anchi-toolkit 1.0.0 → 1.2.0

package/.ai-audit/README.md

@@ -0,0 +1,53 @@
+# Audit Log Format
+
+> This directory stores AI decision logs for review and compliance.
+
+## Structure
+
+```
+.ai-audit/
+├── README.md           # This file
+├── 2024-12-26.jsonl    # Daily logs (JSON Lines format)
+└── summary.json        # Aggregated statistics
+```
+
+## Log Entry Format
+
+```json
+{
+  "id": "uuid",
+  "timestamp": "2024-12-26T10:30:00Z",
+  "command": "/do 'Add payment'",
+  "user": "default",
+  "duration_ms": 5230,
+  "agents": ["fullstack-developer", "database-admin"],
+  "skills": ["payment-integration/", "databases/"],
+  "files_touched": [
+    {"path": "src/lib/payment.ts", "action": "create"},
+    {"path": "prisma/schema.prisma", "action": "modify"}
+  ],
+  "rules_checked": ["S1", "S2", "P3"],
+  "violations": [],
+  "decisions": [
+    "Used Stripe (detected in package.json)",
+    "Added webhook endpoint (best practice)"
+  ],
+  "model": "Sonnet 4.5",
+  "status": "success"
+}
+```
+
+## Commands
+
+```bash
+/audit                # Show today's log
+/audit --last 5       # Last 5 entries
+/audit --date 2024-12-25
+/audit --command "/do"
+/audit --violations   # Only show violations
+```
+
+## Retention
+
+- Daily logs: 30 days
+- Summary: Permanent

package/.ai-memory/README.md

@@ -0,0 +1,137 @@
+# AI Memory System
+
+> **Context as DATA, not chat** - AI memory persisted to files.
+
+---
+
+## 📁 Structure
+
+```
+.ai-memory/
+├── README.md           # This file
+├── context.json        # Current project context
+├── decisions.json      # Architecture decisions
+├── entities.json       # Knowledge graph entities
+└── sessions/           # Session snapshots
+    └── 2024-12-26.json
+```
+
+---
+
+## 📄 context.json
+
+Main context file loaded on every session:
+
+```json
+{
+  "project": {
+    "name": "my-app",
+    "type": "web-app",
+    "framework": "nextjs",
+    "database": "postgresql",
+    "preset": "professional"
+  },
+  "tech_stack": {
+    "frontend": ["react", "tailwindcss"],
+    "backend": ["nextjs-api", "prisma"],
+    "testing": ["vitest", "playwright"]
+  },
+  "conventions": {
+    "component_pattern": "functional",
+    "state_management": "react-query",
+    "auth": "session-based"
+  },
+  "current_work": {
+    "feature": "user-authentication",
+    "status": "in-progress",
+    "files": ["src/lib/auth.ts", "src/app/login/page.tsx"]
+  },
+  "last_updated": "2024-12-26T10:30:00Z"
+}
+```
+
+---
+
+## 📄 decisions.json
+
+Architecture decisions log:
+
+```json
+{
+  "decisions": [
+    {
+      "id": "D001",
+      "date": "2024-12-25",
+      "title": "Use session-based auth instead of JWT",
+      "context": "For this project, session is simpler and more secure",
+      "decision": "Implement session-based authentication",
+      "consequences": ["Need session storage", "Simpler token handling"]
+    },
+    {
+      "id": "D002",
+      "date": "2024-12-26",
+      "title": "Use Stripe for payments",
+      "context": "Already have Stripe account, well-documented",
+      "decision": "Integrate Stripe Checkout",
+      "consequences": ["Add stripe package", "Create webhook endpoint"]
+    }
+  ]
+}
+```
+
+---
+
+## 🔄 Auto-Load Behavior
+
+When `/start` or any command runs:
+
+1. Check `.ai-memory/context.json` exists
+2. Load project context
+3. Load recent decisions
+4. AI "remembers" everything
+
+```
+User: /start
+
+AI: 📚 Loading context from .ai-memory/
+    
+    Project: my-app (Next.js + PostgreSQL)
+    Preset: Professional
+    Current work: user-authentication (in-progress)
+    Recent decisions: 2
+    
+    I remember you're working on authentication.
+    What would you like to do?
+```
+
+---
+
+## 💾 Commands
+
+| Command | Action |
+|---------|--------|
+| `/memory save` | Save current context |
+| `/memory load` | Load context |
+| `/memory add "decision"` | Add decision |
+| `/memory clear` | Clear memory |
+| `/memory export` | Export to JSON |
+
+---
+
+## 🔗 Integration
+
+- **Session start:** Auto-load context
+- **Session end:** Prompt to save
+- **Major changes:** Auto-save snapshot
+- **Decisions:** Auto-log to decisions.json
+
+---
+
+## 📊 Benefits
+
+| Old (chat-based) | New (file-based) |
+|------------------|------------------|
+| Context lost on reset | Context persists |
+| Team can't share | Team shares context |
+| Can't audit | Full audit trail |
+| Random decisions | Logged decisions |

package/.ai-memory/context.json

@@ -0,0 +1,26 @@
+{
+    "project": {
+        "name": "",
+        "type": "",
+        "framework": "",
+        "database": "",
+        "preset": ""
+    },
+    "tech_stack": {
+        "frontend": [],
+        "backend": [],
+        "testing": []
+    },
+    "conventions": {
+        "component_pattern": "",
+        "state_management": "",
+        "auth": ""
+    },
+    "current_work": {
+        "feature": "",
+        "status": "",
+        "files": []
+    },
+    "notes": [],
+    "last_updated": ""
+}

package/.ai-memory/decisions.json

@@ -0,0 +1,3 @@
+{
+    "decisions": []
+}

package/.antigravity/agent-skill-index.yaml

@@ -38,6 +38,7 @@ agents:
       - error_analysis
       - performance_diagnosis
       - log_analysis
+      - interactive_probing # Inject logs -> Test -> Analyze
     boundaries:
       - NOT: code_writing → fullstack-developer
     primary_skills:
@@ -141,6 +142,7 @@ agents:
       - devops
     typical_commands:
       - /do (deployment-related)
+      - /demo
       
   git-manager:
     capabilities:
@@ -183,6 +185,7 @@ agents:
       - web-search
     typical_commands:
       - /scout --external
+      - /skill-learn
       
   scout:
     capabilities:
@@ -197,6 +200,7 @@ agents:
       - task_breakdown
       - estimation
       - dependency_analysis
+      - parallel_workstream_planning
     typical_commands:
       - /do --plan-only
       
@@ -207,6 +211,21 @@ agents:
       - team_coordination
     typical_commands:
       - /status
+      
+  # ─────────────────────── Optimization ───────────────────────
+  failure-analyst:
+    capabilities:
+      - root_cause_analysis
+      - pattern_recognition
+    typical_commands:
+      - /audit
+      
+  rules-architect:
+    capabilities:
+      - rule_definition
+      - failure_mode_prevention
+    escalation_from:
+      - failure-analyst
 
 # ═══════════════════════════════════════════════════════════════
 # SKILL INDEX
@@ -385,3 +404,8 @@ command_mapping:
     default: docs-manager
     skills:
       - document-skills
+
+  /config:
+    default: project-manager
+    skills:
+      - document-skills

package/.antigravity/anchi-toolkit.config.yaml

@@ -0,0 +1,12 @@
+project:
+  name: "Anchi Default Project"
+  version: "0.1.0"
+  type: "auto"
+
+features:
+  memory: true
+  audit: true
+  orchestration: true
+
+security:
+  strict_approval: true # Require confirmation for high-risk actions

package/.antigravity/docs/README.md

@@ -0,0 +1,9 @@
+# Project Documentation
+
+Place your project documentation here.
+
+## Recommended Files:
+
+- `PROJECT.md`: Description of your project.
+- `STACK.md`: Tech stack details.
+- `ARCHITECTURE.md`: System design.

package/.antigravity/skills/_template.md

@@ -0,0 +1,30 @@
+# Skill: [Skill Name]
+
+**Description:** [Short description of the technology/framework]
+
+## 🎯 Activation Criteria
+
+- **Files:** `[file_patterns]`
+- **Dependencies:** `[package_names]`
+- **Keywords:** `[keywords]`
+
+## ✅ Best Practices (Rules)
+
+1.  **[Rule 1]:** [Description]
+2.  **[Rule 2]:** [Description]
+3.  **[Naming Convention]:** [Description]
+
+## ❌ Anti-Patterns (Do Not Do)
+
+1.  **[Anti-Pattern 1]:** [Description]
+2.  **[Anti-Pattern 2]:** [Description]
+
+## 📦 Dependencies & Setup
+
+- Recommended Packages:
+  - [pkg1]
+  - [pkg2]
+
+## 🧠 Memory Hooks
+
+- If user asks for [X], suggest [Y].

package/.antigravity/team.yaml

@@ -0,0 +1,154 @@
+# Team Configuration
+# Role-aware AI behavior and permissions
+# ═══════════════════════════════════════════════════════════════
+
+# Team info
+team:
+  name: "My Team"
+  project: "Project Name"
+  mode: "individual"  # individual | team
+
+# ═══════════════════════════════════════════════════════════════
+# ROLE DEFINITIONS
+# ═══════════════════════════════════════════════════════════════
+
+roles:
+  # Lead/Senior - Full control
+  lead:
+    level: 3
+    permissions:
+      auto_approve: true
+      skip_reviews: allowed
+      override_rules: allowed
+      deploy: true
+    ai_behavior:
+      explanation_level: minimal
+      auto_mode: true
+      speed_priority: true
+      require_confirmation: false
+    
+  # Senior Developer
+  senior:
+    level: 2
+    permissions:
+      auto_approve: true
+      skip_reviews: limited
+      override_rules: false
+      deploy: true
+    ai_behavior:
+      explanation_level: standard
+      auto_mode: true
+      speed_priority: false
+      require_confirmation: false
+
+  # Developer
+  developer:
+    level: 1
+    permissions:
+      auto_approve: false
+      skip_reviews: false
+      override_rules: false
+      deploy: false
+    ai_behavior:
+      explanation_level: standard
+      auto_mode: false
+      speed_priority: false
+      require_confirmation: true
+
+  # Junior Developer
+  junior:
+    level: 0
+    permissions:
+      auto_approve: false
+      skip_reviews: false
+      override_rules: false
+      deploy: false
+    ai_behavior:
+      explanation_level: detailed
+      auto_mode: false
+      speed_priority: false
+      require_confirmation: true
+      suggest_alternatives: true
+      explain_decisions: true
+
+  # Reviewer (read-heavy)
+  reviewer:
+    level: 1
+    permissions:
+      auto_approve: false
+      skip_reviews: false
+      override_rules: false
+      deploy: false
+    ai_behavior:
+      explanation_level: detailed
+      auto_mode: false
+      review_focus: true
+
+# ═══════════════════════════════════════════════════════════════
+# CURRENT USER
+# ═══════════════════════════════════════════════════════════════
+
+# Set your role (affects AI behavior)
+current_user:
+  name: "Developer"
+  role: lead  # lead | senior | developer | junior | reviewer
+
+# ═══════════════════════════════════════════════════════════════
+# TEAM MEMBERS (for team mode)
+# ═══════════════════════════════════════════════════════════════
+
+members:
+  # - name: "Alice"
+  #   role: lead
+  #   github: "@alice"
+  #   email: "alice@company.com"
+  # - name: "Bob"
+  #   role: developer
+  #   github: "@bob"
+
+# ═══════════════════════════════════════════════════════════════
+# WORKFLOW RULES
+# ═══════════════════════════════════════════════════════════════
+
+workflows:
+  feature:
+    require_plan: true
+    require_review: true
+    min_approver_level: 2  # senior or above
+    
+  hotfix:
+    require_plan: false
+    require_review: false
+    min_approver_level: 0
+    
+  refactor:
+    require_plan: true
+    require_review: true
+    min_approver_level: 2
+    
+  release:
+    require_plan: true
+    require_review: true
+    min_approver_level: 3  # lead only
+
+# ═══════════════════════════════════════════════════════════════
+# NOTIFICATIONS
+# ═══════════════════════════════════════════════════════════════
+
+notifications:
+  enabled: false
+  slack_webhook: null
+  events:
+    - plan_approved
+    - review_completed
+    - release_ready
+    - violation_detected
+
+# ═══════════════════════════════════════════════════════════════
+# STANDUP (for /daily command)
+# ═══════════════════════════════════════════════════════════════
+
+standup:
+  enabled: false
+  time: "09:00"
+  channel: "#standup"

package/.antigravity/workflows/config.md

@@ -0,0 +1,144 @@
+---
+description: ⚡⚡ View and edit anchi-toolkit configuration
+argument-hint: [optional: --edit | --reset | key=value]
+---
+
+# /config - Configuration Management
+
+**What:** View and edit anchi-toolkit.config.yaml settings.
+
+## Usage
+```
+/config                        # Show current config
+/config --edit                 # Open config in editor
+/config preset=professional    # Change specific setting
+/config --reset                # Reset to defaults
+```
+
+---
+
+## 💰 Model Selection
+
+| Action | Recommended Model | Cost |
+|--------|-------------------|------|
+| View config | GPT-5.1 Codex Mini | 💚 Low |
+| Edit config | GPT-5.1 Codex Mini | 💚 Low |
+
+> Config operations are simple - always use cheapest models.
+
+---
+
+## Output
+
+```
+⚙️ /config
+
+═══════════ ANCHI-TOOLKIT CONFIG ═══════════
+
+📂 File: .cursor/anchi-toolkit.config.yaml
+
+┌─────────────────────────────────────────────────────────────┐
+│ CURRENT SETTINGS                                            │
+├─────────────────────────────────────────────────────────────┤
+│                                                             │
+│ 📋 Preset: professional                                     │
+│ 🤖 Agents: all (19 agents)                                  │
+│ 🛠️ Skills: all (35 skills)                                  │
+│ 📦 Commands: all (18 commands)                              │
+│                                                             │
+│ ⚙️ Settings:                                                │
+│   ├── auto_commit: false                                    │
+│   ├── auto_test: true                                       │
+│   ├── language: vi                                          │
+│   └── model_preference: cost-optimized                      │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+
+💡 Quick Commands:
+  /config preset=rapid           # Switch preset
+  /config auto_commit=true       # Enable auto-commit
+  /config --edit                 # Full editor mode
+```
+
+---
+
+## Editable Settings
+
+| Key | Values | Default |
+|-----|--------|---------|
+| `preset` | rapid, professional, enterprise | professional |
+| `auto_commit` | true, false | false |
+| `auto_test` | true, false | true |
+| `language` | en, vi | vi |
+| `model_preference` | cost-optimized, balanced, quality | cost-optimized |
+
+---
+
+## Flags
+
+| Flag | Action |
+|------|--------|
+| `--edit` | Open config file in editor |
+| `--reset` | Reset to default settings |
+| `--show-all` | Show all available options |
+| `--validate` | Validate config syntax |
+
+---
+
+## Config File Location
+
+```
+.cursor/anchi-toolkit.config.yaml    # Cursor AI
+.antigravity/anchi-toolkit.config.yaml  # Antigravity
+```
+
+---
+
+## Example Config
+
+```yaml
+# anchi-toolkit.config.yaml
+preset: professional
+
+agents: all  # or list: [fullstack-developer, debugger]
+skills: all  # or list: [databases, frontend-development]
+commands: all
+
+settings:
+  auto_commit: false
+  auto_test: true
+  language: vi
+  model_preference: cost-optimized
+  
+overrides:
+  test_coverage_threshold: 80
+  max_file_changes: 20
+```
+
+---
+
+## Agent & Skill Activation
+
+**Primary Agents:**
+- `.cursor/agents/project-manager.md` - Config management
+
+**Skills:**
+- `document-skills/` - Config parsing
+
+> Config uses minimal AI - mostly file operations.
+
+---
+
+## 🔄 Dynamic Orchestration
+
+> **AI MUST read orchestration config before execution**
+
+```
+1. READ .cursor/agent-skill-index.yaml
+2. CHECK command_mapping for this command
+3. APPLY skill activation rules
+4. CHECK .cursor/failure-modes.yaml
+5. LOG decision to .ai-audit/
+```
+
+📖 [docs/ORCHESTRATION_RUNTIME.md](../docs/ORCHESTRATION_RUNTIME.md)

package/.antigravity/workflows/demo.md

@@ -0,0 +1,50 @@
+---
+description: 📺 One-Click Demo / Preview
+argument-hint: [optional: port]
+---
+
+# /demo - Instant Preview
+
+**What:** Auto-detects and runs the project dev server.
+
+## Logic
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│ 📺 /demo - AUTO LAUNCHER                                    │
+├─────────────────────────────────────────────────────────────┤
+│                                                             │
+│  [1] SCAN: package.json scripts                             │
+│      ├── Look for: "dev", "start", "serve", "preview"       │
+│      └── Priority: dev > start > serve                      │
+│                                                             │
+│  [2] CHECK PORT:                                            │
+│      ├── Default: 3000, 8080, 5173                          │
+│      └── Check if port is in use (kill if needed?)          │
+│                                                             │
+│  [3] EXECUTE:                                               │
+│      Run detected command (e.g., `npm run dev`)             │
+│                                                             │
+│  [4] VERIFY:                                                │
+│      Wait for "Ready" or "Listening" in stdout              │
+│                                                             │
+│  [5] OUTPUT:                                                │
+│      "🚀 Project is LIVE!                                   │
+│       👉 http://localhost:3000                              │
+│       (Ctrl+C to stop)"                                     │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Agent Capabilities
+
+- **Agent:** `devops-engineer` or `fullstack-developer`
+- **Skill:** `terminal-management`
+
+## Usage
+
+```
+/demo           # Auto-detect and run
+/demo 8080      # Run on specific port (if supported)
+/demo --prod    # Run production build
+```