agent-enderun 0.5.0 → 0.5.2

package/.enderun/knowledge/hermes_protocol.md

@@ -0,0 +1,59 @@
+# 📡 Hermes Messaging Protocol
+
+The Hermes protocol defines the standardized way for Agent Enderun specialized agents to communicate, delegate tasks, and share state updates.
+
+---
+
+## 🏗️ Message Structure
+
+Every message sent via `send_agent_message` must follow this conceptual structure (enforced by the MCP tool):
+
+```json
+{
+  "timestamp": "ISO-8601",
+  "from": "@agent_name",
+  "to": "@agent_name",
+  "category": "ACTION | DELEGATION | INFO | ALERT",
+  "priority": "LOW | MEDIUM | HIGH | URGENT",
+  "traceId": "ULID",
+  "content": "Message content",
+  "status": "PENDING | READ | ACKNOWLEDGED | COMPLETED"
+}
+```
+
+---
+
+## 📂 Message Categories
+
+| Category | Usage | Expectation |
+| :--- | :--- | :--- |
+| **ACTION** | Requesting a specific action (e.g., "Run security scan"). | Must be acknowledged and logged in `STATUS.md`. |
+| **DELEGATION** | Handing off a sub-task (e.g., "@backend, create the schema"). | Becomes the primary task for the recipient. |
+| **INFO** | Sharing architectural decisions or updates. | No direct action required, but must be read. |
+| **ALERT** | Critical blockers or security violations. | Immediate attention required by `@manager`. |
+
+---
+
+## 🚦 Priority Levels
+
+- **URGENT:** Must be handled in the current turn.
+- **HIGH:** Top of the queue for the next turn.
+- **MEDIUM:** Standard task priority (Default).
+- **LOW:** Non-critical background updates.
+
+---
+
+## 🔄 Lifecycle Protocol
+
+1.  **Dispatch:** Agent calls `send_agent_message`. Message is saved in `{{FRAMEWORK_DIR}}/messages/recipient.json`.
+2.  **Notification:** The recipient agent checks their inbox during their turn via `read_agent_messages`.
+3.  **Acknowledgment:** For `ACTION` or `DELEGATION`, the recipient should send an `INFO` message back once started or completed.
+4.  **Logging:** All critical communications must be summarized in the agent's log file (`{{FRAMEWORK_DIR}}/logs/agent.json`).
+
+---
+
+## 🛡️ Hermes Safety Rules
+
+- **No circular delegation:** Agent A cannot delegate X to Agent B if B delegated Y (a dependency of X) to A.
+- **Trace ID Integrity:** Every message MUST include a valid `traceId` from `PROJECT_MEMORY.md`.
+- **Atomic Content:** One message per specific intent. Avoid monolithic "do everything" messages.

package/.enderun/knowledge/testing_standards.md

@@ -2,6 +2,6 @@
 
 ## Rules
 1. **Unit Tests**: Mandatory for business logic in services and utils.
-2. **Integration Tests**: Required for API endpoints using real DB (testcontainers).
+2. **Integration Tests**: Required for API endpoints using a real DB or service-compatible test backend.
 3. **Naming**: Files must end in `.test.ts`.
 4. **Coverage**: Aim for >80% coverage in core packages.

package/.enderun/knowledge/zero_ui_library_policy.md

@@ -1,9 +1,13 @@
-# Zero UI Library Policy
+---
+title: Zero UI Library Policy
+tags: [design, security, compliance]
+related: [responsive_design_standards]
+last_updated: 2026-05-15
+---
 
-Do not use Shadcn, MUI, or any other UI library. Build components from scratch using **Panda CSS** tokens defined in `panda.config.ts`.
+The project strictly follows the Zero UI Library Policy. Importing external UI frameworks like shadcn/ui, MUI, or Chakra UI is forbidden. All styling must be implemented using Panda CSS to ensure zero-runtime overhead and complete control over the design system.
 
 ## Rationale
 - **Performance:** Zero-runtime CSS extraction.
 - **Type Safety:** Type-safe styles and tokens.
-- **Originality:** Unique and premium aesthetics without "library look".
-- **Control:** Full control over responsiveness and accessibility.
+- **Originality:** Unique and premium aesthetics without "library look".

package/ENDERUN.md

@@ -1,4 +1,4 @@
-# Agent Enderun (v0.5.0)
+# Agent Enderun (v0.5.2)
 # Place in project root. This file is the single source of truth for Base Project AI Extensions.
 
 ## 🎖️ AGENT CHECKLIST (MANDATORY BEFORE RESPONSE)
@@ -22,7 +22,7 @@ This file (`./{{ADAPTER}}.md`) and the `{{FRAMEWORK_DIR}}/docs/` folder represen
 2. **Check `{{FRAMEWORK_DIR}}/docs/` Folder:** Verify the existence of the `{{FRAMEWORK_DIR}}/docs/` folder (located within the framework directory).
 3. **Absorb Context:** Read `{{FRAMEWORK_DIR}}/docs/tech-stack.md`. If it is empty, ask the user to fill it before proceeding.
 4. **Demand Context:** If the `{{FRAMEWORK_DIR}}/docs/` folder does not exist, ask the user for project context and target audience information before writing any code.
-5. **Mandatory @manager Activation:** You MUST act as `@manager` for the initial response to any new user request.
+5. **Automatic @manager Mode:** You are ALWAYS operating as `@manager` (Team-Lead). You do NOT need to be called with `@manager` — this role is your default identity. You analyze, delegate, and orchestrate on EVERY turn without exception.
 
 **NEVER SKIP THIS STEP.** Do not assume context; read first, then act as @manager.
 
@@ -30,12 +30,17 @@ This file (`./{{ADAPTER}}.md`) and the `{{FRAMEWORK_DIR}}/docs/` folder represen
 
 ## CORE PRINCIPLES
 
+- **Permanent @manager Identity:** The AI assistant is ALWAYS the `@manager` (Team-Lead) by default — on every turn, every message, without exception. The user does NOT need to type `@manager` to trigger this role. Explicitly typing a different agent (e.g. `@backend`) overrides this and activates that specialist directly.
 - **Team-Lead MANDATORY Orchestration:** Every user request MUST first be handled by the `@manager` (Team-Lead) agent. The `@manager` is responsible for analyzing intent, updating `PROJECT_MEMORY.md`, and delegating tasks to specialists. Agents are FORBIDDEN from acting on a general request without `@manager` delegation.
-- **Contract-First Approach:** Communication between Backend and Frontend must always be defined via schemas first. The `packages/shared-types/contract.version.json` file must be kept in MAJOR.MINOR format and updated with every change. The `@backend-architect` is responsible for updating this file.
+- **Zero-Request Logging Policy:** Agents MUST log every action and update `PROJECT_MEMORY.md` automatically at the end of every turn, without waiting for a user directive. This is the "Operating Mode" of the framework.
+- **Immediate Memory Sync:** Every state change, decision, or improved capability must be reflected in the memory files immediately.
+- **Contract-First Agent Evolution:** Tools and SOPs used by agents must be defined via schemas and contracts first.
 - **Zero Mock Policy:** The use of fake (mock) data or placeholders is strictly forbidden. Every line of code must connect to a real endpoint or a typed contract. (Exception: Controlled mock usage is allowed for external 3rd party services like Stripe, Twilio).
 - **Branded Types Law:** All IDs (UserID, ProjectID, etc.) must be in the "Branded Types" format defined under `packages/shared-types`. Using plain strings or numbers is forbidden.
 - **CLI-First Policy:** Due to the AI CLI Assistant focus, all outputs must be user-friendly (using Chalk, Clack, etc.) and stream-based. All commands must support the `--output json` flag and produce machine-readable output.
 - **Audit Logging Necessity:** Every critical action must be logged traceably under the `{{FRAMEWORK_DIR}}/logs/` folder.
+- **Design Continuity & Response Policy:** All UI changes MUST be responsive (Mobile-First + Fluid) and surgical. Unnecessary overhauls of existing layouts are strictly forbidden.
+- **Shared Component First Policy:** Defining common UI elements (Button, Input, Card, etc.) inside page files is FORBIDDEN. All atomic UI components must be created in a shared directory (e.g., `apps/web/src/components/ui/`) and reused across the project.
 - **File Ownership Rule:** Each file is the responsibility of a single agent.
 - **CLI Command Mapping:** All CLI commands in the project must be defined in the `{{FRAMEWORK_DIR}}/cli-commands.json` file and assigned to the relevant agent.
 - **Exit Code Standard:** Standard exit codes (e.g., 64: User Error, 70: Internal Error) must be used in error situations.
@@ -59,7 +64,7 @@ Before writing any code or design, check `{{FRAMEWORK_DIR}}/docs/tech-stack.md`:
 | Environment (prototype / production) | Ask — do not proceed |
 | Auth required? | Ask — do not proceed |
 | Monorepo or separate repos? | Ask — do not proceed |
-| Deploy target (Vercel / Docker / Bare metal)? | Ask — do not proceed |
+| Deploy target (Vercel / Bare metal / Managed platform)? | Ask — do not proceed |
 | i18n (multi-language) required? | Ask — do not proceed |
 | API versioning strategy? | Ask — do not proceed |
 | Accessibility level (WCAG AA / AAA)? | Default AA — ask if different |
@@ -198,4 +203,4 @@ All APIs are versioned via the URL path (`/api/v1/...`). The `packages/shared-ty
    - Delete `.lock` and the message file immediately after processing.
 7. **Phase Rollback Protocol:** If contracts are insufficient, return to Phase 1. All agents become `WAITING` and write `CONTRACT_CHANGED` to their log.
 8. **Next.js Ownership Rule:** `apps/web/api/` and `server/actions/` -> @backend-architect. `apps/web/(routes)/` and `components/` -> @frontend-specialist.
-9. **Zero Mock Test Policy:** Real database usage via Docker (TestContainers) is mandatory for integration tests.
+9. **Zero Mock Test Policy:** Integration tests must use a real database or service-compatible test backend; do not rely on mocks for persistence behavior.

package/README.md

@@ -1,4 +1,4 @@
-# 🏛️ Agent Enderun — v0.5.0
+# 🏛️ Agent Enderun (v0.5.2) — The Supreme AI Governance Framework
 
 **The Supreme AI Governance & Orchestration Framework for Enterprise Development**
 
@@ -10,6 +10,22 @@
 
 ## Executive Summary
 
+Agent Enderun, yazılım ekipleri için tasarlanmış, **Anayasal Yönetişim (Constitutional Governance)** ve **Çoklu Ajan Orkestrasyonu (Multi-Agent Orchestration)** sağlayan kurumsal düzeyde bir framework'tür. 
+
+### 🚀 v0.5.2: Zero-Config & Auto-Wiring
+- **Auto-Wiring:** CLI automatically configures `gemini-extension.json` for MCP.
+- **Automated Build:** Framework now compiles itself during initialization.
+- **Smart Directory Logic:** Enhanced separation between framework and project docs.
+
+### 🚀 v0.5.1: The Academy & Hermes Upgrade
+
+Bu sürümle birlikte Agent Enderun, basit bir yönetişim aracından otonom bir **Ajan Akademisi**'ne dönüşmüştür:
+
+- **📡 Hermes Messaging Protocol:** Ajanlar arası kategorize edilmiş (Action/Delegation/Info) ve önceliklendirilmiş iletişim bus'ı.
+- **📚 Obsidian-Style LLM Wiki:** YAML metadata destekli, ilişkisel ve graf tabanlı teknik bilgi bankası yönetimi.
+- **🛡️ Contract-First Automation:** API ve tip kontratlarının SHA-256 ile otomatik doğrulanması.
+- **🤖 MCP Intelligence:** Bilgi grafiği üretme, inbox istatistikleri ve anlık sistem sağlığı denetimi sağlayan gelişmiş MCP araçları.
+
 Agent Enderun is a **production-grade AI governance framework** designed for engineering teams that must maintain control, traceability, and discipline when using AI assistants for code generation. It transforms chaotic AI output into structured, auditable, enterprise-ready deliverables through:
 
 - **Agent-Led Orchestration**: 8 specialized AI agent roles with defined responsibilities
@@ -37,7 +53,7 @@ git clone https://github.com/ybekar/agent-enderun.git
 cd agent-enderun
 
 # Option B: Or use as npm package (when published)
-npx agent-enderun init gemini
+npx agent{{FRAMEWORK_DIR}} init gemini
 ```
 
 #### Step 2: Install Dependencies
@@ -52,7 +68,7 @@ npm run enderun:build
 
 #### Step 4: Verify Setup
 ```bash
-agent-enderun check
+agent{{FRAMEWORK_DIR}} check
 ```
 
 Expected output:
@@ -66,42 +82,58 @@ Expected output:
 
 ---
 
+## 🤖 Adapter Automation Levels
+
+Choose your AI adapter when running `init`. Each has a different automation level:
+
+| Adapter | Command | Automation | Notes |
+| :--- | :--- | :---: | :--- |
+| **Gemini** | `init gemini` | ✅ Full | MCP auto-wired into `gemini-extension.json`. One command, done. |
+| **Cursor** | `init cursor` | ✅ Full | `cursor.md` auto-synced to `.cursorrules`. One command, done. |
+| **Codex** | `init codex` | ✅ Full | Framework files placed in `.enderun/`. One command, done. |
+| **Claude** | `init claude` | ⚠️ Semi | After init, run one extra command shown in the terminal to register MCP tools. |
+
+> **Claude Note:** Claude Code requires explicit user approval for MCP tools due to its security model.
+> After `init claude`, copy and run the `claude config add ...` command shown in the terminal output.
+
+---
+
 ## 🎯 What You Can Do Right Now
 
 ### Initialize Your Project
 ```bash
-# Creates .enderun/ directory with governance files
-npx agent-enderun init gemini
+# Creates {{FRAMEWORK_DIR}}/ directory with governance files
+npx agent{{FRAMEWORK_DIR}} init gemini
 ```
 
 ### Check Project Health
 ```bash
 # Runs security audit, compliance check, and dependency analysis
-agent-enderun check
+agent{{FRAMEWORK_DIR}} check
 
 # Just security
-agent-enderun check:security
+agent{{FRAMEWORK_DIR}} check:security
 
 # Just compliance
-agent-enderun check:compliance
+agent{{FRAMEWORK_DIR}} check:compliance
 ```
 
 ### View Project Status
 ```bash
 # Shows current phase, active agents, and blockers
-agent-enderun status
+agent{{FRAMEWORK_DIR}} status
 ```
 
 ### Create a New Task
 ```bash
 # Creates a ULID-based trace for a new feature
-agent-enderun trace:new "Implement User Authentication" backend P1
+agent{{FRAMEWORK_DIR}} trace:new "Implement User Authentication" backend P1
 ```
 
 ### Verify API Contracts
 ```bash
 # Ensures shared-types and API docs are synchronized
-agent-enderun verify-contract
+agent{{FRAMEWORK_DIR}} verify-contract
 ```
 
 ---
@@ -112,7 +144,7 @@ Agent Enderun consists of **4 integrated layers**:
 
 ### Layer 1: Governance ({{FRAMEWORK_DIR}}/)
 ```
-.enderun/
+{{FRAMEWORK_DIR}}/
 ├── ENDERUN.md              ← The "Supreme Law" (read this first!)
 ├── PROJECT_MEMORY.md       ← Single source of truth for state
 ├── STATUS.md               ← Agent status dashboard
@@ -237,8 +269,8 @@ Agents use the `search_knowledge_base` tool to find answers to common questions.
 - [ ] **npm 9+** installed (`npm --version`)
 - [ ] **Git** initialized (`git init`)
 - [ ] **Framework installed** (`npm install && npm run enderun:build`)
-- [ ] **Health check passed** (`agent-enderun check` shows ✅)
-- [ ] **First task created** (`agent-enderun trace:new "Your task" backend P1`)
+- [ ] **Health check passed** (`agent{{FRAMEWORK_DIR}} check` shows ✅)
+- [ ] **First task created** (`agent{{FRAMEWORK_DIR}} trace:new "Your task" backend P1`)
 - [ ] **Docs created** (add files to `docs/` for agents to read)
 - [ ] **MCP connected** (agents can now use tools)
 
@@ -259,7 +291,7 @@ Implement JWT-based authentication with refresh tokens.
 " > docs/requirements.md
 
 # Step 2: Create a task
-agent-enderun trace:new "Implement Auth Module" backend P1
+agent{{FRAMEWORK_DIR}} trace:new "Implement Auth Module" backend P1
 
 # Step 3: Agents read requirements and build
 # (They will automatically read docs/requirements.md)
@@ -270,7 +302,7 @@ agent-enderun trace:new "Implement Auth Module" backend P1
 ## 📁 Project Structure
 
 ```
-agent-enderun/
+agent{{FRAMEWORK_DIR}}/
 ├── README.md                          ← This file
 ├── package.json                       ← Root npm config
 ├── bin/
@@ -298,7 +330,7 @@ agent-enderun/
 ├── apps/                              ← Your applications (start here)
 │   ├── backend/                       ← (you create this)
 │   └── web/                           ← (you create this)
-└── .enderun/                          ← Framework governance
+└── {{FRAMEWORK_DIR}}/                          ← Framework governance
     ├── ENDERUN.md                     ← Constitution (MANDATORY READ)
     ├── PROJECT_MEMORY.md              ← State machine
     ├── STATUS.md                      ← Agent dashboard
@@ -351,7 +383,7 @@ agent-enderun/
 1. `ENDERUN.md` (the constitution)
 2. `{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md` (project state)
 3. `docs/` files (your requirements)
-4. `.enderun/knowledge/` (technical guidelines)
+4. `{{FRAMEWORK_DIR}}/knowledge/` (technical guidelines)
 
 ### Q: What if I don't use an AI adapter?
 **A:** The framework still works as a **collaborative development platform**. You and your team use it to enforce:
@@ -364,7 +396,7 @@ agent-enderun/
 **A:** Yes. Add new tool files in `packages/framework-mcp/src/tools/`, define the schema, and export the handler. The CLI will automatically discover them.
 
 ### Q: How do I add my own agents?
-**A:** Create a markdown file in `.enderun/agents/your-agent.md`, define the SOP, and add a CLI mapping in `.enderun/cli-commands.json`.
+**A:** Create a markdown file in `{{FRAMEWORK_DIR}}/agents/your-agent.md`, define the SOP, and add a CLI mapping in `{{FRAMEWORK_DIR}}/cli-commands.json`.
 
 ### Q: Is this production-ready?
 **A:** The **framework** is production-ready. Individual features (like `apps/`) depend on what you build. Start with `apps/backend` or `apps/web`.
@@ -374,7 +406,7 @@ agent-enderun/
 ## 🔗 Key Files to Read First
 
 1. **`{{FRAMEWORK_DIR}}/ENDERUN.md`** — The constitution (rules all agents must follow)
-2. **`.enderun/PROJECT_MEMORY.md`** — Current project state and history
+2. **`{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md`** — Current project state and history
 3. **`docs/tech-stack.md`** — Technology decisions
 4. **`packages/shared-types/src/index.ts`** — The contract (types)
 5. **`README.md`** (this file) — How to use the framework
@@ -387,7 +419,7 @@ agent-enderun/
 File issues with clear reproduction steps and framework version.
 
 ### Contribute
-1. Read `.enderun/ENDERUN.md`
+1. Read `{{FRAMEWORK_DIR}}/ENDERUN.md`
 2. Follow the agent role guidelines
 3. Submit PRs with semantic commit messages
 4. Ensure tests pass: `npm run enderun:build`
@@ -428,7 +460,7 @@ git clone https://github.com/ybekar/agent-enderun.git
 cd agent-enderun
 
 # Seçenek B: veya npm paketi olarak kullan
-npx agent-enderun init gemini
+npx agent{{FRAMEWORK_DIR}} init gemini
 ```
 
 #### Adım 2: Bağımlılıkları Yükle
@@ -443,7 +475,7 @@ npm run enderun:build
 
 #### Adım 4: Kurulumu Doğrula
 ```bash
-agent-enderun check
+agent{{FRAMEWORK_DIR}} check
 ```
 
 Beklenen çıktı:
@@ -461,33 +493,49 @@ Beklenen çıktı:
 
 ### Projeyi Başlat
 ```bash
-npx agent-enderun init gemini
+npx agent{{FRAMEWORK_DIR}} init gemini
 ```
 
 ### Sağlık Durumunu Kontrol Et
 ```bash
-agent-enderun check                 # Tam kontrol
-agent-enderun check:security        # Sadece güvenlik
-agent-enderun check:compliance      # Sadece uyum
+agent{{FRAMEWORK_DIR}} check                 # Tam kontrol
+agent{{FRAMEWORK_DIR}} check:security        # Sadece güvenlik
+agent{{FRAMEWORK_DIR}} check:compliance      # Sadece uyum
 ```
 
 ### Proje Durumunu Görüntüle
 ```bash
-agent-enderun status
+agent{{FRAMEWORK_DIR}} status
 ```
 
 ### Yeni Görev Oluştur
 ```bash
-agent-enderun trace:new "Kullanıcı Doğrulama Uygulaması" backend P1
+agent{{FRAMEWORK_DIR}} trace:new "Kullanıcı Doğrulama Uygulaması" backend P1
 ```
 
 ### API Kontratlarını Doğrula
 ```bash
-agent-enderun verify-contract
+agent{{FRAMEWORK_DIR}} verify-contract
 ```
 
 ---
 
+## 🤖 Adaptör Otomasyon Seviyeleri
+
+`init` komutunu çalıştırırken adaptörünüzü seçin. Her adaptörün otomasyon seviyesi farklıdır:
+
+| Adaptör | Komut | Otomasyon | Not |
+| :--- | :--- | :---: | :--- |
+| **Gemini** | `init gemini` | ✅ Tam | MCP `gemini-extension.json`'a otomatik yazılır. Tek komut, bitti. |
+| **Cursor** | `init cursor` | ✅ Tam | `cursor.md` otomatik olarak `.cursorrules`'a kopyalanır. Tek komut, bitti. |
+| **Codex** | `init codex` | ✅ Tam | Framework dosyaları `.enderun/` dizinine yerleştirilir. Tek komut, bitti. |
+| **Claude** | `init claude` | ⚠️ Yarı | Init sonrası terminalde gösterilen `claude config add ...` komutunu çalıştırmanız gerekir. |
+
+> **Claude Notu:** Claude Code, güvenlik modeli gereği MCP araçlarının kullanıcı tarafından açıkça onaylanmasını zorunlu kılar.
+> `init claude` sonrası terminal çıktısındaki `claude config add ...` komutunu kopyalayıp çalıştırın.
+
+---
+
 ## 🏗️ Temel Mimari
 
 Agent Enderun **4 entegre katmandan** oluşur:
@@ -537,8 +585,8 @@ Agent Enderun **4 entegre katmandan** oluşur:
 - [ ] **npm 9+** yüklü (`npm --version`)
 - [ ] **Git** başlatılmış (`git init`)
 - [ ] **Framework yüklü** (`npm install && npm run enderun:build`)
-- [ ] **Sağlık kontrolü geçti** (`agent-enderun check` ✅ gösteriyor)
-- [ ] **İlk görev oluşturuldu** (`agent-enderun trace:new "Görev" backend P1`)
+- [ ] **Sağlık kontrolü geçti** (`agent{{FRAMEWORK_DIR}} check` ✅ gösteriyor)
+- [ ] **İlk görev oluşturuldu** (`agent{{FRAMEWORK_DIR}} trace:new "Görev" backend P1`)
 - [ ] **Doklar oluşturuldu** (`docs/` klasörüne dosya ekledim)
 - [ ] **MCP bağlandı** (ajanlar araçları kullanabiliyor)
 
@@ -559,7 +607,7 @@ JWT tabanlı kimlik doğrulama sistemi kurun.
 " > docs/requirements.md
 
 # Adım 2: Görev oluşturun
-agent-enderun trace:new "Auth Modülü Uygula" backend P1
+agent{{FRAMEWORK_DIR}} trace:new "Auth Modülü Uygula" backend P1
 
 # Adım 3: Ajanlar sizin için çalışır
 # (Otomatik olarak docs/requirements.md okurlar)
@@ -570,13 +618,13 @@ agent-enderun trace:new "Auth Modülü Uygula" backend P1
 ## 📁 Proje Yapısı
 
 ```
-agent-enderun/
+agent{{FRAMEWORK_DIR}}/
 ├── docs/                 ← Ajanların okuyacağı dokümantasyon
 ├── packages/
 │   ├── shared-types/     ← Paylaşılan türler (sözleşme)
 │   └── framework-mcp/    ← MCP sunucusu (40+ araç)
 ├── apps/                 ← Uygulamalarınız (siz oluşturun)
-├── .enderun/             ← Yönetişim dosyaları
+├── {{FRAMEWORK_DIR}}/             ← Yönetişim dosyaları
 │   ├── ENDERUN.md        ← Anayasa (OKUNMALI)
 │   ├── PROJECT_MEMORY.md ← Proje durumu
 │   ├── agents/           ← 8 ajan tanımı
@@ -599,7 +647,7 @@ agent-enderun/
 1. `ENDERUN.md` (anayasa)
 2. `{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md` (proje durumu)
 3. `docs/` dosyaları (gereksinimler)
-4. `.enderun/knowledge/` (teknik rehberler)
+4. `{{FRAMEWORK_DIR}}/knowledge/` (teknik rehberler)
 
 ### S: AI adaptörü kullanmak zorunlu mu?
 **C:** Hayır. Framework, AI'sız da işlev görür. Faz ilerleme, denetim kaydı ve tür disiplini zorunludur.
@@ -608,7 +656,7 @@ agent-enderun/
 **C:** Evet. `packages/framework-mcp/src/tools/` klasörüne yeni dosya ekleyin.
 
 ### S: Kendi ajanlarımı ekleyebilir miyim?
-**C:** Evet. `.enderun/agents/` klasörüne `.md` dosyası oluşturun ve CLI mapping'ini güncelleyin.
+**C:** Evet. `{{FRAMEWORK_DIR}}/agents/` klasörüne `.md` dosyası oluşturun ve CLI mapping'ini güncelleyin.
 
 ### S: Üretim için hazır mı?
 **C:** Framework hazır. `apps/` klasörü tamamen sizin.
@@ -618,7 +666,7 @@ agent-enderun/
 ## 🔗 Önce Okumanız Gereken Dosyalar
 
 1. **`{{FRAMEWORK_DIR}}/ENDERUN.md`** — Anayasa
-2. **`.enderun/PROJECT_MEMORY.md`** — Proje durumu
+2. **`{{FRAMEWORK_DIR}}/PROJECT_MEMORY.md`** — Proje durumu
 3. **`docs/tech-stack.md`** — Teknoloji kararları
 4. **`packages/shared-types/src/index.ts`** — Sözleşme (türler)
 5. **`README.md`** — Bu dosya
@@ -631,7 +679,7 @@ agent-enderun/
 Net adımlarla ve versiyon numarası ile sorun bildir.
 
 ### Katkıda Bulun
-1. `.enderun/ENDERUN.md` oku
+1. `{{FRAMEWORK_DIR}}/ENDERUN.md` oku
 2. Agent rolü yönergelerine uyun
 3. Semantik commit'ler gönder
 4. Testleri geç: `npm run enderun:build`
@@ -639,30 +687,30 @@ Net adımlarla ve versiyon numarası ile sorun bildir.
 ### Lisans
 MIT © 2026 Yusuf BEKAR
 ```bash
-agent-enderun status
+agent{{FRAMEWORK_DIR}} status
 ```
 
 ### 4. Advanced Intelligence Commands
 ```bash
 # Run Security Audit
-agent-enderun check:security
+agent{{FRAMEWORK_DIR}} check:security
 
 # Generate Dependency Graph
-agent-enderun explorer:graph
+agent{{FRAMEWORK_DIR}} explorer:graph
 
 # Get Commit Suggestion
-agent-enderun git:commit [TRACE-ID]
+agent{{FRAMEWORK_DIR}} git:commit [TRACE-ID]
 ```
 
 ---
 
-## 📂 Consolidated Framework Structure (`.enderun/`)
+## 📂 Consolidated Framework Structure (`{{FRAMEWORK_DIR}}/`)
 
 All governance and engineering assets are consolidated under the framework directory for a clean project root.
 
 ```text
 .
-├── .enderun/
+├── {{FRAMEWORK_DIR}}/
 │   ├── ENDERUN.md           # Supreme Law (Constitution)
 │   ├── PROJECT_MEMORY.md    # Working Memory & History
 │   ├── BRAIN_DASHBOARD.md   # Intelligence & Performance Stats