@damphuquy/agent-init 1.0.0

package/README.md

@@ -0,0 +1,146 @@
+# RIPER-5 Coding Agents & Operational Workspace Scaffolder
+
+Bộ công cụ khởi tạo bộ khung System Prompt / Agent Manual (`AGENTS.md`) và Operational Workspace (`process/`) cho bất kỳ subsystem hoặc repository nào.
+
+---
+
+## 1. Khởi tạo từ xa (Remote Execution)
+
+Không cần clone repository, chạy trực tiếp trên máy đích.
+
+### Node.js (npx)
+
+```bash
+# Khởi tạo tại thư mục hiện tại
+npx @damphuquy/agent-init .
+
+# Khởi tạo vào thư mục chỉ định
+npx @damphuquy/agent-init ./my-project
+```
+
+### Linux / macOS / WSL (Bash)
+
+```bash
+# Khởi tạo tại thư mục hiện tại
+curl -fsSL https://raw.githubusercontent.com/<USER>/<REPO>/main/bootstrap.sh | bash
+
+# Khởi tạo vào thư mục chỉ định
+curl -fsSL https://raw.githubusercontent.com/<USER>/<REPO>/main/bootstrap.sh | bash -s -- ./my-project
+```
+
+### Windows (PowerShell)
+
+```powershell
+# Khởi tạo tại thư mục hiện tại
+irm https://raw.githubusercontent.com/<USER>/<REPO>/main/bootstrap.ps1 | iex
+
+# Khởi tạo vào thư mục chỉ định
+& ([scriptblock]::Create((irm https://raw.githubusercontent.com/<USER>/<REPO>/main/bootstrap.ps1))) -TargetDir ".\my-project"
+```
+
+---
+
+## 2. Khởi tạo cục bộ (Local Execution)
+
+Khi đã tải hoặc clone repository về máy:
+
+```bash
+# Sử dụng Node.js
+node bin/bootstrap.js [target_directory]
+
+# Sử dụng Bash
+bash bootstrap.sh [target_directory]
+
+# Sử dụng Python
+python3 bootstrap.py [target_directory]
+```
+
+---
+
+## 3. Tùy chọn tham số (Options)
+
+- `-f, --force`: Ghi đè file nếu đã tồn tại trước đó.
+- `-h, --help`: Hiển thị hướng dẫn sử dụng.
+
+Ví dụ:
+```bash
+npx @damphuquy/agent-init ./my-project --force
+bash bootstrap.sh ./my-project --force
+```
+
+---
+
+## 4. Cấu trúc thư mục mã nguồn và chỉnh sửa template
+
+Tất cả template mẫu được tách riêng biệt thành các file thực tế trong thư mục `templates/`:
+
+```text
+.
+├── templates/                     # Toàn bộ nội dung template (chỉnh sửa trực tiếp tại đây)
+│   ├── AGENTS.md
+│   ├── .agents/name_rule.md
+│   └── process/
+│       ├── README.md
+│       ├── _seeds/                # Các seed templates (task, program, context)
+│       ├── context/               # Context routers
+│       └── development-protocols/ # Quy chuẩn lập trình & điều phối
+├── bin/
+│   └── bootstrap.js               # CLI runner đọc trực tiếp từ templates/
+├── scripts/
+│   └── build-bundle.js            # Trình biên dịch tự động templates/ vào bootstrap.sh/ps1/py
+├── bootstrap.sh                   # Bản standalone cho curl | bash
+├── bootstrap.ps1                  # Bản standalone cho PowerShell irm | iex
+├── bootstrap.py                   # Bản standalone cho Python
+└── package.json
+```
+
+Khi bạn chỉnh sửa bất kỳ nội dung nào trong thư mục `templates/`, chỉ cần chạy lệnh sau để tự động đồng bộ sang tất cả các file thực thi đơn lẻ:
+
+```bash
+npm run build
+```
+
+---
+
+## 5. Cấu trúc thư mục được sinh ra trên dự án đích
+
+```text
+<target_dir>/
+├── AGENTS.md                      # Master Agent Guidelines (4 Pillars + RIPER-5 Framework)
+├── .agents/
+│   └── name_rule.md               # Quy tắc đặt tên và interface
+└── process/
+    ├── README.md                  # Trung tâm điều hành task process
+    ├── _seeds/                    # Blueprints / Templates gốc (Read-only)
+    │   ├── _GUIDE.md              # Hướng dẫn sử dụng seeds
+    │   ├── task-template.md.seed  # Template cho task đơn lẻ (SPEC, PLAN, AC)
+    │   ├── program-template.md.seed # Blueprint cho chương trình đa pha
+    │   └── context-group.md.seed  # Seed cho router ngữ cảnh domain
+    ├── context/
+    │   ├── all-context.md         # Root context router
+    │   └── planning/all-planning.md # Tiêu chuẩn INVEST, capacity planning
+    ├── development-protocols/
+    │   ├── all-development-protocols.md # Protocols index
+    │   ├── orchestration.md       # Quy tắc subagent delegation
+    │   └── implementation-standards.md # Chuẩn typing, domain purity, testing
+    ├── features/                  # Quản lý task theo feature/domain
+    │   ├── active/                # Task đang thực thi ({task_slug}_{date}/)
+    │   ├── backlog/               # Task chờ xử lý ({note_slug}_NOTE_{date}.md)
+    │   └── completed/             # Task đã hoàn thành
+    └── general-plans/             # Quản lý task cross-cutting / độc lập
+        ├── active/
+        ├── backlog/
+        └── completed/
+```
+
+---
+
+## 6. Các bước sau khi khởi tạo
+
+1. **Cập nhật lệnh kiểm thử trong `AGENTS.md`**:
+   Mở file `<target_dir>/AGENTS.md` và chỉnh sửa các lệnh kiểm thử tại phần `<validation_commands>` phù hợp với công nghệ của dự án (ví dụ: `npm test`, `pytest`, `go test ./...`).
+
+2. **Tạo task đầu tiên từ template**:
+   ```bash
+   cp process/_seeds/task-template.md.seed process/general-plans/active/01-init_PLAN.md
+   ```

package/bin/bootstrap.js

@@ -0,0 +1,88 @@
+#!/usr/bin/env node
+
+const fs = require('fs');
+const path = require('path');
+
+function parseArgs() {
+  const args = process.argv.slice(2);
+  let targetDir = '.';
+  let force = false;
+
+  for (let i = 0; i < args.length; i++) {
+    const arg = args[i];
+    if (arg === '--force' || arg === '-f') {
+      force = true;
+    } else if (arg === '--help' || arg === '-h') {
+      console.log(`
+Usage:
+  npx @damphuquy/agent-init [target_directory] [options]
+  node bin/bootstrap.js [target_directory] [options]
+
+Options:
+  -f, --force      Overwrite existing files if present
+  -h, --help       Display this help message
+
+Examples:
+  npx @damphuquy/agent-init .
+  npx @damphuquy/agent-init ./services/billing --force
+`);
+      process.exit(0);
+    } else if (!arg.startsWith('-')) {
+      targetDir = arg;
+    }
+  }
+
+  return { targetDir, force };
+}
+
+function copyDirectoryRecursive(srcDir, destDir, targetBase, force, stats = { created: 0, skipped: 0 }) {
+  if (!fs.existsSync(destDir)) {
+    fs.mkdirSync(destDir, { recursive: true });
+  }
+
+  const entries = fs.readdirSync(srcDir, { withFileTypes: true });
+
+  for (const entry of entries) {
+    const srcPath = path.join(srcDir, entry.name);
+    const destPath = path.join(destDir, entry.name);
+
+    if (entry.isDirectory()) {
+      copyDirectoryRecursive(srcPath, destPath, targetBase, force, stats);
+    } else {
+      const relPath = path.relative(targetBase, destPath);
+      if (fs.existsSync(destPath) && !force) {
+        console.log(`  [SKIPPED] ${relPath} (already exists, use --force to overwrite)`);
+        stats.skipped++;
+      } else {
+        fs.copyFileSync(srcPath, destPath);
+        console.log(`  [CREATED] ${relPath}`);
+        stats.created++;
+      }
+    }
+  }
+
+  return stats;
+}
+
+function scaffold(targetDir, force) {
+  const templatesDir = path.resolve(__dirname, '../templates');
+
+  if (!fs.existsSync(templatesDir)) {
+    console.error(`Error: Templates directory not found at ${templatesDir}`);
+    process.exit(1);
+  }
+
+  const resolvedTarget = path.resolve(process.cwd(), targetDir);
+  console.log(`Scaffolding RIPER-5 Coding Agents Workspace into: ${resolvedTarget}`);
+
+  const stats = copyDirectoryRecursive(templatesDir, resolvedTarget, resolvedTarget, force);
+
+  console.log(`\nSetup complete: ${stats.created} created, ${stats.skipped} skipped.`);
+  console.log(`\nNext Steps:`);
+  console.log(`  1. Review and customize validation commands in: ${path.join(targetDir, 'AGENTS.md')}`);
+  console.log(`  2. Instantiate your first active task:`);
+  console.log(`     cp ${path.join(targetDir, 'process/_seeds/task-template.md.seed')} ${path.join(targetDir, 'process/general-plans/active/01-init_PLAN.md')}\n`);
+}
+
+const { targetDir, force } = parseArgs();
+scaffold(targetDir, force);

package/package.json

@@ -0,0 +1,35 @@
+{
+  "name": "@damphuquy/agent-init",
+  "version": "1.0.0",
+  "description": "Scaffolding CLI to bootstrap RIPER-5 Coding Agents & Operational Workspace",
+  "main": "bin/bootstrap.js",
+  "bin": {
+    "agent-init": "./bin/bootstrap.js"
+  },
+  "files": [
+    "bin",
+    "templates"
+  ],
+  "publishConfig": {
+    "access": "public"
+  },
+  "scripts": {
+    "build": "node scripts/build-bundle.js",
+    "start": "node ./bin/bootstrap.js",
+    "scaffold": "node ./bin/bootstrap.js"
+  },
+  "keywords": [
+    "ai-agent",
+    "riper-5",
+    "agent-manual",
+    "operational-workspace",
+    "scaffold",
+    "coding-agents",
+    "agent-init"
+  ],
+  "author": "Phu Quy Dam",
+  "license": "MIT",
+  "engines": {
+    "node": ">=16.0.0"
+  }
+}

package/templates/.agents/name_rule.md

@@ -0,0 +1,3 @@
+# name rule
+
+Never use leading underscores `_` for function or method names. Write flat, clean, public functions with self-explanatory names unless explicitly asked.

package/templates/AGENTS.md

@@ -0,0 +1,102 @@
+# Repository Agent Guidelines (RIPER-5 Framework)
+
+<agent_guidelines version="2.0">
+
+<overview>
+  Master operating instructions for AI agents in this subsystem/repository. Establishes the **4 Core Pillars** and the **RIPER-5 Operational Loop**, integrated with the [`process/`](process/README.md) task framework.
+</overview>
+
+---
+
+## 1. Core Foundations
+
+<foundations>
+  <!-- Pillar 1: Task & Specification -->
+  <pillar id="task_spec" title="Task & Specification">
+    <rule>Single Source of Truth: Active task file in [`process/features/{feature}/active/`](process/features/) or [`process/general-plans/active/`](process/general-plans/) (instantiated from [`process/_seeds/task-template.md.seed`](process/_seeds/task-template.md.seed)).</rule>
+    <rule>Define changes via Goal, Current Behavior, Expected Behavior, Invariants, and `<out_of_scope>`.</rule>
+    <rule>Acceptance Criteria (AC) must be unambiguous, verifiable markdown checkboxes (`- [ ]`).</rule>
+  </pillar>
+
+  <!-- Pillar 2: Context Navigation -->
+  <pillar id="context" title="Context Navigation">
+    <rule>Gather minimum sufficient context. No full-repo scanning or drive-by refactoring.</rule>
+    <information_priority>
+      1. Task Spec & AC ([`process/features/**/_SPEC*.md`](process/features/), [`process/general-plans/**/_PLAN*.md`](process/general-plans/), [`process/context/all-context.md`](process/context/all-context.md))
+      2. Relevant Test Suites (`tests/...`)
+      3. Domain Models & Ports (`src/.../domain/`, `src/.../application/port_*`)
+      4. Configuration & DI (`src/.../infrastructure/config/`, `pyproject.toml` / `package.json`)
+      5. Concrete Implementations (`src/.../infrastructure/`, `src/.../application/service/`, `src/.../api/`)
+    </information_priority>
+  </pillar>
+
+  <!-- Pillar 3: Engineering Harness & Guardrails -->
+  <pillar id="harness" title="Engineering Harness & Guardrails">
+    <validation_commands>
+      # Adapt these commands to your subsystem's toolchain:
+      # e.g., Python: uv run pytest && uv run mypy --strict . && uv run ruff check . && uv run ruff format --check .
+      # e.g., Node/TS: npm run test && npm run typecheck && npm run lint
+    </validation_commands>
+    <architecture_guardrail>
+      Clean Architecture & Dependency Injection provide structural guidance, NOT an instruction to blindly over-engineer simple utilities.
+    </architecture_guardrail>
+  </pillar>
+</foundations>
+
+---
+
+## 2. Operational Loop (Pillar 4: RIPER-5 Protocol)
+
+<operational_loop>
+  <phase order="1" name="Research (R)">
+    Ingest active task spec, follow `<information_priority>`, establish domain invariants and boundaries.
+  </phase>
+
+  <phase order="2" name="Innovate & Plan (I)">
+    Decompose into vertical slices (per [`process/context/planning/all-planning.md`](process/context/planning/all-planning.md)), define step-by-step plan and test cases.
+  </phase>
+
+  <phase order="3" name="Produce (P)">
+    Implement scoped atomic edits with strict typing. Preserve public APIs and backward compatibility.
+  </phase>
+
+  <phase order="4" name="Evaluate (E)">
+    Execute focused test $\rightarrow$ full suite $\rightarrow$ type check $\rightarrow$ lint & format check.
+  </phase>
+
+  <phase order="5" name="Reconcile & Review (R)">
+    Inspect `git diff` for zero noise. Safely toggle verified checkboxes (`- [x]`). Move completed task to `completed/`.
+  </phase>
+
+  <retry_budget max_attempts="3">
+    Maximum 3 consecutive attempts per distinct failure symptom. Never bypass errors with suppression flags (e.g. `# type: ignore`, `eslint-disable`). If exhausted, halt and log into `<open_decisions>`.
+  </retry_budget>
+
+  <escalation_and_stop_conditions>
+    Halt immediately and request human guidance if:
+    1. Retry budget is exhausted on a recurring failure.
+    2. Modification requires undeclared changes to public APIs, DB schemas, or security policies.
+    3. Modification requires touching files outside defined boundaries or in `<out_of_scope>`.
+    *Exception:* Do not stop if the change was explicitly authorized by the user in the prompt/spec, or is a mandatory accompanying test/import update.
+  </escalation_and_stop_conditions>
+
+  <completion_gate>
+    A task is COMPLETE only when:
+    1. All Acceptance Criteria in the active task spec are verified (`- [x]`).
+    2. All validation commands execute with zero errors/warnings.
+    3. The final `git diff` contains zero extraneous or unreviewed modifications.
+  </completion_gate>
+</operational_loop>
+
+---
+
+## 3. Workspace Protocols
+
+<workspace_rules>
+  <rule id="env">Execute all commands inside the designated runtime virtual environment / harness.</rule>
+  <rule id="sync">Only toggle `- [x]` after Phase 4 (Evaluate) and Phase 5 (Reconcile) pass. Never overwrite human-written specs.</rule>
+  <rule id="isolation">Keep edits within this subsystem unless explicit cross-system coordination is requested.</rule>
+  <rule id="subagents">Subagent delegation must adhere to [`process/development-protocols/orchestration.md`](process/development-protocols/orchestration.md).</rule>
+</workspace_rules>
+
+</agent_guidelines>

package/templates/process/README.md

@@ -0,0 +1,58 @@
+# Process & Task Orchestration (RIPER-5)
+
+<process_orchestration version="2.0" framework="RIPER-5">
+
+<overview>
+  Standard template and operational control center for managing engineering tasks and coordinating AI agent execution in this subsystem.
+</overview>
+
+## 1. Directory Structure
+```text
+process/
+├── README.md                    # Operational guide (this file)
+├── _seeds/                      # Read-only archetype blueprints and templates
+│   ├── _GUIDE.md                # Guide on using seeds
+│   ├── task-template.md.seed    # Archetype for single tasks (SPEC, PLAN, REPORT)
+│   ├── program-template.md.seed # Archetype for multi-phase programs (Umbrella PLAN)
+│   └── context-group.md.seed    # Archetype for domain context routers
+├── context/                     # Durable knowledge base & context routers
+│   ├── all-context.md           # Root context router
+│   └── planning/all-planning.md # Planning calibration & vertical slicing rules
+├── development-protocols/       # System rules & execution harness
+│   ├── all-development-protocols.md
+│   ├── orchestration.md         # Subagent delegation rules
+│   └── implementation-standards.md # Typing, linting, and testing standards
+├── features/                    # Domain features (≥5 files / ≥3 phases)
+│   ├── active/                  # Active task folders: {task_slug}_{dd-mm-yy}/
+│   ├── completed/               # Archived task folders
+│   └── backlog/                 # Backlog notes: {note_slug}_NOTE_{dd-mm-yy}.md
+└── general-plans/               # Cross-cutting & standalone tasks
+    ├── active/
+    ├── completed/
+    └── backlog/
+```
+
+## 2. The RIPER-5 Operational Flow
+<operational_phases>
+  <phase order="1" name="Research">
+    Ingest task spec and follow `<information_priority>` (Spec $\rightarrow$ Tests $\rightarrow$ Domain $\rightarrow$ Config $\rightarrow$ Target code).
+  </phase>
+
+  <phase order="2" name="Innovate & Plan">
+    Decompose into vertical slices; populate the execution plan.
+  </phase>
+
+  <phase order="3" name="Produce">
+    Apply minimal atomic edits with strict typing.
+  </phase>
+
+  <phase order="4" name="Evaluate">
+    Run test suites, static type checking, linter and code format checks.
+  </phase>
+
+  <phase order="5" name="Reconcile & Review">
+    Inspect `git diff`, update checkboxes (`- [x]`), verify all Acceptance Criteria.
+  </phase>
+</operational_phases>
+
+</process_orchestration>

package/templates/process/_seeds/_GUIDE.md

@@ -0,0 +1,30 @@
+# Seeds & Archetypes Scaffolding Guide
+
+<seeds_guide version="1.0">
+
+<scope>
+  `_seeds/` is a read-only scaffolding directory containing blueprint templates.
+  Copy and instantiate these seeds when defining new tasks, programs, or context routers.
+</scope>
+
+## 1. Blueprint Catalog
+<catalog>
+  <seed type="task" path="task-template.md.seed">
+    Standard single-task template covering `_SPEC`, `_PLAN`, `_REPORT`, and verifiable Acceptance Criteria.
+  </seed>
+  
+  <seed type="program" path="program-template.md.seed">
+    Multi-phase program blueprint with umbrella planning, phase breakdown, and blast radius registries.
+  </seed>
+
+  <seed type="context" path="context-group.md.seed">
+    Template for creating domain-specific context routers (`all-{group}.md`).
+  </seed>
+</catalog>
+
+## 2. Instantiation Command
+```bash
+cp process/_seeds/task-template.md.seed process/features/your-feature/active/your-task_PLAN_$(date +%d-%m-%y).md
+```
+
+</seeds_guide>

package/templates/process/_seeds/context-group.md.seed

@@ -0,0 +1,24 @@
+# Context Group: [Group Name]
+
+<context_group name="[Group Name]" version="1.0">
+
+<overview>
+  [Domain-specific knowledge base and architectural references for Group Name.]
+</overview>
+
+## 1. Domain Principles & Invariants
+<domain_invariants>
+  - [Invariant 1 — Core business rule]
+  - [Invariant 2 — Data integrity or architectural constraint]
+</domain_invariants>
+
+---
+
+## 2. Key References & System Contracts
+<references>
+  <domain_models>`src/domain/...`</domain_models>
+  <port_interfaces>`src/application/port_...`</port_interfaces>
+  <adapters>`src/infrastructure/...`</adapters>
+</references>
+
+</context_group>

package/templates/process/_seeds/program-template.md.seed

@@ -0,0 +1,56 @@
+# Multi-Phase Program: [PROG-ID] [Program Name]
+
+<program_umbrella_plan version="2.0" framework="RIPER-5">
+
+<metadata>
+  <program_id>[PROG-ID]</program_id>
+  <lead>@engineering_lead</lead>
+  <target_timeline>[e.g. Sprint 1-3]</target_timeline>
+</metadata>
+
+## 1. Executive Strategy & Outcome
+<strategy>
+  <target_outcome>
+    [High-level measurable architectural or business goal.]
+  </target_outcome>
+
+  <system_impact>
+    [Affected subsystems, downstream services, or performance targets.]
+  </system_impact>
+</strategy>
+
+---
+
+## 2. Phase Breakdown & Blast Radius
+<phase_breakdown>
+  <phase number="1" id="phase-01">
+    <title>[Domain Models & Port Interfaces]</title>
+    <scope>`src/domain/`, `src/application/port_*`</scope>
+    <blast_radius level="LOW">Zero external dependency impacts</blast_radius>
+    <status>NOT_STARTED</status>
+  </phase>
+
+  <phase number="2" id="phase-02">
+    <title>[Infrastructure Adapters & Persistence]</title>
+    <scope>`src/infrastructure/`</scope>
+    <blast_radius level="MEDIUM">Depends on Phase 01 domain contracts</blast_radius>
+    <status>NOT_STARTED</status>
+  </phase>
+
+  <phase number="3" id="phase-03">
+    <title>[API Exposure & End-to-End Integration]</title>
+    <scope>`src/api/`</scope>
+    <blast_radius level="HIGH">Exposes public HTTP endpoints and DTO contracts</blast_radius>
+    <status>NOT_STARTED</status>
+  </phase>
+</phase_breakdown>
+
+---
+
+## 3. Global Invariants & Phase Gate Rules
+<phase_gates>
+  <rule>Every phase must pass 100% of validation commands before the next phase begins.</rule>
+  <rule>No phase may introduce breaking changes to existing public APIs without prior approval.</rule>
+</phase_gates>
+
+</program_umbrella_plan>

package/templates/process/_seeds/task-template.md.seed

@@ -0,0 +1,93 @@
+# Task: [TASK-ID] [Task Title]
+
+<task_spec version="2.0" framework="RIPER-5">
+
+<status>
+  <phase>PLANNING</phase> <!-- RESEARCHING | PLANNING | PRODUCING | EVALUATING | RECONCILED | COMPLETED -->
+  <state>IN_PROGRESS</state>
+  <assignee>@agent_or_human</assignee>
+</status>
+
+## 1. Specification (Pillar 1: Task / Spec)
+<specification>
+  <goal>
+    [Target outcome, business value, or functional capability.]
+  </goal>
+
+  <current_behavior>
+    [Current behavior prior to this change.]
+  </current_behavior>
+
+  <expected_behavior>
+    [Expected behavior once the change is complete.]
+  </expected_behavior>
+
+  <invariants>
+    - [Invariant 1 — Conditions that must remain true.]
+  </invariants>
+
+  <out_of_scope>
+    - [Explicitly excluded components, refactoring, or undeclared API/schema changes.]
+  </out_of_scope>
+
+  <acceptance_criteria>
+    - [ ] [AC-1: Verifiable functional behavior with explicit input and expected output]
+    - [ ] [AC-2: Edge cases, validation rules, or error handling]
+    - [ ] [AC-3: Automated tests added/updated and passing]
+  </acceptance_criteria>
+</specification>
+
+---
+
+## 2. Context Boundaries (Pillar 2: Context)
+<context_boundaries>
+  <target_files>
+    - `src/[path/to/file]` — [Planned modification]
+    - `tests/[path/to/test_file]` — [Target assertions and test fixtures]
+  </target_files>
+</context_boundaries>
+
+---
+
+## 3. RIPER-5 Execution Plan (Pillar 4: Loop)
+<execution_plan>
+  <phase name="Research">
+    - [ ] Ingest task spec, domain invariants, and out-of-scope boundaries.
+    - [ ] Read corresponding tests and port interfaces.
+  </phase>
+
+  <phase name="Innovate & Plan">
+    - [ ] Step 1: [Design domain models / port contracts]
+    - [ ] Step 2: [Formulate test strategy and edge cases]
+  </phase>
+
+  <phase name="Produce">
+    - [ ] Step 1: [Implement core logic with strict typing]
+    - [ ] Step 2: [Implement automated unit/integration tests]
+  </phase>
+
+  <phase name="Evaluate">
+    - [ ] Execute focused tests and full validation suite.
+  </phase>
+
+  <phase name="Reconcile & Review">
+    - [ ] Review `git diff` for zero unwanted changes or debug statements.
+    - [ ] Verify all Acceptance Criteria are satisfied (`- [x]`).
+    - [ ] Mark phase as COMPLETED.
+  </phase>
+</execution_plan>
+
+---
+
+## 4. Guardrails & Escalation (Pillar 3 & 4: Harness)
+<guardrails>
+  <open_decisions>
+    <!-- Log any technical trade-offs or items requiring human guidance here -->
+  </open_decisions>
+
+  <retry_budget max_attempts="3">
+    Maximum 3 consecutive attempts per distinct failure symptom before halting.
+  </retry_budget>
+</guardrails>
+
+</task_spec>

package/templates/process/context/all-context.md

@@ -0,0 +1,30 @@
+# Root Context Router
+
+<context_router version="1.0">
+
+<description>
+  Central durable knowledge index routing to specialized domain context groups across the system.
+</description>
+
+## Context Directory Index
+<context_groups>
+  <group id="planning">
+    <title>Planning Standards & Calibration</title>
+    <path>[`planning/all-planning.md`](planning/all-planning.md)</path>
+    <scope>INVEST criteria, vertical slicing rules, Story Point capacity calibration</scope>
+  </group>
+
+  <group id="seeds">
+    <title>Seeds & Archetypes Guide</title>
+    <path>[`../_seeds/_GUIDE.md`](../_seeds/_GUIDE.md)</path>
+    <scope>Scaffolding seeds for tasks, programs, and context groups</scope>
+  </group>
+
+  <group id="protocols">
+    <title>Development Protocols Index</title>
+    <path>[`../development-protocols/all-development-protocols.md`](../development-protocols/all-development-protocols.md)</path>
+    <scope>Engineering harness, subagent orchestration, and code standards</scope>
+  </group>
+</context_groups>
+
+</context_router>

package/templates/process/context/planning/all-planning.md

@@ -0,0 +1,31 @@
+# Planning Standards & Calibration Context
+
+<planning_context version="1.0">
+
+<overview>
+  Guidelines for story point estimation, vertical slicing, and capacity calibration.
+</overview>
+
+## 1. Quality Standards
+<quality_standards>
+  <standard name="INVEST">
+    - **Independent:** Deliverable without cross-story blockers.
+    - **Negotiable:** Implementation details are flexibly refined.
+    - **Valuable:** Delivers measurable user or business value.
+    - **Estimable:** Scoped clearly to estimate effort.
+    - **Small:** Fits within 1-3 engineering days.
+    - **Testable:** Concrete Acceptance Criteria defined.
+  </standard>
+
+  <standard name="Vertical Slicing">
+    Avoid horizontal silos. Deliver end-to-end vertical slices across API, logic, and persistence.
+  </standard>
+</quality_standards>
+
+## 2. Capacity Calibration
+<capacity_calibration>
+  <unit>1 Story Point ≈ 2-4 focused engineering hours</unit>
+  <max_task_size>3-5 Story Points (larger tasks must be decomposed)</max_task_size>
+</capacity_calibration>
+
+</planning_context>

package/templates/process/development-protocols/all-development-protocols.md

@@ -0,0 +1,27 @@
+# Development Protocols Index
+
+<protocols_router version="1.0">
+
+<description>
+  Central router for engineering protocols, subagent orchestration, and code quality standards.
+</description>
+
+## Protocol Catalog
+<protocol_list>
+  <protocol name="Subagent Orchestration">
+    <path>[`orchestration.md`](orchestration.md)</path>
+    <description>Rules for subagent delegation, isolation, and reactive coordination</description>
+  </protocol>
+
+  <protocol name="Implementation & Testing Standards">
+    <path>[`implementation-standards.md`](implementation-standards.md)</path>
+    <description>Strict typing, code hygiene, and test harness standards</description>
+  </protocol>
+
+  <protocol name="System Agent Guidelines & RIPER-5">
+    <path>[`../../AGENTS.md`](../../AGENTS.md)</path>
+    <description>Core 4 pillars and RIPER-5 operational loop specification</description>
+  </protocol>
+</protocol_list>
+
+</protocols_router>

package/templates/process/development-protocols/implementation-standards.md

@@ -0,0 +1,28 @@
+# Implementation & Harness Standards
+
+<implementation_standards version="1.0">
+
+<description>
+  Engineering quality, type safety, and testing conventions for this codebase.
+</description>
+
+## 1. Type Safety & Code Hygiene
+<conventions>
+  <rule id="strict_typing">
+    All functions, methods, and class attributes must have explicit type annotations. Use modern union types (`int | None` or `string | null`) and avoid untyped `Any`/`any` unless interfacing with raw external payloads.
+  </rule>
+  <rule id="domain_purity">
+    Code in domain layers must remain pure with zero external infrastructure dependencies.
+  </rule>
+  <rule id="immutability">
+    Prefer immutable models for domain events, value objects, and DTOs.
+  </rule>
+</conventions>
+
+## 2. Test Architecture
+<test_structure>
+  - `tests/unit/`: Fast, isolated tests for domain models, core logic, and mock adapters.
+  - `tests/integration/`: End-to-end flow tests with test services or local databases.
+</test_structure>
+
+</implementation_standards>

package/templates/process/development-protocols/orchestration.md

@@ -0,0 +1,24 @@
+# Subagent Delegation & Orchestration Protocol
+
+<orchestration_protocol version="1.0">
+
+<description>
+  Guidelines for delegating, isolating, and coordinating subagents during complex tasks.
+</description>
+
+## 1. Delegation Principles
+<delegation_rules>
+  <rule id="explicit_scope">
+    Always specify exact files, function signatures, and expected structured output formats.
+  </rule>
+
+  <rule id="context_containment">
+    Do not grant unbounded repo access; constrain subagent context to relevant test suites and port contracts.
+  </rule>
+
+  <rule id="no_polling">
+    Rely on the system's reactive message wakeup mechanism when subagents complete their execution.
+  </rule>
+</delegation_rules>
+
+</orchestration_protocol>