class-ai-agent 1.4.1 → 1.5.0

package/.agents/workflows/test.md

@@ -0,0 +1,213 @@
+---
+description: "Write tests using TDD patterns — tests are proof of correctness"
+---
+
+# /test — Test-Driven Development
+
+> "Tests are proof, not afterthought."
+
+## Purpose
+
+Write tests that prove code works correctly. Use the RED-GREEN-REFACTOR cycle for new features and the Prove-It pattern for bug fixes.
+
+## For New Features: RED-GREEN-REFACTOR
+
+### RED: Write Failing Test First
+
+```javascript
+describe('UserService.findById', () => {
+  it('should return user when found', async () => {
+    // Arrange
+    const userId = 'user-123';
+    
+    // Act
+    const user = await userService.findById(userId);
+    
+    // Assert
+    expect(user).toBeDefined();
+    expect(user.id).toBe(userId);
+  });
+
+  it('should throw NotFoundError when user does not exist', async () => {
+    await expect(userService.findById('non-existent'))
+      .rejects.toThrow(NotFoundError);
+  });
+});
+```
+
+Run tests — **they should fail** (proves nothing is implemented yet).
+
+### GREEN: Write Minimal Code to Pass
+
+```javascript
+async findById(id: string): Promise<User> {
+  const user = await this.db.user.findUnique({ where: { id } });
+  if (!user) throw new NotFoundError('User not found');
+  return user;
+}
+```
+
+Run tests — **they should pass**.
+
+### REFACTOR: Improve While Green
+
+Clean up code while keeping tests passing:
+- Better naming
+- Extract helpers
+- Remove duplication
+
+---
+
+## For Bug Fixes: Prove-It Pattern
+
+### Step 1: Write Test That Reproduces the Bug
+
+```javascript
+it('should not duplicate items when adding to cart twice', async () => {
+  // This test should FAIL with the current buggy code
+  await cart.addItem('product-1', 1);
+  await cart.addItem('product-1', 1);
+  
+  expect(cart.items).toHaveLength(1);
+  expect(cart.items[0].quantity).toBe(2);
+});
+```
+
+### Step 2: Verify Test Fails
+
+Run the test — confirm it **fails** (proving the bug exists).
+
+### Step 3: Fix the Bug
+
+```javascript
+async addItem(productId: string, quantity: number) {
+  const existing = this.items.find(i => i.productId === productId);
+  if (existing) {
+    existing.quantity += quantity;  // Fix: increment instead of duplicate
+  } else {
+    this.items.push({ productId, quantity });
+  }
+}
+```
+
+### Step 4: Verify Test Passes
+
+Run the test — confirm it **passes** (proving the fix works).
+
+### Step 5: Run Full Suite
+
+```bash
+npm test  # Ensure no regressions
+```
+
+---
+
+## Test Pyramid
+
+| Level | Percentage | Speed | Scope |
+|-------|------------|-------|-------|
+| **Unit** | 80% | ms | Single function, no I/O |
+| **Integration** | 15% | seconds | API + DB, component interactions |
+| **E2E** | 5% | minutes | Full user flows |
+
+---
+
+## Writing Good Tests
+
+### Arrange-Act-Assert Pattern
+
+```javascript
+it('should calculate total with discount', () => {
+  // Arrange — setup
+  const cart = new Cart();
+  cart.addItem({ price: 100 });
+  cart.applyDiscount(10);
+
+  // Act — execute
+  const total = cart.calculateTotal();
+
+  // Assert — verify
+  expect(total).toBe(90);
+});
+```
+
+### DAMP Over DRY
+
+Tests should be **Descriptive And Meaningful Phrases**. Each test reads independently:
+
+```javascript
+// ✅ DAMP — clear and independent
+it('should reject password shorter than 8 characters', () => {
+  const result = validatePassword('short');
+  expect(result.valid).toBe(false);
+  expect(result.error).toBe('Password must be at least 8 characters');
+});
+
+// ❌ Too DRY — requires reading shared setup
+it('should reject short password', () => {
+  expect(validate(shortPassword)).toBe(false);
+});
+```
+
+### Descriptive Test Names
+
+```javascript
+// ✅ Good — describes behavior
+'should return 404 when user is not found'
+'should increment quantity when adding existing product'
+'should send welcome email after registration'
+
+// ❌ Bad — vague
+'works correctly'
+'handles error'
+'test user'
+```
+
+### One Behavior Per Test
+
+```javascript
+// ✅ Good — focused
+it('should validate email format', () => { ... });
+it('should require email field', () => { ... });
+
+// ❌ Bad — testing multiple things
+it('should validate email', () => {
+  expect(validate('')).toBe(false);      // required
+  expect(validate('bad')).toBe(false);   // format
+  expect(validate('a@b.c')).toBe(true);  // valid
+});
+```
+
+---
+
+## Test Doubles Preference
+
+```
+1. Real implementations (best)
+2. In-memory fakes (test DB, fake filesystem)
+3. Stubs (canned responses)
+4. Mocks (verify interactions — use sparingly)
+```
+
+---
+
+## Anti-Patterns to Avoid
+
+| Anti-Pattern | Problem | Fix |
+|--------------|---------|-----|
+| Testing internals | Breaks on refactor | Test inputs/outputs only |
+| Flaky tests | Erodes trust | Use deterministic data, isolate state |
+| Over-mocking | False confidence | Prefer real implementations |
+| Snapshot abuse | Large diffs ignored | Use for rare cases only |
+| Shared state | Tests affect each other | Reset state in beforeEach |
+
+---
+
+## Verification Checklist
+
+- [ ] All new behaviors have tests
+- [ ] Bug fixes have reproduction tests
+- [ ] Test names describe behavior
+- [ ] No skipped or disabled tests
+- [ ] Coverage maintained or improved
+- [ ] Full test suite passes

package/.cursor/rules/cursor-overview.mdc

@@ -33,10 +33,11 @@ Supporting prompts: `debug`, `simplify`, `fix-issue`, `handoff`, `resume` in `.c
 
 Specialized instructions live in **`.cursor/agents/`**. In Cursor, **@ mention** the file you want (e.g. `@.cursor/agents/code-reviewer.md`) when you need that role.
 
-## Relation to `.claude/` and `.kiro/`
+## Relation to `.claude/`, `.kiro/`, and Antigravity
 
 - **`.claude/`** — Claude Code
 - **`.cursor/`** — Cursor
 - **`.kiro/`** — Kiro (steering + MCP; sync from `.cursor/` via `npm run sync:all`)
+- **`.agents/`** + **`GEMINI.md`** — Antigravity (workflows, skills; sync from `.cursor/` via `npm run sync:all`)
 
-Keep all three aligned when you change workflows or standards.
+Keep all four trees aligned when you change workflows or standards. After editing `.cursor/`, run `npm run sync:all`.

package/.kiro/steering/kiro-overview.md

@@ -33,6 +33,6 @@ Supporting prompts: `debug`, `simplify`, `fix-issue`, `handoff`, `resume` in `.k
 
 Specialized instructions live in **`.kiro/agents/`**. Reference files in chat (paste or attach).
 
-## Relation to `.claude/` and `.cursor/`
+## Relation to `.claude/`, `.cursor/`, and Antigravity
 
-Keep all three trees aligned when you change workflows or standards. After editing `.cursor/`, run `npm run sync:all`.
+Keep all four trees aligned when you change workflows or standards. After editing `.cursor/`, run `npm run sync:all`.

package/AGENTS.md

@@ -7,6 +7,7 @@ Project guidance for AI coding agents:
 | **Cursor** | [`.cursor/CURSOR.md`](.cursor/CURSOR.md) |
 | **Kiro** | [`.kiro/KIRO.md`](.kiro/KIRO.md) |
 | **Claude Code** | [`.claude/CLAUDE.md`](.claude/CLAUDE.md) |
+| **Antigravity** | [`GEMINI.md`](GEMINI.md) |
 
 ## Quick start (any tool)
 
@@ -22,15 +23,17 @@ Project guidance for AI coding agents:
 | **Cursor** | `.cursor/CURSOR.md` | `@.cursor/commands/build.md` | `@.cursor/agents/backend.md` |
 | **Claude Code** | `.claude/CLAUDE.md` | `/build` slash command | reference `.claude/agents/backend.md` |
 | **Kiro** | `.kiro/KIRO.md` | `.kiro/commands/build.md` (paste or attach) | reference `.kiro/agents/backend.md` |
+| **Antigravity** | `GEMINI.md` | `/build` workflow (`.agents/workflows/build.md`) | reference `.agents/agents/backend.md` |
 
 ## Layout
 
 - **Cursor:** `.cursor/rules/` (`.mdc`), `.cursor/commands/`, `.cursor/mcp.json`
 - **Kiro:** `.kiro/steering/` (`*.md`), `.kiro/commands/`, `.kiro/settings/mcp.json`
 - **Claude Code:** `.claude/rules/`, `.claude/commands/`
+- **Antigravity:** `.agents/workflows/`, `.agents/skills/`, `.agent/rules/`, `GEMINI.md` (MCP: user-level `~/.gemini/antigravity/mcp_config.json`)
 
 **Cross-tool continuity:** committed [`.agent/SESSION.md`](.agent/README.md) — use `/resume` at session start and `/handoff` at session end (see hub docs and `.agent/README.md`).
 
 ## Maintainers
 
-Keep **`.claude/`**, **`.cursor/`**, and **`.kiro/`** in sync when you change workflows or standards. After editing **`.cursor/`** (canonical), run **`npm run sync:all`** to refresh `.claude/` and `.kiro/`. To refresh vendored Supabase skills from upstream, run **`npm run sync:supabase-skills`**.
+Keep **`.claude/`**, **`.cursor/`**, **`.kiro/`**, and the Antigravity layout in sync when you change workflows or standards. After editing **`.cursor/`** (canonical), run **`npm run sync:all`** to refresh `.claude/`, `.kiro/`, `.agents/`, `.agent/rules/`, and `GEMINI.md`. To refresh vendored Supabase skills from upstream, run **`npm run sync:supabase-skills`**.

package/GEMINI.md

@@ -0,0 +1,152 @@
+# Antigravity AI agent configuration
+
+## Overview
+
+This project uses **Google Antigravity** with the same structured workflows, specialized agent personas, and coding standards as **`.cursor/`**, **`.claude/`**, and **`.kiro/`**. Antigravity-specific files live under **`.agents/`**, **`.agent/rules/`**, and this hub (**`GEMINI.md`**).
+
+Root **`AGENTS.md`** provides cross-tool rules read by Antigravity, Cursor, and Claude Code. **`GEMINI.md`** holds Antigravity-specific overrides and takes precedence over `AGENTS.md` when rules conflict.
+
+---
+
+## Development workflow
+
+Follow this workflow for feature development:
+
+```
+/spec  →  /plan  →  /build  →  /test  →  /review  →  Ship
+```
+
+| Phase | Workflow | Purpose |
+|-------|----------|---------|
+| **Define** | `.agents/workflows/spec.md` (`/spec`) | PRD: objectives, scope, boundaries |
+| **Plan** | `.agents/workflows/plan.md` (`/plan`) | Vertical slices, acceptance criteria |
+| **Build** | `.agents/workflows/build.md` (`/build`) | Incremental implementation, TDD |
+| **Verify** | `.agents/workflows/test.md` (`/test`) | Tests and verification |
+| **Review** | `.agents/workflows/review.md` (`/review`) | Five-axis review before merge |
+| **Ship** | `.agents/workflows/deploy.md` (`/deploy`) | Build, test, deploy |
+
+### Supporting workflows
+
+| File | Purpose |
+|------|---------|
+| `workflows/debug.md` (`/debug`) | Systematic diagnosis |
+| `workflows/simplify.md` (`/simplify`) | Reduce complexity, same behavior |
+| `workflows/fix-issue.md` (`/fix-issue`) | Analyze and fix reported issues |
+| `workflows/handoff.md` (`/handoff`) | End session — update `.agent/SESSION.md` for cross-tool continuity |
+| `workflows/resume.md` (`/resume`) | Start session — load `.agent/SESSION.md` and continue prior work |
+| `workflows/publish-npm.md` | **Maintainers:** draft release notes, bump version, update README, publish to npm |
+
+**How to use:** Type the slash command (e.g. `/build`) in Antigravity, or open the workflow file and paste/attach in chat.
+
+---
+
+## Core principles
+
+- **TDD** — Failing tests first, then implementation (`.agents/skills/tdd/`)
+- **Incremental implementation** — Small vertical slices (`.agents/skills/incremental-implementation/`)
+- **Five-axis review** — Correctness, readability, architecture, security, performance (`.agents/skills/code-review/`)
+
+---
+
+## Mandatory standards (rules)
+
+Project standards are **`.agent/rules/*.md`**. They use YAML frontmatter:
+
+- **`trigger: always_on`** — Loaded every session (`antigravity-overview.md`, `security.md`, `codegraph.md`, `agent-continuity.md`)
+- **`trigger: glob`** — Loaded when active files match `globs`
+- **`trigger: model_decision`** — Activated by intent (persona rules)
+
+| Topic | Rule file |
+|-------|-----------|
+| Clean code, style, errors | `clean-code`, `code-style`, `error-handling` |
+| Stack, structure, APIs | `tech-stack`, `project-structure`, `api-conventions` |
+| Data & naming | `naming-conventions`, `database` |
+| Ops & quality | `security`, `monitoring`, `testing`, `git-workflow`, `system-design` |
+| Code intelligence | `codegraph` (MCP usage; see below) |
+| Agent continuity | `agent-continuity` (`.agent/SESSION.md` handoff) |
+
+---
+
+## Agent continuity
+
+Cross-tool handoff lives in **`.agent/SESSION.md`** (committed). Use **`/resume`** at session start and **`/handoff`** at session end when switching chats or tools. See **`.agents/references/agent-continuity.md`** and **`.agent/rules/agent-continuity.md`**.
+
+---
+
+## Code intelligence (CodeGraph)
+
+This project includes **[CodeGraph](https://github.com/colbymchenry/codegraph)** for local, structural code search via MCP.
+
+| Item | Location |
+|------|----------|
+| MCP server config | `~/.gemini/antigravity/mcp_config.json` (user-level; see `.agents/references/mcp-antigravity.md`) |
+| Usage rules | `.agent/rules/codegraph.md` |
+| Symbol index (generated) | `.codegraph/` (gitignored) |
+| Setup reference | `.agents/references/codegraph.md` |
+
+After configuring MCP, **restart Antigravity** so the CodeGraph MCP server connects. Use `codegraph_*` tools for structural questions (callers, callees, traces, impact); use grep/read for literal text in comments or strings.
+
+If the index is missing, run `npx @colbymchenry/codegraph init -i` in the project root.
+
+---
+
+## Agent personas
+
+Instructions live in **`.agents/agents/`**. Invoke by **referencing** the file (paste or attach in chat).
+
+| Area | File |
+|------|------|
+| Frontend, backend, architecture | `frontend.md`, `backend.md`, `systems-architect.md` |
+| Quality | `code-reviewer.md`, `test-engineer.md`, `qa.md`, `security-auditor.md` |
+| Product & content | `business-analyst.md`, `project-manager.md`, `ui-ux-designer.md`, `copywriter-seo.md` |
+
+---
+
+## Skills
+
+Reusable playbooks: **`.agents/skills/*/SKILL.md`** (and related `.md` files where present).
+
+| Skill | Use for |
+|-------|---------|
+| `tdd` | Red–green–refactor |
+| `code-review` | Five-axis review |
+| `incremental-implementation` | Vertical slices |
+| `deploy` | Deployment pipeline |
+| `security-review` | Security audit |
+| `agent-continuity` | Cross-tool session handoff via `.agent/SESSION.md` |
+| `supabase` | Supabase products, Auth, CLI, MCP, migrations, RLS |
+| `supabase-postgres-best-practices` | Postgres performance, indexes, RLS tuning |
+
+---
+
+## Reference checklists
+
+**`.agents/references/`**
+
+| File | Use for |
+|------|---------|
+| `security-checklist.md` | Pre-deploy security |
+| `testing-patterns.md` | Test structure |
+| `performance-checklist.md` | Performance |
+| `accessibility-checklist.md` | WCAG-oriented checks |
+| `codegraph.md` | CodeGraph setup (all tools) |
+| `mcp-antigravity.md` | Antigravity MCP config (`mcp_config.json`) |
+| `agent-continuity.md` | Session handoff and `/resume` / `/handoff` |
+| `supabase.md` | Supabase skills, MCP OAuth, secrets |
+
+---
+
+## Config parity
+
+Antigravity loads root **`AGENTS.md`**, **`GEMINI.md`**, **`.agent/rules/*.md`**, **`.agents/workflows/`**, and **`.agents/skills/`**. MCP servers are configured in user-level **`~/.gemini/antigravity/mcp_config.json`** — see `.agents/references/mcp-antigravity.md`.
+
+---
+
+## Agent behavior
+
+1. Follow the workflow and use slash commands when starting a phase.
+2. If **`.agent/SESSION.md`** exists, read it before planning or coding; run **`/resume`** when continuing prior work.
+3. Apply **`.agent/rules/`**; treat **`security.md`** as non-negotiable.
+4. Prefer tests first and small, buildable changes.
+5. **Reference** the right **`.agents/agents/`** file when the task matches that role.
+6. Update **`.agent/SESSION.md`** (or **`/handoff`**) before ending a session.

package/README.md

@@ -1,6 +1,6 @@
 # AI Agent Project
 
-**Production-grade configuration for [Claude Code](https://code.claude.com/docs), [Cursor](https://cursor.com), and [Kiro](https://kiro.dev)** — shared rules, specialized agents, workflow prompts, and checklists you can drop into any repository.
+**Production-grade configuration for [Claude Code](https://code.claude.com/docs), [Cursor](https://cursor.com), [Kiro](https://kiro.dev), and [Antigravity](https://antigravity.google)** — shared rules, specialized agents, workflow prompts, and checklists you can drop into any repository.
 
 <div align="center">
 
@@ -18,7 +18,7 @@ Open-source AI agent scaffolding by **Royal Solution** — use it in your own pr
   <a href="https://www.npmjs.com/package/class-ai-agent"><img src="https://img.shields.io/npm/v/class-ai-agent?label=npm&logo=npm&style=flat-square" alt="npm version" /></a>
   <img src="https://img.shields.io/badge/node-%3E%3D16.7-339933?logo=node.js&logoColor=white&style=flat-square" alt="Node.js 16.7+" />
   <img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License MIT" />
-  <img src="https://img.shields.io/badge/version-1.4.1-blue?style=flat-square" alt="Version" />
+  <img src="https://img.shields.io/badge/version-1.5.0-blue?style=flat-square" alt="Version" />
 </p>
 
 </div>
@@ -51,15 +51,15 @@ Open-source AI agent scaffolding by **Royal Solution** — use it in your own pr
 
 | You get | Details |
 |--------|---------|
-| **Three layouts** | **`.claude/`** (Claude Code), **`.cursor/`** (Cursor), **`.kiro/`** (Kiro steering + MCP) |
+| **Four layouts** | **`.claude/`** (Claude Code), **`.cursor/`** (Cursor), **`.kiro/`** (Kiro), **`.agents/`** + **`GEMINI.md`** (Antigravity) |
 | **One workflow** | Spec → Plan → Build → Test → Review → Ship |
 | **11 agent personas** | Frontend, backend, architect, review, QA, security, BA, PM, UX, SEO, test engineer |
 | **13 topic rules** | Code style, security, API, DB, testing, git, and more (same ideas in both trees) |
 | **`npx` installer** | Copies the folders into your project in one command |
-| **CodeGraph** | MCP + usage rules for Cursor and Kiro; local index via [CodeGraph](https://github.com/colbymchenry/codegraph) |
-| **Agent continuity** | Committed **`.agent/SESSION.md`** — `/resume` and `/handoff` across Cursor, Claude Code, and Kiro |
+| **CodeGraph** | MCP + usage rules for Cursor and Kiro; Antigravity via user `mcp_config.json`; local index via [CodeGraph](https://github.com/colbymchenry/codegraph) |
+| **Agent continuity** | Committed **`.agent/SESSION.md`** — `/resume` and `/handoff` across Cursor, Claude Code, Kiro, and Antigravity |
 
-Root **`AGENTS.md`** links hubs: **`.cursor/CURSOR.md`**, **`.kiro/KIRO.md`**, **`.claude/CLAUDE.md`**.
+Root **`AGENTS.md`** links hubs: **`.cursor/CURSOR.md`**, **`.kiro/KIRO.md`**, **`.claude/CLAUDE.md`**, **`GEMINI.md`**.
 
 ---
 
@@ -74,7 +74,7 @@ When one agent stops and another starts (new chat, different IDE, or teammate),
 
 **Read order:** `.agent/SESSION.md` → `tasks/todo.md` → `SPEC.md` (from SESSION pointers).
 
-Rules: `.cursor/rules/agent-continuity.mdc`, `.claude/rules/agent-continuity.md`, `.kiro/steering/agent-continuity.md`. Reference: `.cursor/references/agent-continuity.md`.
+Rules: `.cursor/rules/agent-continuity.mdc`, `.claude/rules/agent-continuity.md`, `.kiro/steering/agent-continuity.md`, `.agent/rules/agent-continuity.md`. Reference: `.cursor/references/agent-continuity.md`.
 
 Do **not** put secrets or PII in `SESSION.md`. See [`.agent/README.md`](.agent/README.md).
 
@@ -103,6 +103,7 @@ npx class-ai-agent --dir /path/to/your/project
 npx class-ai-agent --claude
 npx class-ai-agent --cursor
 npx class-ai-agent --kiro
+npx class-ai-agent --antigravity
 npx class-ai-agent --force    # overwrite existing
 npx class-ai-agent --help
 ```
@@ -116,7 +117,7 @@ npm exec -- class-ai-agent --dir /path/to/your/project
 # or: node bin/class-ai-agent.cjs --dir /path/to/your/project
 ```
 
-**Manual copy:** copy **`.agent/`**, **`.claude/`**, **`.cursor/`**, **`.kiro/`**, and **`AGENTS.md`** into your project root. Copy `.agent/SESSION.template.md` → `.agent/SESSION.md` if needed. Then run `npx @colbymchenry/codegraph init -i` and reload Cursor / restart Kiro.
+**Manual copy:** copy **`.agent/`**, **`.agents/`**, **`.claude/`**, **`.cursor/`**, **`.kiro/`**, **`AGENTS.md`**, and **`GEMINI.md`** into your project root. Copy `.agent/SESSION.template.md` → `.agent/SESSION.md` if needed. Then run `npx @colbymchenry/codegraph init -i` and reload Cursor / restart Kiro / configure Antigravity MCP.
 
 ---
 
@@ -130,21 +131,23 @@ npm exec -- class-ai-agent --dir /path/to/your/project
 | **Cursor** | `.cursor/mcp.json`, `.cursor/rules/codegraph.mdc` — reload window after install |
 | **Kiro** | `.kiro/settings/mcp.json`, `.kiro/steering/codegraph.md` — restart Kiro after install |
 | **Claude Code** | Not wired by this package — `codegraph install --target=claude` (see `.claude/references/codegraph.md`) |
+| **Antigravity** | User `~/.gemini/antigravity/mcp_config.json`, `.agent/rules/codegraph.md` — see `.agents/references/mcp-antigravity.md` |
 | **Manual index** | `npx @colbymchenry/codegraph init -i` if auto-init failed |
-| **Opt-out** | `CODEGRAPH_SKIP_INIT=1` when running `npx class-ai-agent` |
 | **Troubleshooting** | [CodeGraph README](https://github.com/colbymchenry/codegraph#troubleshooting) · `.cursor/references/codegraph.md` |
+| **Opt-out** | `CODEGRAPH_SKIP_INIT=1` when running `npx class-ai-agent` |
 
 ---
 
 ## Overview
 
-This repo ships **three parallel trees** so you can use the same habits in Claude Code, Cursor, and Kiro:
+This repo ships **four parallel layouts** so you can use the same habits in Claude Code, Cursor, Kiro, and Antigravity:
 
 | Layout | Tool | What you use |
 |--------|------|----------------|
 | **`.claude/`** | Claude Code | Slash commands, **`CLAUDE.md`**, rules as **`.md`** |
 | **`.cursor/`** | Cursor | Project rules as **`.mdc`**, hub **`CURSOR.md`**, **`@`** file mentions |
 | **`.kiro/`** | Kiro | **Steering** as **`.md`** in `.kiro/steering/`, hub **`KIRO.md`**, **`.kiro/settings/mcp.json`** |
+| **`.agents/`** + **`GEMINI.md`** | Antigravity | **Workflows** in `.agents/workflows/` (slash commands), **`.agent/rules/`**, root **`AGENTS.md`** |
 
 What is inside:
 
@@ -155,9 +158,9 @@ What is inside:
 - **9 skills** (TDD, code review, incremental implementation, deploy, security review, agent continuity, UI/UX Pro Max, **supabase**, **supabase-postgres-best-practices**)
 - **7 reference docs** (security, testing, performance, accessibility, codegraph, agent-continuity, **supabase**)
 - **`.agent/SESSION.md`** for cross-tool session handoff
-- **CodeGraph + Supabase MCP** for Cursor and Kiro (`.cursor/mcp.json`, `.kiro/settings/mcp.json`)
+- **CodeGraph + Supabase MCP** for Cursor and Kiro (`.cursor/mcp.json`, `.kiro/settings/mcp.json`); Antigravity via user `mcp_config.json` (example in `.agents/references/mcp-antigravity.md`)
 
-Keep **`.claude/`**, **`.cursor/`**, and **`.kiro/`** in sync when you change standards. After editing `.cursor/` (canonical), run **`npm run sync:all`** to refresh `.claude/` and `.kiro/`.
+Keep **`.claude/`**, **`.cursor/`**, **`.kiro/`**, and the Antigravity layout in sync when you change standards. After editing `.cursor/` (canonical), run **`npm run sync:all`** to refresh `.claude/`, `.kiro/`, `.agents/`, `.agent/rules/`, and `GEMINI.md`.
 
 ---
 
@@ -193,9 +196,32 @@ At session boundaries, use **`/handoff`** before switching tools and **`/resume`
 .agent/
 ├── README.md
 ├── SESSION.md              # Live handoff (committed; seeded on install)
-└── SESSION.template.md     # Schema reference
+├── SESSION.template.md     # Schema reference
+└── rules/                  # Antigravity supplement rules (synced from .cursor/rules/)
+```
+
+### `.agents/` + `GEMINI.md` (Antigravity)
+
+Mirrors `.cursor/` for skills, agents, and references. Commands become **workflows** (slash commands):
+
+| Item | Role |
+|------|------|
+| **`GEMINI.md`** | Hub (Antigravity-specific; overrides `AGENTS.md` when rules conflict) |
+| **`workflows/*.md`** | Slash-command workflows (`/build`, `/resume`, …) |
+| **`skills/`**, **`agents/`**, **`references/`** | Same content as `.cursor/` (path-rewritten) |
+| **`.agent/rules/`** | Supplement rules (`trigger: always_on` / `glob`) |
+
+```
+.agents/
+├── workflows/              # 12 workflows (from .cursor/commands/)
+├── agents/
+├── skills/
+└── references/             # includes mcp-antigravity.md
+GEMINI.md                   # Antigravity hub (repo root)
 ```
 
+MCP is **user-level**: `~/.gemini/antigravity/mcp_config.json` — see `.agents/references/mcp-antigravity.md`.
+
 ### `.claude/` (Claude Code)
 
 ```
@@ -332,7 +358,9 @@ Use **`.claude/rules/*.md`** or **`.cursor/rules/*.mdc`** (paired content; Curso
 
 **Kiro** — prompts live under **`.kiro/commands/`**. Open the file, paste or attach in chat, or reference it when running a slash workflow. Restart Kiro after install so MCP (CodeGraph, Supabase) connects.
 
-**Agents** — describe the role in natural language, or **`@`** (Cursor) / reference (Claude, Kiro) an agent file, e.g. `@.cursor/agents/code-reviewer.md` or `.kiro/agents/code-reviewer.md`.
+**Antigravity** — use slash workflows (`/build`, `/spec`, …) or open **`.agents/workflows/*.md`**. Read **`GEMINI.md`** for the hub. Configure MCP via **Manage MCP Servers** (see `.agents/references/mcp-antigravity.md`).
+
+**Agents** — describe the role in natural language, or **`@`** (Cursor) / reference (Claude, Kiro, Antigravity) an agent file, e.g. `@.cursor/agents/code-reviewer.md` or `.agents/agents/code-reviewer.md`.
 
 ---
 
@@ -368,6 +396,15 @@ Ship thin end-to-end slices (DB + API + UI), not “all models first, then all r
 
 
 
+
+
+### 1.5.0 — 2026-06-17
+
+- Add Google Antigravity IDE support: `GEMINI.md` hub, `.agents/` workflows/skills/agents, `.agent/rules/` supplement rules
+- New `sync-antigravity-from-cursor.mjs` wired into `npm run sync:all` with parity checks
+- CLI `--antigravity` flag; safe merge of `.agent/rules/` without overwriting `SESSION.md`
+- MCP setup reference at `.agents/references/mcp-antigravity.md` (user-level `mcp_config.json`)
+
 ### 1.4.1 — 2026-06-17
 
 - Add **Business Analyst** agent persona (BABOK v3) for Cursor, Claude Code, and Kiro
@@ -393,7 +430,7 @@ Ship thin end-to-end slices (DB + API + UI), not “all models first, then all r
 2. Keep tests green.
 3. Run **`/review`** before opening a PR.
 4. Use [conventional commits](https://www.conventionalcommits.org/).
-5. Update **`.cursor/`** when rules or workflows change, then run **`npm run sync:all`** to refresh `.claude/` and `.kiro/`; run **`npm run sync:supabase-skills`** to refresh vendored Supabase skills.
+5. Update **`.cursor/`** when rules or workflows change, then run **`npm run sync:all`** to refresh `.claude/`, `.kiro/`, and Antigravity layout; run **`npm run sync:supabase-skills`** to refresh vendored Supabase skills.
 
 ---