antigravity-ai-kit 3.4.0 → 3.5.0

package/.agent/CheatSheet.md

@@ -1,6 +1,6 @@
 # Antigravity AI Kit — CheatSheet
 
-> **Version**: v3.1.0 | **Quick Reference** for all capabilities
+> **Version**: v3.5.0 | **Quick Reference** for all capabilities
 > **Session**: Start with `/status`, end with session-end checklist
 
 ---
@@ -138,7 +138,7 @@
 
 ---
 
-## 🧩 Skills (31)
+## 🧩 Skills (32)
 
 ### Operational (5)
 
@@ -234,7 +234,7 @@
 
 ---
 
-## ⚖️ Governance Rules (6)
+## ⚖️ Governance Rules (8)
 
 | Rule File | Scope |
 |:----------|:------|
@@ -244,6 +244,8 @@
 | `git-workflow.md` | Commits, branches, push policy |
 | `documentation.md` | Doc hierarchy, SSOT, preservation |
 | `sprint-tracking.md` | ROADMAP.md as SSOT, session protocols |
+| `quality-gate.md` | Pre-task validation and quality standards |
+| `architecture.md` | System design patterns and ADR governance |
 
 ---
 

package/.agent/checklists/pre-commit.md

@@ -1,6 +1,6 @@
 # Pre-Commit Checklist
 
-> **Framework**: Antigravity AI Kit v2.0.0  
+> **Framework**: Antigravity AI Kit v3.5.0  
 > **Purpose**: Quality gate before committing code  
 > **Principle**: Prevention over correction
 

package/.agent/checklists/session-end.md

@@ -1,6 +1,6 @@
 # Session End Checklist
 
-> **Framework**: Antigravity AI Kit v3.1.0  
+> **Framework**: Antigravity AI Kit v3.5.0  
 > **Purpose**: Complete this checklist before ending any work session  
 > **Principle**: Context preservation for continuity
 

package/.agent/checklists/session-start.md

@@ -1,6 +1,6 @@
 # Session Start Checklist
 
-> **Framework**: Antigravity AI Kit v3.1.0  
+> **Framework**: Antigravity AI Kit v3.5.0  
 > **Purpose**: Complete this checklist at the beginning of every work session  
 > **Principle**: Full context before new work
 

package/.agent/checklists/task-complete.md

@@ -0,0 +1,78 @@
+# Task-Complete Checkpoint
+
+> **Framework**: Antigravity AI Kit v3.5.0
+> **Purpose**: Decision gate after task completion — present options before commit/push
+> **Principle**: Human-in-the-loop governance
+
+---
+
+## 🎯 Trigger Condition
+
+This checkpoint activates when:
+- Implementation work is complete AND quality gates have passed (VERIFY → CHECKPOINT transition)
+- The agent has made code changes that are ready for commit
+
+This checkpoint does NOT activate when:
+- The developer has explicitly enabled "skip checkpoint" mode for the session
+- The change is docs-only or config-only (handled by commit-type scoping)
+
+---
+
+## 📋 Decision Prompt
+
+Present these options to the developer:
+
+| # | Action | Command | When to Recommend |
+|:--|:-------|:--------|:-----------------|
+| 1 | 🔍 Quality Review | `/review` | ✅ Always (if not already run) |
+| 2 | 🛡️ Retrospective Audit | `/retrospective` | Sprint-end or milestone |
+| 3 | 📋 Update Tracking | Manual | ✅ Always |
+| 4 | 📦 Commit & Push | `git commit + push` | After review passes |
+| 5 | 🔚 Session-End | Protocol | End of work session |
+| 6 | 🚀 Deploy | `/deploy` | Production-impacting changes |
+| 7 | 📝 Continue Working | Skip commit | Batching multiple changes |
+| 8 | ⏭️ Skip Checkpoint | Session flag | Rapid iteration mode |
+
+**Prompt format:**
+
+```
+How should we proceed?
+
+1. 🔍 /review — Run quality gates (lint, type-check, test, security, build)
+2. 🛡️ /retrospective — Tier-1 audit (architecture, market benchmark, ethics)
+3. 📋 Update tracking — Sync ROADMAP.md, session-context.md, session-state.json
+4. 📦 Commit & push — Stage, commit (conventional), push to remote
+5. 🔚 Session-end protocol — Preserve context and prepare for handoff
+6. 🚀 /deploy — Production deployment with pre-flight checks
+7. 📝 Continue working — Proceed to next task without committing
+8. ⏭️ Skip checkpoint — Disable checkpoint for remainder of session
+
+> Choose options (e.g., "1, 3, 4" or "1 through 5"):
+```
+
+---
+
+## 🧠 Recommendation Intelligence
+
+Dynamically adjust recommendations based on:
+
+- [ ] **Sprint boundary**: If ROADMAP shows sprint ending → recommend `/retrospective`
+- [ ] **Production files**: If `apps/api/**` or `apps/web/**` changed → recommend `/deploy`
+- [ ] **Session duration**: If >2 hours of work → recommend session-end
+- [ ] **File count**: If >5 files changed → recommend atomic commit review
+- [ ] **New code without tests**: Flag with ⚠️ if test coverage gap detected
+- [ ] **Security-sensitive**: If auth/crypto/token files changed → recommend `/review security`
+
+---
+
+## 🔒 Governance
+
+**PROHIBITED:**
+- Committing or pushing without presenting this checkpoint
+- Auto-selecting options without developer input
+- Skipping this checkpoint for session-end commits
+
+**REQUIRED:**
+- Present decision prompt after every task completion
+- Wait for explicit developer response
+- Log the developer's choice for session audit trail

package/.agent/commands/help.md

@@ -13,7 +13,7 @@ Your complete guide to the Antigravity AI Kit. Type `/help` for a quick overview
 /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 skills           # All 32 skill modules
 /help rules            # Governance rules
 /help checklists       # Quality gate checklists
 /help cli              # Terminal CLI commands (ag-kit)
@@ -24,17 +24,17 @@ Your complete guide to the Antigravity AI Kit. Type `/help` for a quick overview
 
 ## Quick Overview
 
-**Antigravity AI Kit v3.0.0** — Trust-Grade AI Development Framework
+**Antigravity AI Kit v3.5.0** — 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) |
+| 🛠️ Skills | 32 | Domain knowledge modules |
+| ⚖️ Rules | 8 | Modular governance constraints |
+| ✅ Checklists | 4 | Quality gate checklists |
+| ⚙️ Runtime | 29 | Engine modules (governance, reputation, self-healing) |
 
 ### Getting Started
 
@@ -174,7 +174,7 @@ Agents are specialized AI roles. They are automatically activated based on task
 
 ---
 
-## Skills (31)
+## Skills (32)
 
 Skills are domain knowledge modules that agents use. They are loaded automatically based on task context.
 
@@ -194,9 +194,9 @@ Skills are domain knowledge modules that agents use. They are loaded automatical
 
 ---
 
-## Rules (4)
+## Rules (8)
 
-Rules are immutable governance constraints that all agents must follow.
+Rules are modular governance constraints that all agents must follow.
 
 | Rule | Purpose |
 |:-----|:--------|
@@ -204,6 +204,10 @@ Rules are immutable governance constraints that all agents must follow.
 | `git-workflow` | Conventional commits, atomic changes, branch strategy |
 | `security` | Secret management, input validation, OWASP |
 | `testing` | Test-first, coverage targets, test naming |
+| `documentation` | Doc hierarchy, SSOT, preservation |
+| `sprint-tracking` | ROADMAP.md as SSOT, session protocols |
+| `quality-gate` | Pre-task validation and quality standards |
+| `architecture` | System design patterns and ADR governance |
 
 ---
 

package/.agent/engine/sdlc-map.json

@@ -24,12 +24,18 @@
       "description": "Testing and quality gate validation",
       "workflows": ["test", "review"],
       "previous": "build",
+      "next": "checkpoint"
+    },
+    "checkpoint": {
+      "description": "Developer decision gate with intelligence-driven recommendations",
+      "workflows": [],
+      "previous": "verify",
       "next": "ship"
     },
     "ship": {
       "description": "Production deployment with pre-flight checks",
       "workflows": ["deploy"],
-      "previous": "verify",
+      "previous": "checkpoint",
       "next": "evaluate"
     },
     "evaluate": {

package/.agent/engine/workflow-state.json

@@ -37,6 +37,15 @@
       "startedAt": null,
       "completedAt": null
     },
+    "CHECKPOINT": {
+      "status": "pending",
+      "description": "Developer decision gate — presents completion options before commit/push",
+      "checklist": "checklists/task-complete.md",
+      "artifact": null,
+      "startedAt": null,
+      "completedAt": null,
+      "requiresApproval": true
+    },
     "REVIEW": {
       "status": "pending",
       "description": "Code review and security audit",
@@ -95,7 +104,7 @@
     },
     {
       "from": "VERIFY",
-      "to": "REVIEW",
+      "to": "CHECKPOINT",
       "trigger": "Quality gates pass",
       "guard": "All quality gates pass (build, lint, test)"
     },
@@ -105,6 +114,18 @@
       "trigger": "Quality gates fail",
       "guard": "One or more quality gates failed"
     },
+    {
+      "from": "CHECKPOINT",
+      "to": "REVIEW",
+      "trigger": "Developer chooses review/commit",
+      "guard": "Developer selects review or commit option"
+    },
+    {
+      "from": "CHECKPOINT",
+      "to": "IMPLEMENT",
+      "trigger": "Developer chooses continue working",
+      "guard": "Developer selects continue or batch option"
+    },
     {
       "from": "REVIEW",
       "to": "DEPLOY",

package/.agent/hooks/hooks.json

@@ -88,6 +88,17 @@
         { "action": "Append retrospective findings to contexts/plan-quality-log.md", "severity": "low", "onFailure": "log" },
         { "action": "Extract learnings for continuous-learning skill (PAAL cycle)", "severity": "low", "onFailure": "log" }
       ]
+    },
+    {
+      "event": "task-complete",
+      "description": "Triggered after quality gates pass. Presents developer with structured decision options before commit/push.",
+      "enforcement": "runtime",
+      "actions": [
+        { "action": "Present task completion decision prompt to developer", "severity": "critical", "onFailure": "block" },
+        { "action": "Evaluate change scope for recommendations (sprint boundary, production impact, session duration)", "severity": "high", "onFailure": "warn" },
+        { "action": "Check if tracking files (ROADMAP, session-context, session-state) need updating", "severity": "medium", "onFailure": "warn" },
+        { "action": "Suggest session-end protocol if session has accumulated significant changes", "severity": "low", "onFailure": "log" }
+      ]
     }
   ]
 }

package/.agent/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
-  "kitVersion": "3.3.1",
-  "lastAuditedAt": "2026-03-16T00:30:00Z",
+  "kitVersion": "3.5.0",
+  "lastAuditedAt": "2026-03-16T05:47:00Z",
   "description": "Antigravity AI Kit — Trust-Grade AI Development Framework",
   "repository": "https://github.com/besync-labs/antigravity-ai-kit",
   "capabilities": {
@@ -101,6 +101,28 @@
         { "name": "sprint-tracking", "file": "rules/sprint-tracking.md" },
         { "name": "testing", "file": "rules/testing.md" }
       ]
+    },
+    "checklists": {
+      "count": 4,
+      "items": [
+        { "name": "pre-commit", "file": "checklists/pre-commit.md" },
+        { "name": "session-start", "file": "checklists/session-start.md" },
+        { "name": "session-end", "file": "checklists/session-end.md" },
+        { "name": "task-complete", "file": "checklists/task-complete.md" }
+      ]
+    },
+    "hooks": {
+      "count": 8,
+      "items": [
+        { "name": "session-start", "event": "session-start" },
+        { "name": "session-end", "event": "session-end" },
+        { "name": "pre-commit", "event": "pre-commit" },
+        { "name": "secret-detection", "event": "secret-detection" },
+        { "name": "phase-transition", "event": "phase-transition" },
+        { "name": "sprint-checkpoint", "event": "sprint-checkpoint" },
+        { "name": "plan-complete", "event": "plan-complete" },
+        { "name": "task-complete", "event": "task-complete" }
+      ]
     }
   }
 }

package/.agent/rules.md

@@ -218,7 +218,23 @@ After generating code, you MUST enter **Self-Correction Mode**.
 □ Only then may I declare "complete" or "done"
 ```
 
-### F. Continuous Learning Protocol
+### F. Task-Complete Checkpoint Protocol
+
+**After completing a task and before committing or pushing code, present the developer with structured decision options.**
+
+This protocol is defined in `.agent/checklists/task-complete.md` and enforced by the `task-complete` hook event.
+
+**PROHIBITED:**
+- ❌ Committing or pushing without presenting the checkpoint prompt
+- ❌ Auto-selecting options without explicit developer input
+- ❌ Skipping this checkpoint for session-end commits
+
+**REQUIRED:**
+- ✅ Present the 8-option decision prompt after every task completion
+- ✅ Wait for explicit developer response before proceeding
+- ✅ Evaluate change scope for intelligent recommendation annotation
+
+### G. Continuous Learning Protocol
 
 **User corrections become permanent operational rules.**
 
@@ -226,7 +242,7 @@ After generating code, you MUST enter **Self-Correction Mode**.
 2. **Internalize**: Add to operational memory for this session
 3. **Apply**: Use immediately and in all future similar situations
 
-### G. Error Recovery Protocol
+### H. Error Recovery Protocol
 
 **When errors occur, recover gracefully without excuses.**
 

package/.agent/session-context.md

@@ -42,7 +42,7 @@
 
 **Branch**: `main`  
 **Repository**: `besync-labs/antigravity-ai-kit`  
-**Framework**: Antigravity AI Kit v2.0.0
+**Framework**: Antigravity AI Kit v3.5.0
 
 ### Key File Locations
 

package/README.md

@@ -1,21 +1,21 @@
 # 🚀 Antigravity AI Kit
 
-![version](https://img.shields.io/badge/version-3.3.1-blue)
+![version](https://img.shields.io/badge/version-3.5.0-blue)
 ![license](https://img.shields.io/badge/license-MIT-green)
 ![AI Agents](https://img.shields.io/badge/AI%20Agents-19-purple)
 ![Skills](https://img.shields.io/badge/Skills-32-orange)
 ![Commands](https://img.shields.io/badge/Commands-31-red)
 ![Workflows](https://img.shields.io/badge/Workflows-14-teal)
 ![Runtime Modules](https://img.shields.io/badge/Runtime%20Modules-29-blueviolet)
-![Tests](https://img.shields.io/badge/Tests-327%20passing-brightgreen)
-![Checklists](https://img.shields.io/badge/Checklists-3-yellow)
+![Tests](https://img.shields.io/badge/Tests-341%20passing-brightgreen)
+![Checklists](https://img.shields.io/badge/Checklists-4-yellow)
 
 <p align="center">
   <b>🎯 Transform Your IDE into an AI Engineering Team</b>
 </p>
 
 <p align="center">
-  Antigravity AI Kit is a <b>Trust-Grade AI development framework</b> with a <b>29-module runtime engine</b>, <b>19 specialized agents</b>, <b>31 commands</b>, <b>32 skills</b>, and <b>14 workflows</b> — all backed by <b>327 tests</b> and governance-first principles.
+  Antigravity AI Kit is a <b>Trust-Grade AI development framework</b> with a <b>29-module runtime engine</b>, <b>19 specialized agents</b>, <b>31 commands</b>, <b>32 skills</b>, and <b>14 workflows</b> — all backed by <b>341 tests</b> and governance-first principles.
 </p>
 
 <p align="center">
@@ -60,9 +60,9 @@
 | ⌨️ **Commands**   | 31    | Slash commands for every development workflow                          |
 | 🔄 **Workflows**  | 14    | Process templates (/create, /debug, /deploy, /test...)                 |
 | ⚙️ **Runtime**    | 29    | Runtime engine modules (governance, reputation, self-healing...)       |
-| ✅ **Checklists** | 3     | Quality gates (session-start, session-end, pre-commit)                 |
+| ✅ **Checklists** | 4     | Quality gates (session-start, session-end, pre-commit, task-complete)  |
 | ⚖️ **Rules**      | 8     | Modular governance constraints (coding, security, testing, git, docs, sprint)  |
-| 🔗 **Hooks**      | 7     | Event-driven automation (runtime + git-hook enforcement)               |
+| 🔗 **Hooks**      | 8     | Event-driven automation (runtime + git-hook enforcement)               |
 | 🧪 **Tests**      | 327   | Unit, structural, integration, and security tests (32 test files)      |
 
 ---
@@ -188,10 +188,10 @@ Antigravity AI Kit is designed to **never touch your project files**. All operat
 
 ### How It Works: The Autonomy Engine
 
-Antigravity AI Kit uses a **6-phase workflow state machine** that guides development:
+Antigravity AI Kit uses a **7-phase workflow state machine** that guides development:
 
 ```
-EXPLORE → PLAN → IMPLEMENT → VERIFY → REVIEW → DEPLOY
+EXPLORE → PLAN → IMPLEMENT → VERIFY → CHECKPOINT → REVIEW → DEPLOY
 ```
 
 | Phase | What Happens | Transition Guard |
@@ -200,6 +200,7 @@ EXPLORE → PLAN → IMPLEMENT → VERIFY → REVIEW → DEPLOY
 | **PLAN** | Implementation plan with user approval | Plan approved by user |
 | **IMPLEMENT** | Code generation with agent routing | Auto on commit |
 | **VERIFY** | Quality gates, tests, lint | All gates pass |
+| **CHECKPOINT** | Developer decision gate | Explicit developer choice |
 | **REVIEW** | Code review (human or Copilot) | Review approved |
 | **DEPLOY** | Production deployment | Deployment checklist complete |
 
@@ -635,9 +636,9 @@ antigravity-ai-kit/
 │   ├── skills/               # 32 capability modules
 │   ├── workflows/            # 14 process templates
 │   ├── engine/               # Autonomy Engine (state machine, loading rules, configs)
-│   ├── hooks/                # 7 event hooks (runtime + git-hook)
+│   ├── hooks/                # 8 event hooks (runtime + git-hook)
 │   ├── rules/                # 8 modular governance rules
-│   ├── checklists/           # Verification checklists (3)
+│   ├── checklists/           # Verification checklists (4)
 │   ├── templates/            # ADR, feature-request, bug-report templates
 │   ├── decisions/            # Architecture Decision Records
 │   └── manifest.json         # Machine-readable capability registry
@@ -728,7 +729,7 @@ Want to use Antigravity AI Kit in your project? The **[Contributor Guide](https:
 - Context-driven development from [Google Conductor](https://developers.googleblog.com/en/conductor-introducing-context-driven-development-for-gemini-cli/)
 - Hook concepts from [everything-claude-code](https://github.com/affaan-m/everything-claude-code)
 
-_Antigravity AI Kit v3.2.0 extends these foundations with a 29-module runtime engine, Trust-Grade governance, session management, and 100+ capabilities._
+_Antigravity AI Kit v3.5.0 extends these foundations with a 29-module runtime engine, Trust-Grade governance, session management, and 100+ capabilities._
 
 ---
 

package/lib/workflow-engine.js

@@ -19,7 +19,7 @@ const { writeJsonAtomic } = require('./io');
 const { createLogger } = require('./logger');
 const log = createLogger('workflow-engine');
 
-/** @typedef {'IDLE' | 'EXPLORE' | 'PLAN' | 'IMPLEMENT' | 'VERIFY' | 'REVIEW' | 'DEPLOY' | 'MAINTAIN'} WorkflowPhase */
+/** @typedef {'IDLE' | 'EXPLORE' | 'PLAN' | 'IMPLEMENT' | 'VERIFY' | 'CHECKPOINT' | 'REVIEW' | 'DEPLOY' | 'MAINTAIN'} WorkflowPhase */
 
 /**
  * @typedef {object} TransitionResult

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "antigravity-ai-kit",
-  "version": "3.4.0",
-  "description": "🚀 Trust-Grade AI development framework with a 29-module runtime engine — 19 Agents, 32 Skills, 31 Commands, 14 Workflows, 8 Rules, 330 Tests. Workflow enforcement, task governance, agent reputation, self-healing, and skill marketplace.",
+  "version": "3.5.0",
+  "description": "🚀 Trust-Grade AI development framework with a 29-module runtime engine — 19 Agents, 32 Skills, 31 Commands, 14 Workflows, 8 Rules, 341 Tests. Workflow enforcement, task governance, agent reputation, self-healing, and skill marketplace.",
   "main": "bin/ag-kit.js",
   "bin": {
     "ag-kit": "./bin/ag-kit.js"
@@ -9,6 +9,8 @@
   "scripts": {
     "test": "vitest run",
     "test:watch": "vitest watch",
+    "preversion": "npm test",
+    "version": "node scripts/sync-version.js && git add -A",
     "postinstall": "echo '✅ Antigravity AI Kit installed! Run: ag-kit init'"
   },
   "keywords": [