting, type, or build errors |
+| `/debug` | Systematic debugging with hypothesis tracking |
+| `/refactor` | Improve code quality without changing behavior |
+| `/cook` | Full scratch-to-done workflow (plan → build → test → review) |
+| `/design` | UI/UX design specifications and mockups |
+
+### Testing & Quality
+
+| Command | Description |
+|:--------|:------------|
+| `/tdd` | Test-driven development — write tests first, then implement |
+| `/code-review` | Comprehensive code review with security analysis |
+| `/security-scan` | Security audit and vulnerability scan |
+| `/perf` | Performance analysis and optimization |
+| `/eval` | Evaluate metrics and measure quality |
+
+### Documentation & Git
+
+| Command | Description |
+|:--------|:------------|
+| `/doc` | Generate or update documentation |
+| `/adr` | Create Architecture Decision Record |
+| `/changelog` | Generate changelog from commits |
+| `/git` | Git operations with best practices |
+| `/pr` | Create or manage pull requests |
+| `/checkpoint` | Save progress checkpoint for session continuity |
+
+### Exploration & Research
+
+| Command | Description |
+|:--------|:------------|
+| `/scout` | Explore and understand an unfamiliar codebase |
+| `/research` | Research technologies, libraries, or solutions |
+| `/ask` | Ask questions about code, architecture, or patterns |
+
+### Infrastructure & Integration
+
+| Command | Description |
+|:--------|:------------|
+| `/integrate` | Third-party service integration |
+| `/db` | Database schema design and migrations |
+| `/deploy` | Deploy to target environment with pre-flight checks |
+| `/setup` | Configure a new project with Antigravity AI Kit |
+
+### Context Management
+
+| Command | Description |
+|:--------|:------------|
+| `/learn` | Extract reusable patterns from current session (PAAL cycle) |
+| `/compact` | Compress context window for long sessions |
+| `/help` | This reference — show available capabilities |
+
+---
+
+## Workflows (14)
+
+Workflows are multi-step development lifecycles. Use them with the `/` prefix.
+
+| Workflow | Description | Key Steps |
+|:---------|:------------|:----------|
+| `/brainstorm` | Structured ideation and discovery | Socratic questioning → options → decision |
+| `/create` | Build new features from scratch | Scaffold → implement → test → review |
+| `/debug` | Systematic debugging | Reproduce → hypothesize → verify → fix |
+| `/deploy` | Production deployment | Pre-flight → execute → verify → monitor |
+| `/enhance` | Iterative feature improvement | Analyze → plan → implement → validate |
+| `/orchestrate` | Multi-agent task coordination | Decompose → delegate → merge → verify |
+| `/plan` | Implementation planning | Research → design → breakdown → verify |
+| `/preview` | Local dev server management | Start → verify → iterate → stop |
+| `/quality-gate` | Pre-task validation protocol | Market research → gap analysis → ethics review |
+| `/retrospective` | Sprint audit and review | Metrics → findings → action items |
+| `/review` | Quality gate pipeline | Lint → types → tests → security → build |
+| `/status` | Project state overview | Session → git → health → capabilities |
+| `/test` | Systematic test writing | Strategy → write → run → coverage |
+| `/ui-ux-pro-max` | Premium UI/UX design | Style → palette → typography → implement |
+
+---
+
+## Agents (19)
+
+Agents are specialized AI roles. They are automatically activated based on task context, or you can request a specific agent.
+
+| Agent | Domain |
+|:------|:-------|
+| `architect` | System design, DDD, Hexagonal Architecture |
+| `backend-specialist` | Node.js, NestJS, API design |
+| `build-error-resolver` | Rapid build/compile error fixes |
+| `code-reviewer` | Quality + security code review |
+| `database-architect` | Schema design, queries, optimization |
+| `devops-engineer` | CI/CD, Docker, deployment pipelines |
+| `doc-updater` | Documentation synchronization |
+| `e2e-runner` | End-to-end test execution |
+| `explorer-agent` | Codebase discovery and mapping |
+| `frontend-specialist` | React, Next.js, UI architecture |
+| `knowledge-agent` | RAG retrieval and context lookup |
+| `mobile-developer` | React Native, Expo mobile development |
+| `performance-optimizer` | Core Web Vitals, profiling, optimization |
+| `planner` | Task breakdown, Socratic analysis |
+| `refactor-cleaner` | Dead code cleanup, code improvement |
+| `reliability-engineer` | SRE, production readiness, SLA monitoring |
+| `security-reviewer` | Vulnerability analysis, OWASP compliance |
+| `sprint-orchestrator` | Sprint planning, velocity tracking |
+| `tdd-guide` | Test-first development enforcement |
+
+---
+
+## Skills (31)
+
+Skills are domain knowledge modules that agents use. They are loaded automatically based on task context.
+
+| Category | Skills |
+|:---------|:-------|
+| **Architecture** | `architecture`, `api-patterns`, `clean-code`, `database-design`, `docker-patterns` |
+| **Frontend** | `frontend-patterns`, `ui-ux-pro-max`, `mobile-design`, `i18n-localization` |
+| **Backend** | `nodejs-patterns`, `typescript-expert`, `security-practices` |
+| **Testing** | `testing-patterns`, `webapp-testing`, `eval-harness` |
+| **DevOps** | `deployment-procedures`, `git-workflow`, `shell-conventions` |
+| **AI & Orchestration** | `intelligent-routing`, `parallel-agents`, `mcp-integration`, `context-budget`, `behavioral-modes` |
+| **Planning** | `brainstorming`, `plan-writing`, `strategic-compact`, `continuous-learning` |
+| **Performance** | `performance-profiling` |
+| **Scaffolding** | `app-builder` |
+| **Debugging** | `debugging-strategies` |
+| **Verification** | `verification-loop` |
+
+---
+
+## Rules (4)
+
+Rules are immutable governance constraints that all agents must follow.
+
+| Rule | Purpose |
+|:-----|:--------|
+| `coding-style` | Naming conventions, file limits, type safety |
+| `git-workflow` | Conventional commits, atomic changes, branch strategy |
+| `security` | Secret management, input validation, OWASP |
+| `testing` | Test-first, coverage targets, test naming |
+
+---
+
+## Checklists (3)
+
+Checklists are quality gates run at specific lifecycle moments.
+
+| Checklist | When | Key Checks |
+|:----------|:-----|:-----------|
+| `session-start` | Beginning of each session | Read context, verify git, check dependencies |
+| `session-end` | End of each session | Update ROADMAP, CHANGELOG, commit tracking files |
+| `pre-commit` | Before git commit | Tests pass, lint clean, no secrets, build succeeds |
+
+---
+
+## CLI Commands (ag-kit)
+
+Terminal commands available after installing the kit:
+
+| Command | Description |
+|:--------|:------------|
+| `ag-kit init` | Install .agent/ into your project |
+| `ag-kit status` | Show project health dashboard |
+| `ag-kit verify` | Run manifest integrity checks (90 checks) |
+| `ag-kit scan` | Enhanced security scanning |
+| `ag-kit update` | Update to latest version (diff-based, preserves customizations) |
+| `ag-kit heal` | Detect and diagnose CI failures |
+| `ag-kit plugin list` | List installed plugins |
+| `ag-kit plugin install <path>` | Install a plugin |
+| `ag-kit plugin remove <name>` | Remove a plugin |
+| `ag-kit market search <query>` | Search marketplace plugins |
+| `ag-kit market info <name>` | Get marketplace plugin details |
+| `ag-kit market install <name>` | Install from marketplace |
+
+---
+
+## Quick Reference Card
+
+```
+Start here:        /status → /plan → /create → /review
+Debug issues:      /debug → /fix → /verify
+Write tests:       /tdd → /test → /verify
+Deploy:            /review → /deploy
+Learn more:        /help <topic>
+Terminal:          ag-kit verify | ag-kit scan | ag-kit status
+```

package/.agent/commands/plan.md

@@ -2,6 +2,7 @@
 name: plan
 description: Create a comprehensive implementation plan for a feature or change
 invokes: planner
+workflow: plan
 ---
 
 # /plan

package/.agent/commands/status.md

@@ -1,6 +1,7 @@
 ---
 name: status
 description: Display current session status and context
+workflow: status
 ---
 
 # /status

package/.agent/commands/tdd.md

@@ -2,6 +2,7 @@
 name: tdd
 description: Start test-driven development workflow for a component
 invokes: tdd-guide
+workflow: test
 ---
 
 # /tdd

package/.agent/contexts/brainstorm.md

@@ -0,0 +1,26 @@
+---
+mode: brainstorm
+description: "Ideas-only exploration mode — Socratic discovery without implementation"
+constraints: [no-code, no-modifications, socratic-only]
+agent-focus: [planner, explorer-agent]
+---
+
+# Brainstorm Mode Context
+
+## Behavioral Rules
+
+- Generate ideas and alternatives only — never write code
+- Ask Socratic questions to clarify requirements
+- Present minimum 3 options for every decision point
+- Support each option with evidence or industry precedent
+- Never commit to a single approach without user confirmation
+
+## Loaded Skills
+
+- `brainstorming` — Socratic discovery protocol
+
+## Exit Criteria
+
+- Requirements are clarified with concrete acceptance criteria
+- At least 3 viable approaches documented with trade-offs
+- User selects preferred approach for planning phase

package/.agent/contexts/debug.md

@@ -0,0 +1,28 @@
+---
+mode: debug
+description: "Systematic investigation mode — minimal changes, preserve evidence"
+constraints: [evidence-first, minimal-changes, root-cause-required]
+agent-focus: [build-error-resolver, tdd-guide]
+---
+
+# Debug Mode Context
+
+## Behavioral Rules
+
+- Identify root cause before applying any fix
+- Preserve all evidence (logs, stack traces, reproduction steps)
+- Make minimal, surgical changes — one fix per iteration
+- Always verify the fix resolves the original issue
+- Add regression tests to prevent recurrence
+
+## Loaded Skills
+
+- `debugging-strategies` — Systematic hypothesis testing
+- `testing-patterns` — Regression test creation
+
+## Exit Criteria
+
+- Root cause identified and documented
+- Fix applied with minimal code changes
+- Regression test added and passing
+- No new issues introduced (full test suite passes)