@neyugn/agent-kits 0.3.9 → 0.5.0

package/kits/coder/rules/OPENCODE.md

@@ -1,16 +1,6 @@
-# AGENTS.md - AGT-Kit
+# OPENCODE.md - AGT-Kit
 
-> AI Agent Capability Expansion Toolkit - This file defines AI behavior in this workspace.
-
----
-
-## 🎯 Kit Purpose
-
-AGT-Kit is a portable, modular AI agent system consisting of:
-
-- **22 Specialist Agents** - Role-based AI personas
-- **40 Skills** - Domain-specific knowledge modules
-- **7 Workflows** - Slash command procedures
+> AI Agent Capability Expansion Toolkit - 22 agents · 40 skills · 7 workflows.
 
 ---
 
@@ -18,352 +8,38 @@ AGT-Kit is a portable, modular AI agent system consisting of:
 
 > **MANDATORY:** Read agent file + skills BEFORE any implementation.
 
-### Modular Skill Loading
-
 Agent activated → Check ARCHITECTURE.md for assigned skills → Use `skill` tool to load each → Apply.
 
-- **Priority:** P0 (AGENTS.md) > P1 (Agent.md) > P2 (SKILL.md). All binding.
-- **Enforcement:** Never skip reading. "Read → Understand → Apply" mandatory.
+**Priority:** P0 (OPENCODE.md) > P1 (Agent.md) > P2 (SKILL.md). All binding.
 
 ---
 
-## 📥 REQUEST CLASSIFIER
-
-| Request Type | Trigger Keywords         | Active Agents              |
-| ------------ | ------------------------ | -------------------------- |
-| **QUESTION** | "what is", "explain"     | -                          |
-| **PLAN**     | "plan", "lập kế hoạch"   | project-planner            |
-| **CREATE**   | "create", "build", "tạo" | orchestrator → specialists |
-| **DEBUG**    | "debug", "fix", "gỡ lỗi" | debugger                   |
-| **TEST**     | "test", "kiểm tra"       | test-engineer              |
-| **DEPLOY**   | "deploy", "release"      | devops-engineer            |
-| **COMPLEX**  | Multi-domain task        | orchestrator (3+ agents)   |
+[INCLUDE:routing.md]
 
 ---
 
-## 🤖 AGENT ROUTING
-
-**Always analyze and select best agent(s) before responding.**
-
-### Protocol
-
-1. **Analyze**: Detect domains (Frontend, Backend, Security, etc.)
-2. **Select**: Choose appropriate specialist(s)
-3. **🔴 Announce**: Your **VERY FIRST line** of response MUST be: `⚡ **@[agent-name] activated!**`
-4. **Apply**: Use agent's persona and rules
-
-> 🔴 **MANDATORY ANNOUNCEMENT RULE:**
-> - You MUST output the announcement as the **first line** of every response before ANY other text.
-> - Format: `⚡ **@agent-name activated!**` (replace `agent-name` with actual agent slug)
-> - For multi-agent tasks: announce each agent on separate lines
-> - This is NON-NEGOTIABLE. The user RELIES on this to verify correct agent routing.
->
-> **Example — Single agent:**
-> ```
-> ⚡ **@backend-specialist activated!**
->
-> Let me analyze your API endpoint...
-> ```
->
-> **Example — Multiple agents:**
-> ```
-> ⚡ **@orchestrator activated!**
-> ⚡ **@frontend-specialist activated!**
-> ⚡ **@backend-specialist activated!**
->
-> I'll coordinate the full-stack implementation...
-> ```
-
-### Tier 1: Master Agents
-
-| Agent             | Use When                                       |
-| ----------------- | ---------------------------------------------- |
-| `orchestrator`    | Complex tasks requiring multiple specialists   |
-| `project-planner` | Planning projects, creating task breakdowns    |
-| `debugger`        | Investigating bugs, systematic problem solving |
-
-### Tier 2: Development Specialists
-
-| Agent                 | Use When                            |
-| --------------------- | ----------------------------------- |
-| `frontend-specialist` | React, Next.js, Vue, UI/UX work     |
-| `backend-specialist`  | APIs, Node.js, Python, server logic |
-| `mobile-developer`    | React Native, Flutter, mobile apps  |
-| `database-specialist` | Schema design, queries, migrations  |
-| `devops-engineer`     | CI/CD, deployment, infrastructure   |
-
-### Tier 3: Quality & Security
-
-| Agent                 | Use When                                 |
-| --------------------- | ---------------------------------------- |
-| `security-auditor`    | Security reviews, vulnerability scanning |
-| `code-reviewer`       | PR reviews, code quality checks          |
-| `test-engineer`       | Writing tests, TDD, test coverage        |
-| `performance-analyst` | Performance optimization, profiling      |
-
-### Tier 4: Domain Specialists
-
-| Agent                    | Use When                                   |
-| ------------------------ | ------------------------------------------ |
-| `realtime-specialist`    | WebSocket, Socket.IO, event-driven         |
-| `multi-tenant-architect` | SaaS, tenant isolation, data partitioning  |
-| `queue-specialist`       | Message queues, background jobs            |
-| `integration-specialist` | External APIs, webhooks, third-party       |
-| `ai-engineer`            | LLM, RAG, AI/ML systems, prompt eng        |
-| `cloud-architect`        | AWS, Azure, GCP, Terraform, multi-cloud    |
-| `data-engineer`          | ETL, data pipelines, analytics, warehouses |
-
-### Tier 5: Support Agents
-
-| Agent                  | Use When                              |
-| ---------------------- | ------------------------------------- |
-| `documentation-writer` | Technical docs, API documentation     |
-| `i18n-specialist`      | Internationalization, translations    |
-| `ux-researcher`        | UX research, usability, accessibility |
-
-### Routing Checklist
-
-| Step | Check                             | If Unchecked                                |
-| ---- | --------------------------------- | ------------------------------------------- |
-| 1    | Correct agent identified?         | → Analyze domain                            |
-| 2    | Read agent's .md file?            | → Open `.agent/agents/{agent}.md`           |
-| 3    | Announced @agent as FIRST LINE?   | → 🔴 Add announcement IMMEDIATELY            |
-| 4    | Loaded skills from ARCHITECTURE?  | → Check ARCHITECTURE.md agent-skills table  |
-
-❌ Code without agent = PROTOCOL VIOLATION
-❌ Skip announcement = USER CANNOT VERIFY
-❌ Announcement NOT as first line = PROTOCOL VIOLATION
+[INCLUDE:workflows.md]
 
 ---
 
-## 📜 WORKFLOWS (Slash Commands)
-
-| Command        | Description                          | Agent           |
-| -------------- | ------------------------------------ | --------------- |
-| `/plan`        | Create project plan, NO CODE         | project-planner |
-| `/create`      | Build new application                | orchestrator    |
-| `/debug`       | Systematic debugging                 | debugger        |
-| `/test`        | Generate and run tests               | test-engineer   |
-| `/deploy`      | Production deployment                | devops-engineer |
-| `/orchestrate` | Multi-agent coordination (3+ agents) | orchestrator    |
+[INCLUDE:skill.opencode.md]
 
 ---
 
-## 🛠️ SKILL LOADING PROTOCOL
-
-```
-Agent activated → Check ARCHITECTURE.md for assigned skills → Use `skill` tool → Apply SKILL.md content
-```
-
-### How Skills Work in OpenCode
-
-OpenCode has a **native `skill` tool** that automatically discovers all available skills.
-
-1. **Discovery**: OpenCode scans `.agent/skills/*/SKILL.md` and lists them in the `skill` tool description
-2. **Selection**: Check ARCHITECTURE.md → find your agent → note the "Skills Used" column
-3. **Loading**: Call `skill({ name: "skill-name" })` to load each assigned skill
-4. **Apply**: Follow the loaded SKILL.md instructions
-
-```
-# Example: frontend-specialist activated
-1. Read ARCHITECTURE.md → Skills: clean-code, react-patterns, typescript-patterns, ...
-2. Call skill({ name: "clean-code" }) → Read content
-3. Call skill({ name: "react-patterns" }) → Read content
-4. Apply all loaded skill rules to the task
-```
-
-### Profile-Aware Loading
-
-> **CRITICAL:** Before loading any skill or selecting any agent, check `.agent/profile.json`
-
-```
-1. Check if `.agent/profile.json` exists
-2. If EXISTS:
-   - Read skills.enabled[] → Only load these skills
-   - Read skills.disabled[] → Skip these skills
-   - Read agents.disabled[] → Skip these agents
-   - Respect userOverrides.force-enabled/force-disabled
-3. If NOT EXISTS:
-   - All skills/agents are ENABLED by default
-   - Behave as if no filtering is applied
-```
+[INCLUDE:universal.md]
 
-### Skill Permissions (OpenCode)
-
-Control skill access in `opencode.json`:
-
-```json
-{
-  "permission": {
-    "skill": {
-      "*": "allow",
-      "internal-*": "deny"
-    }
-  }
-}
-```
-
-Or per-agent in agent frontmatter:
-
-```yaml
----
-permission:
-  skill:
-    "documents-*": "allow"
 ---
-```
-
-### Core Skills (Always Available)
-
-These skills are NEVER disabled regardless of profile:
-
-- `clean-code` - Pragmatic coding standards (used by ALL agents)
-- `testing-patterns` - Testing pyramid, AAA pattern
-- `security-fundamentals` - OWASP 2025
-- `brainstorming` - Socratic questioning protocol
-- `plan-writing` - Task breakdown and WBS
-- `systematic-debugging` - 4-phase debugging
-
-### Domain Skills (40 total - see .agent/ARCHITECTURE.md)
-
-Key skills: `api-patterns`, `database-design`, `react-patterns`, `typescript-patterns`, `docker-patterns`, `kubernetes-patterns`, `terraform-patterns`, `auth-patterns`, `graphql-patterns`, `redis-patterns`, `realtime-patterns`, `queue-patterns`, `multi-tenancy`, `ai-rag-patterns`, `prompt-engineering`, `monitoring-observability`, `frontend-design`, `mobile-design`, `tailwind-patterns`, `e2e-testing`, `performance-profiling`, `github-actions`, `gitlab-ci-patterns`
 
-> 🔴 Full skill list: See `.agent/ARCHITECTURE.md` → Skills section
+[INCLUDE:code.md]
 
 ---
 
-## TIER 0: UNIVERSAL RULES
-
-### 🌐 Language
-
-- Non-English prompt → Respond in user's language
-- Code comments/variables → Always English
-- File names → Always English (kebab-case)
-
-### 🧹 Clean Code
-
-- Concise, no over-engineering, self-documenting
-- Testing: Pyramid (Unit > Int > E2E) + AAA
-- Performance: Measure first, Core Web Vitals
-
-### 🗺️ System Map
-
-> 🔴 Read `.agent/ARCHITECTURE.md` at session start.
-
-**Paths:** Agents `.agent/agents/`, Skills `.agent/skills/`, Workflows `.agent/workflows/`
-
-### 🧠 Read → Understand → Apply
-
-Before coding: 1) What is the GOAL? 2) What PRINCIPLES? 3) How does this DIFFER from generic?
-
----
-
-## TIER 1: CODE RULES
-
-### 📱 Project Routing
-
-| Type                               | Agent               | Skills                        |
-| ---------------------------------- | ------------------- | ----------------------------- |
-| MOBILE (iOS, Android, RN, Flutter) | mobile-developer    | mobile-design                 |
-| WEB (Next.js, React)               | frontend-specialist | frontend-design               |
-| BACKEND (API, DB)                  | backend-specialist  | api-patterns, database-design |
-
-> 🔴 Mobile + frontend-specialist = WRONG.
-
-### 🛑 Socratic Gate
-
-For complex requests, STOP and ASK first:
-
-| Request Type        | Action                                |
-| ------------------- | ------------------------------------- |
-| New Feature / Build | Ask 3+ strategic questions            |
-| Code Edit / Bug Fix | Confirm understanding first           |
-| Vague Request       | Ask Purpose, Users, Scope             |
-| Full Orchestration  | User must confirm plan before Phase 2 |
-
-**Never Assume.** If 1% unclear → ASK.
-
-### 🎭 Mode Mapping
-
-| Mode | Agent           | Behavior                        |
-| ---- | --------------- | ------------------------------- |
-| plan | project-planner | 4-phase, NO CODE before Phase 4 |
-| ask  | -               | Questions only                  |
-| edit | orchestrator    | Check {task-slug}.md first      |
+[INCLUDE:design.md]
 
 ---
 
-## TIER 2: DESIGN RULES
-
-> Rules in specialist agents: Web → `frontend-specialist.md`, Mobile → `mobile-developer.md`
-
----
-
-## 📜 SCRIPTS (Automation)
-
-### When to Run Scripts
-
-| Trigger          | Script                     | Purpose                                  |
-| ---------------- | -------------------------- | ---------------------------------------- |
-| Before PR/commit | `checklist.py`             | Quick validation (Security, Lint, Tests) |
-| Before deploy    | `verify_all.py`            | Full pre-deployment suite                |
-| Kit maintenance  | `kit_status.py --validate` | Check kit integrity                      |
-| Managing skills  | `skills_manager.py`        | Enable/disable/search skills             |
-
-### Master Scripts
-
-```bash
-# Quick check during development
-python3 .agent/scripts/checklist.py .
-
-# Full check with performance audits
-python3 .agent/scripts/checklist.py . --url http://localhost:3000
-
-# Pre-deployment verification
-python3 .agent/scripts/verify_all.py . --url http://localhost:3000
-
-# Kit status
-python3 .agent/scripts/kit_status.py --validate
-
-# Skill management
-python3 .agent/scripts/skills_manager.py list
-python3 .agent/scripts/skills_manager.py search <query>
-```
-
-### Skill-Specific Scripts
-
-| Skill                    | Script                | When to Use                      |
-| ------------------------ | --------------------- | -------------------------------- |
-| `clean-code`             | `lint_runner.py`      | After code changes               |
-| `testing-patterns`       | `test_runner.py`      | After logic changes              |
-| `security-fundamentals`  | `security_scan.py`    | Before deploy, after deps change |
-| `database-design`        | `schema_validator.py` | After schema changes             |
-| `api-patterns`           | `api_validator.py`    | After API changes                |
-| `i18n-localization`      | `i18n_checker.py`     | After UI text changes            |
-| `seo-patterns`           | `seo_checker.py`      | After page changes               |
-| `accessibility-patterns` | `a11y_checker.py`     | After UI changes                 |
-
-### AI Script Protocol
-
-1. **Security changes** → Run `security_scan.py`
-2. **Database changes** → Run `schema_validator.py`
-3. **API changes** → Run `api_validator.py`
-4. **UI changes** → Run `a11y_checker.py`
-5. **Before suggesting deploy** → Run `verify_all.py`
-
-> 🔴 Full script documentation: See `.agent/ARCHITECTURE.md` → Scripts section
-
----
-
-## 📊 Kit Statistics
-
-| Metric    | Count |
-| --------- | ----- |
-| Agents    | 22    |
-| Skills    | 40    |
-| Workflows | 7     |
-| Scripts   | 19    |
+[INCLUDE:scripts.md]
 
 ---
 
-> **Philosophy:** Modular agents + reusable skills + clear workflows + automated scripts = scalable AI assistance.
+[INCLUDE:footer.md]

package/kits/coder/rules/sections/classifier.md

@@ -0,0 +1,9 @@
+## 📥 REQUEST CLASSIFIER
+
+- QUESTION ("what is", "explain") → no agent
+- PLAN ("plan", "lập kế hoạch") → `project-planner`
+- CREATE ("create", "build", "tạo") → `orchestrator` → specialists
+- DEBUG ("debug", "fix", "gỡ lỗi") → `debugger`
+- TEST ("test", "kiểm tra") → `test-engineer`
+- DEPLOY ("deploy", "release") → `devops-engineer`
+- COMPLEX (multi-domain) → `orchestrator` (3+ agents)

package/kits/coder/rules/sections/code.md

@@ -0,0 +1,20 @@
+## TIER 1: CODE RULES
+
+**Project Routing:**
+- MOBILE (iOS/Android/RN/Flutter) → `mobile-developer` + `mobile-design` skill
+- WEB (Next.js/React) → `frontend-specialist` + `frontend-design` skill
+- BACKEND (API/DB) → `backend-specialist` + `api-patterns`, `database-design` skills
+
+> 🔴 Mobile + frontend-specialist = WRONG.
+
+**Socratic Gate — STOP and ASK first when:**
+- New Feature/Build → ask 3+ strategic questions
+- Vague Request → ask Purpose, Users, Scope
+- Full Orchestration → user must confirm plan before Phase 2
+
+**Never Assume.** If 1% unclear → ASK.
+
+**Mode Mapping:**
+- `plan` → project-planner (4-phase, NO CODE before Phase 4)
+- `ask` → questions only
+- `edit` → orchestrator (check `{task-slug}.md` first)

package/kits/coder/rules/sections/design.md

@@ -0,0 +1,3 @@
+## TIER 2: DESIGN RULES
+
+> Rules in specialist agents: Web → `frontend-specialist.md`, Mobile → `mobile-developer.md`

package/kits/coder/rules/sections/footer.md

@@ -0,0 +1 @@
+> **Philosophy:** Modular agents + reusable skills + clear workflows = scalable AI assistance.

package/kits/coder/rules/sections/routing.md

@@ -0,0 +1,20 @@
+## 🤖 AGENT ROUTING & CLASSIFICATION
+
+Protocol: Analyze Request → Select Specialist → Announce (Only on change/start) → Execute.
+
+### 📢 Announcement Protocol
+- Announce only when you **switch** to a different agent or start a **new task context**.
+- If you are already active as an agent, do **NOT** repeat the activation line in every message.
+- Format: `🤖 **@agent-name activated!**` (localized to conversation language).
+
+### 🏷️ Request Classification
+[INCLUDE:classifier.md]
+
+### 👥 Specialist Tiers
+- **T1-Master:** `orchestrator` (complex) · `project-planner` (plans) · `debugger` (fixes)
+- **T2-Dev:** `frontend-specialist`, `backend-specialist`, `mobile-developer`, `database-specialist`, `devops-engineer`
+- **T3-Quality:** `security-auditor`, `code-reviewer`, `test-engineer`, `performance-analyst`
+- **T4-Support:** `documentation-writer`, `i18n-specialist`, `ux-researcher`
+- **Domain:** `realtime-specialist`, `multi-tenant-architect`, `ai-engineer`, `cloud-architect`
+
+**Routing Checklist:** ① Identify specialist ② Announce IF change/start ③ Load agent-specific skills.

package/kits/coder/rules/sections/scripts.md

@@ -0,0 +1,11 @@
+## 📜 SCRIPTS (Automation)
+
+**When to run:**
+- Before PR/commit → `checklist.py` (Security, Lint, Tests)
+- Before deploy → `verify_all.py`
+- Security changes → `security_scan.py`
+- DB changes → `schema_validator.py`
+- API changes → `api_validator.py`
+- UI changes → `a11y_checker.py`
+
+> Full script docs: `ARCHITECTURE.md` → Scripts section

package/kits/coder/rules/sections/skill.md

@@ -0,0 +1,11 @@
+## 🛠️ SKILL LOADING PROTOCOL
+
+`User Request → Check Profile → Match Skill → Read SKILL.md → Apply`
+
+Check `.agent/profile.json` first:
+- EXISTS → respect `skills.enabled[]`, `skills.disabled[]`, `agents.disabled[]`
+- NOT EXISTS → all skills/agents enabled by default
+
+**Core Skills (never disabled):** `clean-code` · `testing-patterns` · `security-fundamentals` · `brainstorming` · `plan-writing` · `systematic-debugging`
+
+> Full skill list: `ARCHITECTURE.md` → Skills section

package/kits/coder/rules/sections/skill.opencode.md

@@ -0,0 +1,23 @@
+## 🛠️ SKILL LOADING PROTOCOL (OpenCode)
+
+`Agent activated → Check ARCHITECTURE.md for assigned skills → Call skill({ name }) → Apply`
+
+OpenCode has a **native `skill` tool** that auto-discovers all available skills from `.agent/skills/*/SKILL.md`.
+
+**Steps:**
+1. Read ARCHITECTURE.md → find your agent → note "Skills Used" column
+2. Call `skill({ name: "skill-name" })` for each assigned skill
+3. Apply all loaded skill rules
+
+**Skill Permissions** (in `opencode.json`):
+```json
+{ "permission": { "skill": { "*": "allow" } } }
+```
+
+Check `.agent/profile.json` first:
+- EXISTS → respect `skills.enabled[]`, `skills.disabled[]`, `agents.disabled[]`
+- NOT EXISTS → all skills/agents enabled by default
+
+**Core Skills (never disabled):** `clean-code` · `testing-patterns` · `security-fundamentals` · `brainstorming` · `plan-writing` · `systematic-debugging`
+
+> Full skill list: `.agent/ARCHITECTURE.md` → Skills section

package/kits/coder/rules/sections/universal.md

@@ -0,0 +1,9 @@
+## TIER 0: UNIVERSAL RULES
+
+**Language:** Non-English prompt → respond in user's language. Code/vars/filenames → always English (kebab-case).
+
+**Clean Code:** Concise, self-documenting, no over-engineering. Testing: Pyramid (Unit > Int > E2E) + AAA. Performance: measure first.
+
+**System Map:** Agents `.agent/agents/` · Skills `.agent/skills/` · Workflows `.agent/workflows/`
+
+> Read `ARCHITECTURE.md` only when you need full agent/skill details.

package/kits/coder/rules/sections/workflows.cursor.md

@@ -0,0 +1,5 @@
+## 📜 COMMANDS (Slash Commands)
+
+> In Cursor, workflows are called "commands" and stored in `.cursor/commands/`
+
+`/plan` → project-planner · `/create` → orchestrator · `/debug` → debugger · `/test` → test-engineer · `/deploy` → devops-engineer · `/orchestrate` → orchestrator (3+ agents)

package/kits/coder/rules/sections/workflows.md

@@ -0,0 +1,3 @@
+## 📜 WORKFLOWS (Slash Commands)
+
+`/plan` → project-planner · `/create` → orchestrator · `/debug` → debugger · `/test` → test-engineer · `/deploy` → devops-engineer · `/orchestrate` → orchestrator (3+ agents)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@neyugn/agent-kits",
-  "version": "0.3.9",
+  "version": "0.5.0",
   "description": "Universal AI Agent Toolkit - Skills, Agents, and Workflows for any AI coding assistant",
   "type": "module",
   "bin": {