@jakkrichm/create-nexus-devflow 2.0.15 → 2.0.18

package/template/.claude/skills/implement/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: implement
-description: "[Devflow] Fast-Track Implement stage in DevFlow (Blueprint Mode) - execute checklist tasks incrementally with TDD and update spec.md."
+description: "[Devflow] Fast-Track Implement stage in DevFlow (Blueprint Mode) - execute checklist tasks incrementally with TDD and update current-feature.md in context."
 argument-hint: "{running-id or workspace path}"
 ---
 
@@ -8,18 +8,18 @@ argument-hint: "{running-id or workspace path}"
 
 $ARGUMENTS
 
-Incremental code execution stage in Fast-Track. Reads the Single Living Spec (`spec.md`), executes checklist tasks, implements tests (TDD), and updates the implementation record.
+Incremental code execution stage in Fast-Track. Reads the Single Living Spec (`devflow/context/current-feature.md`), executes checklist tasks, implements tests (TDD), and updates the implementation record.
 
 ## Invocations & Aliases
 
 - `/implement`: Run implementation on current active run
-- `/implement {running-id}`: Run implementation on specified running ID
+- `/implement {id}`: Run implementation on specified ID
 - `$implement`: Codex CLI invocation
 
 ## Fast-Track Mainline Workflow
 
 ```text
-/spec ──▶ /implement ──▶ /check ──▶ /complete
+/feature (หรือ /fix) ──▶ /implement ──▶ /check ──▶ /complete
 ```
 
 ## Behavior & Contract
@@ -27,8 +27,8 @@ Incremental code execution stage in Fast-Track. Reads the Single Living Spec (`s
 When invoked:
 
 ### 1. Load Active Context
-1. Identify active Running ID from `devflow/context/current-stage.md` or argument.
-2. Read `devflow/runs/{RUNNING_ID}/spec.md`.
+1. Identify active Running ID from `devflow/context/current-stage.md` or `devflow/context/current-feature.md`.
+2. Read `devflow/context/current-feature.md`.
 3. Locate `## 2. Plan & Test Strategy` and `## 3. Implementation Checklist`.
 
 ### 2. Incremental Execution with TDD
@@ -37,10 +37,10 @@ When invoked:
    - **TDD (Red-Green-Refactor)**: When `Test Decision: Required`, create or update unit tests first.
    - Implement the minimal, clean code change satisfying the task.
    - Run localized verification (e.g. `npm test`, linter).
-   - Mark the item as `- [x]` in `spec.md`.
+   - Mark the item as `- [x]` in `current-feature.md`.
 
-### 3. Update Living Spec (`spec.md`)
-Append or update `## 4. Implementation Record` in `spec.md` with:
+### 3. Update Living Spec (`current-feature.md`)
+Append or update `## 4. Implementation Record` in `devflow/context/current-feature.md` with:
 - Summary of completed tasks and modified files
 - Key architectural observations or notes
 - Status of checklist items
@@ -61,4 +61,4 @@ Update `devflow/context/current-stage.md`:
 Report to the user:
 - Completed checklist items and modified files
 - Local verification results
-- **Next Command**: `/check` (or `/check {RUNNING_ID}`)
+- **Next Command**: `/check` (or `/check {ID}`)

package/template/.claude/skills/insight/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: insight
-description: "[Devflow] Extract reusable lessons, architectural patterns, post-mortem incident learning, and token optimizations from completed work."
+description: "[Devflow] Extract reusable lessons, patterns, file insights, and post-mortem learning from completed work."
 ---
 
 # Insight Extraction & Post-Mortem Learning

package/template/.claude/skills/overview/SKILL.md

@@ -13,7 +13,7 @@ codebase + devflow/history/HISTORY.md  ->  [overview]  ->  devflow/context/proje
                                              synthesize)
 ```
 
-`overview` is the context synchronization and synthesis engine for Nexus-DevFlow. It inspects the actual codebase (manifest, dependencies, directory layout, models/schemas, entry points) along with the completed delivery history (`devflow/history/HISTORY.md` and `devflow/runs/`) to build or refresh `devflow/context/project-overview.md`.
+`overview` is the context synchronization and synthesis engine for Nexus-DevFlow. It inspects the actual codebase (manifest, dependencies, directory layout, models/schemas, entry points) along with the completed delivery history (`devflow/history/HISTORY.md` and `devflow/history/`) to build or refresh `devflow/context/project-overview.md`.
 
 It ensures that `project-overview.md` remains a **Living Source of Truth** that evolves alongside your software, rather than a stale artifact left behind after onboarding.
 
@@ -26,7 +26,7 @@ overview
 ```
 
 Use this when:
-- Multiple delivery runs (`RUN-xxx`) have shipped and `project-overview.md` needs to reflect newly added capabilities.
+- Multiple delivery runs (`xxx-slug`) have shipped and `project-overview.md` needs to reflect newly added capabilities.
 - New database schemas, ORM models, or API boundaries were introduced.
 - Major dependencies or architectural patterns were added or modified.
 - After completing `70-release` to keep project context perfectly aligned.
@@ -59,7 +59,7 @@ Inspect the actual codebase to establish hard facts:
 Inspect DevFlow history records:
 
 1. Read `devflow/history/HISTORY.md` for completed and released milestones.
-2. Scan completed delivery runs in `devflow/runs/` to extract shipped user-visible capabilities and core system features.
+2. Scan completed delivery runs in `devflow/history/features/`, `devflow/history/fixes/`, and `devflow/history/rollbacks/` to extract shipped user-visible capabilities and core system features.
 
 ---
 

package/template/.claude/skills/report-html/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: report-html
-description: "[Devflow] Standalone HTML Report Generator - render an interactive standalone HTML dashboard from spec.md or 60-report.md on demand."
+description: "[Devflow] Standalone HTML Report Generator - render an interactive standalone HTML dashboard from current-feature.md or 60-report.md on demand."
 argument-hint: "{running-id or workspace path}"
 ---
 
@@ -8,7 +8,7 @@ argument-hint: "{running-id or workspace path}"
 
 $ARGUMENTS
 
-Standalone companion command to generate an interactive, self-contained HTML report dashboard on demand from either a Fast-Track `spec.md` or a Deep-Track `60-report.md`.
+Standalone companion command to generate an interactive, self-contained HTML report dashboard on demand from either a Fast-Track `current-feature.md` or a Deep-Track `60-report.md`.
 
 > [!NOTE]
 > HTML reports are **never automatically generated** during normal mainline stages (`/complete` or `60-report`). Use this command whenever you or stakeholders wish to view or share an interactive web report.
@@ -27,7 +27,7 @@ When invoked:
 ### 1. Identify Target Run
 1. Locate target run directory in `devflow/runs/{running-id}` from argument or `devflow/context/current-stage.md`.
 2. Check for either:
-   - Fast-Track Living Spec: `devflow/runs/{RUNNING_ID}/spec.md` (or `blueprint.md`)
+   - Fast-Track Living Spec: `devflow/runs/{RUNNING_ID}/current-feature.md` (or `spec.md` / `blueprint.md`)
    - Deep-Track Report Digest: `devflow/runs/{RUNNING_ID}/60-report.md`
 
 ### 2. Render Interactive HTML Dashboard

package/template/.claude/skills/security-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: security-review
-description: "[Devflow] Security review, vulnerability scanner, and code hardening. Audits for OWASP vulnerabilities, secrets, injections, and auth flaws."
+description: "[Devflow] High-severity security code review and vulnerability audit for folders, projects, files, or diffs."
 ---
 
 # Security Review, Hardening & Vulnerability Audit

package/template/.claude/skills/spec/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: spec
-description: "[Devflow] Fast-Track Spec router in DevFlow (Blueprint Mode) - aliases and routes to /feature or /fix to create the single living spec.md contract."
+description: "[Devflow] Fast-Track Spec router in DevFlow (Blueprint Mode) - aliases and routes to /feature or /fix to create the living current-feature.md contract in context."
 argument-hint: "{feature title, bug description, IDEA-xxx, or running-id}"
 ---
 
@@ -8,7 +8,7 @@ argument-hint: "{feature title, bug description, IDEA-xxx, or running-id}"
 
 $ARGUMENTS
 
-Unified Fast-Track entry point that routes to `/feature` or `/fix` to create and maintain the **Single Living Spec (`spec.md`)**.
+Unified Fast-Track entry point that routes to `/feature` or `/fix` to create and maintain the **Single Living Spec (`devflow/context/current-feature.md`)**.
 
 > [!TIP]
 > **Preferred Commands**:
@@ -32,7 +32,8 @@ Unified Fast-Track entry point that routes to `/feature` or `/fix` to create and
 
 When invoked:
 
-1. If the input describes a bug or hotfix, routes to `/fix` behavior.
-2. Otherwise, routes to `/feature` behavior.
-3. Allocates sequential Running ID (`RUN-xxx`), creates directory `devflow/runs/{RUNNING_ID}/`, and generates `spec.md` in **Thai (`th`)**.
-4. Updates `devflow/context/current-stage.md` and reports next step: `/implement`.
+1. Checks Single Active Run Guardrail: rejects if an uncompleted active run already exists in `devflow/context/current-stage.md` or `devflow/context/current-feature.md`.
+2. If the input describes a bug or hotfix, routes to `/fix` behavior.
+3. Otherwise, routes to `/feature` behavior.
+4. Allocates sequential ID without prefix (`xxx-slug`), generates `devflow/context/current-feature.md` in **Thai (`th`)**.
+5. Updates `devflow/context/current-stage.md` and reports next step: `/implement`.

package/template/.claude/skills/spec-driven-development/SKILL.md

@@ -83,8 +83,8 @@ Don't silently fill in ambiguous requirements. The spec's entire purpose is to s
 
 Every specification must stand on its own in markdown under `devflow/runs/{ID}-*/`:
 
-1. **`define.md`**: Decision and scope framing when the problem still needs clarification.
-2. **`spec.md`**: The delivery contract following the template below.
+1. **`current-feature.md`**: Fast-Track Single Living Spec delivery contract.
+2. **`20-spec.md`**: Deep-Track formal specification delivery contract.
 
 **Spec template:**
 

package/template/.claude/skills/test/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: test
-description: "[Devflow] Test-driven development, test generation, test execution, and coverage analysis across unit, integration, and smoke test suites."
+description: "[Devflow] Test execution, missing test generation, and coverage analysis across unit, integration, and smoke test suites."
 ---
 
 # Test-Driven Development, Generation & Execution

package/template/AGENTS.md

@@ -1,12 +1,13 @@
-# Nexus-DevFlow 2.0 (Dual-Track Blueprint & Architect Model)
+# Nexus-DevFlow 2.0 (The 3-Pillars & Dual-Track Model)
 
 Instructions for AI coding agents working in this project. This is the cross-tool entry point: Codex, Google Antigravity, Cursor, GitHub Copilot, Gemini CLI, Aider, Zed, Windsurf, and others read `AGENTS.md`. Claude Code reads `CLAUDE.md`, which imports this file (`@AGENTS.md`), so there is a single source of truth.
 
 ## What this is
 
-This project uses **Nexus-DevFlow**, an agentic workflow layer supporting **Dual-Track Delivery**:
-1. **🏎️ Fast-Track (Blueprint Mode - 4 Steps)**: High-velocity spec-driven loop driven by a **Single Living Spec (`spec.md`)**.
-2. **🏗️ Deep-Track (Architect Mode - 8 Steps)**: Full-lifecycle delivery pipeline with modular stage artifacts (`00-70`).
+This project uses **Nexus-DevFlow**, an agentic workflow layer supporting **The 3-Pillars Workspace Architecture & Dual-Track Delivery**:
+1. **🔮 Future (Backlog)**: `devflow/ideas.md` — Centralized Idea Inbox with AI scoring.
+2. **⚡ Present (Active Context)**: `devflow/context/` — Living Source of Truth & Active Work (`current-feature.md` for Fast-Track, `current-run/` for Deep-Track).
+3. **📦 Past (History Archive)**: `devflow/history/` — Categorized delivery archives (`features/`, `fixes/`, `rollbacks/`, and `HISTORY.md`).
 
 To start a new project, scaffold the application first in an empty folder, then run `npx @jakkrichm/create-nexus-devflow` to overlay DevFlow onto your codebase.
 
@@ -35,8 +36,8 @@ Unused adapter families can be removed. Codex and Antigravity projects keep `.ag
    - **Dollar Prefix (`$`)**: For OpenAI Codex CLI or skill-invocation tools, e.g., `$feature`, `$fix`, `$40-execute`, `$devflow`.
 2. **OpenAI Codex & Non-Native CLI Tools**: In environments without automatic background skill discovery (such as OpenAI Codex CLI, Aider, or generic terminals), **you MUST use your file reading tool to inspect `.agents/skills/<skill>/SKILL.md` before executing the stage** to strictly follow its schema, artifact contract, and quality gates.
 3. **Google Antigravity & Claude Code**: Native skill engines automatically discover and surface `.agents/skills/` and `.claude/skills/`.
-4. **State-Aware Inspection**: When unsure what to do next, invoke `devflow` to automatically inspect `devflow/context/current-stage.md` and active runs in `devflow/runs/`.
-5. **Default Artifact & Communication Language (Thai)**: All generated markdown stage artifacts (`spec.md`, `00-discover.md`...`70-release.md`) and user communication MUST default to **Thai (`th`)**, while code, technical terms, file paths, and identifiers remain in English.
+4. **State-Aware Inspection**: When unsure what to do next, invoke `devflow` to automatically inspect `devflow/context/current-stage.md` and active context in `devflow/context/`.
+5. **Default Artifact & Communication Language (Thai)**: All generated markdown stage artifacts (`current-feature.md`, `00-discover.md`...`70-release.md`) and user communication MUST default to **Thai (`th`)**, while code, technical terms, file paths, and identifiers remain in English.
 
 ---
 
@@ -49,14 +50,14 @@ Recommended for 85% of daily work (features, bug fixes, UI improvements, iterati
 ```
 
 1. **`feature` / `fix` (`/feature`, `/fix`, `/spec`)**:
-   - **Purpose**: Combines Discover, Define, Spec, and Plan into one unified step. Allocates sequential Running ID (`RUN-xxx`) and creates the **Single Living Spec (`spec.md`)**.
-   - **Artifact**: `devflow/runs/{running-id}-{slug}/spec.md`
+   - **Purpose**: Combines Discover, Define, Spec, and Plan into one unified step. Checks Single Active Run Guardrail, allocates sequential ID (`xxx-slug`), and creates the **Single Living Spec (`devflow/context/current-feature.md`)**.
+   - **Artifact**: `devflow/context/current-feature.md`
 2. **`implement` (`/implement`)**:
-   - **Purpose**: Incrementally executes checklist tasks with TDD discipline and appends progress to `spec.md`.
+   - **Purpose**: Incrementally executes checklist tasks with TDD discipline and appends progress to `devflow/context/current-feature.md`.
 3. **`check` (`/check`)**:
-   - **Purpose**: Senior QA review, multi-lane verification matrix (Typecheck, Lint, Test suites, manual proof), and records evidence into `spec.md`.
+   - **Purpose**: Senior QA review, multi-lane verification matrix (Typecheck, Lint, Test suites, manual proof), and records evidence into `devflow/context/current-feature.md`.
 4. **`complete` (`/complete`)**:
-   - **Purpose**: Final safety pass, records Release Digest in `spec.md`, performs git merge, and closes the run without auto HTML generation.
+   - **Purpose**: Final safety pass, records Release Digest, automatically archives to `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`, resets the stub, performs git merge, and closes the run without auto HTML generation.
 
 ---
 
@@ -69,13 +70,13 @@ Recommended for large architectural epics, database migrations, and multi-agent
 ```
 
 1. `00-discover`: Explore request before delivery commitment without allocating running ID (`00-discover.md`).
-2. `10-define`: Turn approved discovery into bounded delivery run(s) with sequential Running IDs (`10-define.md`).
+2. `10-define`: Turn approved discovery into bounded delivery run in `devflow/context/current-run/10-define.md`.
 3. `20-spec`: Formalize markdown-first delivery contract & acceptance criteria (`20-spec.md`).
 4. `30-plan`: Breakdown spec into executable tasks with test decisions (`30-plan.md` + checklists).
 5. `40-execute`: Incremental task execution behind review gates (`40-execute.md`).
 6. `50-verify`: Senior QA review & multi-lane verification checks (`50-verify.md`).
 7. `60-report`: Standardized markdown delivery digest (`60-report.md`).
-8. `70-release`: Release packaging, release notes, git merge, and deployment (`70-release.md`).
+8. `70-release`: Release packaging, git merge, archives `devflow/context/current-run/` ➔ `devflow/history/{category}/{xxx-slug}/`, and closes run.
 
 ---
 
@@ -84,55 +85,10 @@ Recommended for large architectural epics, database migrations, and multi-agent
 > [!IMPORTANT]
 > **No Auto-Generated HTML**: Mainline flows (`/complete` and `60-report`) strictly output Markdown only.
 > When an interactive web dashboard is desired for presentation or sharing, invoke the standalone companion command:
-> `/report:html` (or `npm run report:html -- {RUNNING_ID}`).
+> `/report:html` (or `npm run report:html -- {ID}`).
 
 ---
 
-## Public Companion Commands
-
-- `devflow`: Flagship interactive guide, state inspector, and intent router.
-- `idea` (`/idea`): Quick idea capture and AI feasibility enrichment into `devflow/ideas.md`.
-- `report-html` (`/report:html`): Standalone interactive HTML report dashboard generator.
-- `onboard`: Initial stack detection and baseline setup for fresh/scaffolded projects.
-- `adopt`: Survey existing brownfield codebases and bootstrap DevFlow context.
-- `doctor`: Read-only health check for context files, adapters, commands, and workflow drift.
-- `try`: Step-by-step human manual QA review guide (where to go, what to click, what to expect).
-- `rollback`: Safe feature/run reversal planner with dependency and commit risk analysis.
-- `ci`: Automatic GitHub Actions workflow (`.github/workflows/verify.yml`) setup and alignment.
-- `brief`: Read-only scope, dependency, and size pre-briefing before speccing a run.
-- `autopilot`: Optional explicit mode for one bounded spec/plan/implement/verify/report pass.
-- `goal`: Route broad, open-ended goals before Discovery.
-- `brainstorm`: Structured divergent & convergent ideation without creating running IDs.
-- `research`: Conduct deep codebase or web research with source-backed citations.
-- `debug`: Root cause investigation before or during implementation without editing code.
-- `overview`: Refresh `devflow/context/project-overview.md`.
-- `wiki`: Knowledge base management under `devflow/wiki/`.
-- `check-for-updates`: Verify or upgrade DevFlow setup.
-- `help`: Routing and process assistance across DevFlow workflows.
-
----
-
-## Invocation Reference
-
-| Track / Category | Canonical Name | Claude / Antigravity (`/`) | OpenAI Codex (`$`) | Purpose / Action |
-| :--- | :--- | :--- | :--- | :--- |
-| **Fast: Feature** | `feature` | `/feature` | `$feature` | 4-step Fast-Track spec & living spec creation for new features (supports `IDEA-xxx`) |
-| **Fast: Fix** | `fix` | `/fix` | `$fix` | 4-step Fast-Track spec & living spec creation for bug fixes (supports `IDEA-xxx`) |
-| **Fast: Implement** | `implement` | `/implement` | `$implement` | Fast-Track incremental execution with TDD |
-| **Fast: Check** | `check` | `/check` | `$check` | Fast-Track QA review & multi-lane verification |
-| **Fast: Complete** | `complete` | `/complete` | `$complete` | Fast-Track safety pass, release digest & git merge |
-| **Idea Capture** | `idea` | `/idea` | `$idea` | Quick idea capture and AI feasibility enrichment |
-| **HTML Report** | `report-html` | `/report:html` | `$report:html` | Standalone interactive HTML dashboard generator |
-| **Deep: 00** | `00-discover` | `/00-discover` | `$00-discover` | Explore request and decide Proceed, Defer, or Reject |
-| **Deep: 10** | `10-define` | `/10-define` | `$10-define` | Turn approved discovery into bounded delivery run(s) |
-| **Deep: 20** | `20-spec` | `/20-spec` | `$20-spec` | Formal markdown delivery contract & acceptance criteria |
-| **Deep: 30** | `30-plan` | `/30-plan` | `$30-plan` | Breakdown spec into executable tasks with test decisions |
-| **Deep: 40** | `40-execute` | `/40-execute` | `$40-execute` | Execute planned tasks in small reviewable increments (`40-execute.md`) |
-| **Deep: 50** | `50-verify` | `/50-verify` | `$50-verify` | Senior QA review & multi-lane verification checks |
-| **Deep: 60** | `60-report` | `/60-report` | `$60-report` | Standalone markdown summary report |
-| **Deep: 70** | `70-release` | `/70-release` | `$70-release` | Package for delivery, git merge, PR, or deployment |
-| **Router** | `devflow` | `/devflow` | `$devflow` | Interactive guide, state inspector, and intent router |
-
 ## Commands
 
 - Dev Server: `npm run dev`

package/template/devflow/context/ai-interaction.md

@@ -1,35 +1,122 @@
-# AI Interaction Guidelines for DevFlow
+# AI Interaction Guidelines for Nexus-DevFlow
 
-> **DevFlow is an agentic workflow layer**, overlaying on top of scaffolded or existing codebases.
+> **Nexus-DevFlow is an agentic workflow layer**, overlaying on top of scaffolded or existing codebases. Never run a framework scaffolder inside an initialized DevFlow directory.
 
-## Communication & Interaction
+---
 
-- Be concise and direct in communication.
-- Explain technical trade-offs and non-obvious design decisions briefly.
-- Always confirm before performing major refactors or destructive operations.
-- Maintain markdown-first evidence for all stage activities.
+## 1. Communication & Principles
 
-## Artifact Language
+- **Be Concise and Direct**: State conclusions, status, and findings first; provide supporting context afterward.
+- **Explain Non-Obvious Decisions Briefly**: Highlight architectural trade-offs, edge-case rationale, or safety considerations in 1–2 sentences.
+- **Ask Before Destructive or Architectural Changes**: Always obtain explicit confirmation before deleting files, executing major refactors, or altering public interfaces.
+- **Don't Add Unplanned Scope**: Stick strictly to the Acceptance Criteria defined in the spec. Avoid adding "nice-to-have" features that were not requested.
+- **Preserve Existing Codebase Patterns**: Respect existing file structure, typing patterns, naming conventions, and deep module boundaries.
 
-- Default language for user-facing artifacts and summaries is Thai (`th`), while code, paths, and identifiers remain in English.
-- Use exact schema headings when validators check for specific contract sections.
+---
 
-## Output Formatting
+## 2. Output Formatting
 
-- Use GitHub-style markdown for clean scanning.
-- Use lists for steps, options, and findings.
-- Use tables for comparative matrices or stage summaries.
-- Use backticks for paths, filenames, identifiers, and CLI commands.
+Format every response for fast scanning and readability:
 
-## DevFlow Timeline Lifecycle
+- **Real Markdown, Not Prose Walls**: Use bold labels, concise bullet points, and blank lines between blocks.
+- **Enumerations Are Lists**: Numbered or bulleted lists for sequential steps or findings, never inline runs crammed into paragraphs.
+- **Tables for Comparative Matrices**: Use markdown tables when comparing status, options, test results, or trade-offs.
+- **Backticks for Code References**: Wrap file paths, variable names, functions, CLI flags, and commands in backticks (e.g. `current-feature.md`, `npm run check`).
+- **Clickable File Links**: Use GitHub-style markdown links with `file://` scheme (e.g. `[current-feature.md](file:///d:/path/to/current-feature.md)`).
+- **Lead With the Result**: State pass/fail status or completed action before presenting logs.
+
+---
+
+## 3. Dual-Track Workflow Lifecycle (The 3-Pillars Model)
 
 ```text
-/00-Discover -> /10-Define -> /20-Spec -> /30-Plan -> /40-Execute -> /50-Verify -> /60-Report -> /70-Release
+devflow/
+├── 🔮 ideas.md        # [Future] Idea Inbox
+├── ⚡ context/         # [Present] Living Spec (current-feature.md) & Active State
+└── 📦 history/         # [Past] features/, fixes/, rollbacks/, and HISTORY.md
 ```
 
-- Run `/00-Discover` to explore requests under a Discovery ID.
-- Run `/10-Define` to set delivery boundaries and allocate Running IDs.
-- Run `/20-Spec` and `/30-Plan` to establish formal delivery specifications and execution plans.
-- Run `/40-Execute` for step-by-step code implementation with evidence.
-- Run `/50-Verify`, `/60-Report`, and `/70-Release` for quality verification, reporting, and release packaging.
-- Use **Fast-Track / Quick-Fix mode** for minor hotfixes to skip heavy ceremony while keeping test evidence.
+### 🏎️ Track 1: Fast-Track (Blueprint Mode — 4 Steps)
+*Recommended for 85% of daily engineering work (features, bug fixes, UI improvements, iterative refactoring).*
+
+The entire lifecycle is driven by the **Single Living Spec (`devflow/context/current-feature.md`)**:
+
+1. **Spec (`/feature` or `/fix`)**:
+   - Checks **Single Active Run Guardrail** (rejects if an uncompleted task is still active).
+   - Analyzes request (or consumes `IDEA-xxx` from `devflow/ideas.md`).
+   - Allocates sequential ID without prefix (e.g. `022-{slug}`) and creates branch `feature/{xxx-slug}` or `fix/{xxx-slug}`.
+   - Generates `devflow/context/current-feature.md` containing **Section 1 (Scope & AC)**, **Section 2 (Plan & Test Strategy)**, and **Section 3 (Checklist)**.
+2. **Implement (`/implement`)**:
+   - Executes checklist tasks incrementally one small diff at a time using **TDD (Red-Green-Refactor)**.
+   - Updates `## 4. Implementation Record` and marks tasks `- [x]` in `current-feature.md`.
+3. **Check (`/check`)**:
+   - Senior QA multi-lane verification (Lane 1: Typecheck/Lint, Lane 2: Test Suites, Lane 3: Manual Proof).
+   - Records empirical proof under `## 5. Verification Evidence` in `current-feature.md`.
+4. **Complete (`/complete`)**:
+   - Final safety pass, updates `## 6. Release & Handoff` digest in `current-feature.md`.
+   - Automatically archives `current-feature.md` ➔ `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`.
+   - Appends resolved findings and cleans `findings.md`.
+   - Resets `current-feature.md` back to the idle stub.
+   - Performs Git squash-merge into `main`, updates `devflow/history/HISTORY.md`, and sets workspace to Idle.
+
+---
+
+### 🏗️ Track 2: Deep-Track (Architect Mode — 8 Steps)
+*Recommended for large architectural epics, database migrations, security audits, and multi-agent coordination.*
+
+```text
+00-discover ➔ 10-define ➔ 20-spec ➔ 30-plan ➔ 40-execute ➔ 50-verify ➔ 60-report ➔ 70-release
+```
+
+1. `00-discover`: Explore request before delivery commitment (`DISC-YYYYMMDD-NNN`).
+2. `10-define`: Turn approved discovery into bounded delivery run in `devflow/context/current-run/10-define.md`.
+3. `20-spec`: Formalize markdown delivery contract & acceptance criteria (`20-spec.md`).
+4. `30-plan`: Breakdown spec into executable tasks with test decisions (`30-plan.md` + checklists).
+5. `40-execute`: Incremental task execution behind review gates (`40-execute.md`).
+6. `50-verify`: Senior QA review & multi-lane verification checks (`50-verify.md`).
+7. `60-report`: Standardized markdown delivery digest (`60-report.md`).
+8. `70-release`: Release packaging, git merge, archives `devflow/context/current-run/` ➔ `devflow/history/{features|fixes|rollbacks}/{xxx-slug}/`, and closes the run.
+
+---
+
+## 4. Standalone HTML Reporting Policy
+
+> [!IMPORTANT]
+> **No Auto-Generated HTML**: Mainline stages (`/complete` and `60-report`) strictly output Markdown only.
+> When an interactive web dashboard is desired for presentation or sharing, invoke the standalone companion command:
+> `/report:html` (or `npm run report:html -- {ID}`).
+
+---
+
+## 5. Resuming After Context Clear
+
+Progress lives in persistent files, not in transient chat history:
+
+- In Fast-Track: `devflow/context/current-feature.md` maintains ticked checklist boxes `- [x]`.
+- In Deep-Track: `devflow/context/current-run/` maintains stage markdown files.
+- In Git: Commits, branches, and working tree maintain the code history.
+- When starting a fresh session after a context clear, run `devflow` or inspect `current-stage.md` to pick up immediately from the next pending step.
+
+---
+
+## 6. Single Active Run Guardrail (One Thing at a Time)
+
+- Only one active run is allowed at a time across both Fast-Track and Deep-Track.
+- The AI will actively block opening a new feature or fix until the current one is completed with `/complete` or `70-release` (or explicitly rolled back/cancelled).
+
+---
+
+## 7. Branching & Git Conventions
+
+- **Branch Naming**: `feature/{xxx-slug}` or `fix/{xxx-slug}`.
+- **Commit Messages**: Conventional imperative format (e.g. `feat(uninstall): add clean eject CLI command`, `fix(parser): handle undefined metadata field`).
+- **No AI Attribution in Commits**: Never include "Generated with AI" or agent metadata in Git commit logs.
+- **Explicit Approval for Push & Deploy**: Merge approval is strictly separate from consent to `git push` to remote repositories or deploy to production.
+
+---
+
+## 8. Autopilot Policy
+
+- `autopilot` is an explicit opt-in command (`/autopilot`). Never suggest it as the default next action.
+- When invoked, it runs one bounded spec/plan/implement/verify pass.
+- Autopilot **MUST stop** before `/complete`, merge, push, deploy, or any destructive action.

package/template/devflow/context/coding-standards.md

@@ -1,40 +1,131 @@
-# Coding Standards & Guidelines
+# Coding Standards & Engineering Guidelines
 
-General engineering standards for code, tests, and documentation in Nexus-DevFlow.
+> Engineering standards, architecture conventions, testing policies, and code quality guidelines for **Nexus-DevFlow**.
 
-## 1. Code Quality & Architecture
+---
 
-- Write clear, self-documenting code with single-responsibility functions.
-- Avoid unnecessary complexity (prefer simple solutions over indirect abstractions).
-- Maintain type safety and static validation across module boundaries.
-- Treat `project-overview.md` as the single source of truth for concrete data models and entity definitions.
+## 1. TypeScript & Runtime Standards
 
-## 2. Testing & Empirical Proof Standards
+- **Strict Mode Enabled**: Always adhere to strict TypeScript compilation (`"strict": true` in `tsconfig.json`).
+- **No `any` Types**: Prohibit the use of `any`. Use precise interface definitions, generics, or `unknown` with runtime type narrowing.
+- **Type Definitions**: Define clear interfaces and types for all function options, CLI arguments, parse results, and data payloads.
+- **Type Inference vs. Explicit Types**: Use type inference for straightforward local variables, and explicit return types for public functions, exports, and complex utilities.
+- **ESM-First Architecture**: Use native Node.js ESM (`"type": "module"`). Always use explicit `node:` protocol imports (e.g. `node:fs`, `node:path`, `node:os`, `node:child_process`).
 
-- **Unit Test Mandate**: Any logic modification or bug fix must be accompanied by new or updated unit tests.
-- **Empirical Proof Contract**: Never claim "passed", "verified", or "working" without citing exact command outputs, test run reports, route responses, logs, or screenshots.
-- **Manual Try Guide**: Every delivery run must provide a human-testable Try Guide ("Where to go", "What to click", "What to expect") for manual validation.
+---
 
-## 3. Findings Ledger & Quality Gates (`findings.md`)
+## 2. CLI Architecture & Engineering Principles
 
-- All audit, security, and verification issues must be tracked in `devflow/context/findings.md`.
+- **Separation of Concerns (Deep Modules)**:
+  - Keep CLI entry points (`bin/create-nexus-devflow.ts`) thin: handle argument parsing, option normalization, and terminal formatting.
+  - Encapsulate all core business logic, filesystem operations, and parsing inside modular libraries (`lib/current-work.ts`, `lib/findings.ts`, `lib/git.ts`, `lib/uninstall.ts`, `lib/update.ts`).
+- **Safety Flags & Idempotency**:
+  - Destructive or mutating operations (e.g. `uninstall`, `update`, `install`) must support safety flags:
+    - `--dry-run`: Preview actions and affected files without modifying the disk.
+    - `-y`, `--yes`, `-f`, `--force`: Non-interactive mode for CI/CD automation.
+    - `--json`: Machine-readable structured output for integrations.
+- **Cross-Platform Compatibility**:
+  - Never assume POSIX-only paths or Windows-only backslashes. Always use `path.join()`, `path.resolve()`, or normalize paths with forward slashes for URLs and identifiers.
+  - Handle Windows permission quirks (EPERM, EBUSY) with graceful retries or clear explanatory messages.
+- **Terminal UX & ANSI Formatting**:
+  - Provide clear, high-contrast, and aesthetic terminal outputs.
+  - Automatically respect `process.stdout.isTTY` and support `--no-color` / `NO_COLOR` environment variables.
+
+---
+
+## 3. File Organization & Directory Structure
+
+```text
+nexus-devflow/
+├── .agents/skills/             # Codex & Google Antigravity skill definitions
+├── .claude/skills/             # Claude Code mirrored skill adapters
+├── .nexus/                     # Metadata tracking & upstream baseline ledger
+├── devflow/                    # Framework workspace context, runs, and discoveries
+│   ├── context/                # Living source-of-truth context files
+│   ├── discoveries/            # Pre-delivery discovery records (00-discover.md)
+│   ├── runs/                   # Running delivery artifacts (current-feature.md / 00-70)
+│   ├── history/                # Master delivery archive (HISTORY.md)
+│   └── ideas.md                # Idea Inbox and backlog
+├── packages/
+│   └── create-nexus-devflow/   # Distribution npm package source
+│       ├── bin/                # CLI executable binaries
+│       ├── lib/                # Modular domain libraries
+│       └── test/               # Automated unit tests (*.test.ts)
+└── scripts/                    # Maintainer verification & automation scripts
+```
+
+---
+
+## 4. Naming Conventions
+
+- **Files & Directories**:
+  - Skills and command directories: `kebab-case` (e.g. `00-discover`, `report-html`, `sync-upstream`).
+  - Source modules and scripts: `kebab-case.ts` / `kebab-case.mjs` (e.g. `current-work.ts`, `check-devflow.ts`).
+  - Test files: `[module].test.ts` (e.g. `status.test.ts`, `uninstall.test.ts`).
+- **Identifiers**:
+  - Functions & methods: `camelCase` (e.g. `parseCurrentWork`, `applyUninstall`, `readProjectStatus`).
+  - Variables & properties: `camelCase`.
+  - Types & Interfaces: `PascalCase` without prefixes like `I` or `T` (e.g. `ProjectStatus`, `RunWorkSummary`).
+  - Constants & Enums: `SCREAMING_SNAKE_CASE` (e.g. `LEGACY_FEATURE_PATH`, `DEFAULT_ADAPTERS`).
+
+---
+
+## 5. Testing & Empirical Proof Standards
+
+Testing is a core quality gate in Nexus-DevFlow, not an afterthought:
+
+- **Unit Test Mandate**: Any new feature, modified logic, parser improvement, or bug fix **MUST ship with automated unit tests** in the same diff.
+- **Test Framework**: Use Node.js native test runner executed via `tsx --test test/*.test.ts` under `packages/create-nexus-devflow/`.
+- **Test Design (AAA Pattern)**:
+  - Structure each test case cleanly: **Arrange** (setup fixtures/mock directories), **Act** (execute function), **Assert** (verify invariants).
+  - Use isolated temporary directories (`fs.mkdtemp` in `os.tmpdir()`) and ensure cleanup in `finally` blocks.
+- **Empirical Proof Contract**:
+  - Never claim a task is "working", "tested", or "verified" without providing concrete empirical proof (exact command executed, terminal output, pass/fail counts, exit code).
+- **3-Lane Verification Matrix**:
+  - **Lane 1 (Type & Syntax Safety)**: `tsc --noEmit` (0 type errors).
+  - **Lane 2 (Automated Test Suites & Evals)**: `npm test` (Unit tests 100% pass) + `npm run test:routing` (Skill routing accuracy).
+  - **Lane 3 (Manual / Scenario Proof)**: Concrete walkthrough steps ("Where to go", "What to run", "What to expect").
+
+---
+
+## 6. Findings Ledger & Quality Gates (`findings.md`)
+
+- All quality defects, security findings, or regression issues identified during review must be logged in `devflow/context/findings.md`.
 - **Finding State Machine**:
-  - `open`: Confirmed defect not yet repaired.
-  - `fixed`: Repaired in code, pending verification.
-  - `closed`: Verified in `50-verify` as completely resolved without regressions.
-  - `accepted`: Waived with recorded user rationale.
-  - `invalid`: Proven non-issue with concrete evidence.
-- **P0/P1 Blockers**: P0 and P1 findings in `open` or `fixed` status block `70-release` unconditionally. `fixed` status must be promoted to `closed` via `50-verify` re-examination.
-
-## 4. Git Workflow & Release Safety
- 
-- Commit messages follow conventional/imperative format (e.g., `feat(RUN-007): ...`).
-- Feature branches follow `feature/{slug}-{running-id}` or `fix/{slug}-{running-id}`.
-- **2-Stage Release Approvals**: Explicit consent to merge into `main` is strictly separate from consent to `git push` to remote repositories or deploy to production.
-
-## 5. Fast-Track & Quick-Fix Guidelines (Lean Mode)
-
-- For trivial bug fixes, typo corrections, or single-file non-architectural changes, developers and agents may use the **Quick-Fix Fast-Track**:
-  - Consolidate Discovery, Define, and Spec into an inline fix brief (`devflow/runs/{fix-id}/fix-brief.md`).
-  - Jump directly to `40-execute` (with reproduction unit test) ➔ `50-verify` ➔ `70-release`.
-  - Avoid creating heavy redundant documentation for changes under 20 lines of code while preserving Empirical Proof and Unit Test requirements.
+  - `open`: Confirmed issue waiting to be fixed.
+  - `fixed`: Repaired in code, pending QA re-verification.
+  - `closed`: Verified by QA as completely resolved without regressions.
+  - `accepted`: Formally waived with recorded user justification.
+- **P0/P1 Blockers**: Any P0 or P1 finding in `open` or `fixed` status unconditionally blocks `/complete` and `70-release`.
+
+---
+
+## 7. Error Handling & Exit Codes
+
+- Use structured `try / catch` blocks around filesystem and process operations.
+- Create meaningful, actionable error messages for the user (explain what failed and how to resolve it).
+- Exit cleanly with standard POSIX process exit codes:
+  - `0`: Successful execution.
+  - `1`: Validation failure, missing arguments, or runtime error.
+
+---
+
+## 8. Comments & Documentation Discipline
+
+Write code that explains itself; comment only what the code cannot say:
+
+- Comment the **why**, not the **what**. Avoid comments that simply rephrase the line of code.
+- Avoid noisy banner blocks, section divider lines (`// ====================`), or obvious step narrations.
+- Comments earn their place when documenting:
+  - Non-obvious architectural decisions.
+  - Upstream compatibility quirks or workarounds.
+  - Edge-case handling rationale.
+- Keep JSDoc minimal and useful: provide a one-line summary and document non-obvious parameters.
+
+---
+
+## 9. Writing & Language Conventions
+
+- **Default Communication & Artifacts**: Thai (`th`) for all generated markdown stage artifacts (`current-feature.md`, `00-discover.md`, etc.), explanations, and user interactions.
+- **Code & Identifiers**: English for all source code, variable names, file paths, CLI flags, and commit messages.
+- **Typography**: Do not use em dashes (`—`) in AI-generated commit messages or technical summaries; use standard hyphens (`-`) or colons.

package/template/devflow/context/current-feature.md

@@ -0,0 +1,3 @@
+# Current Feature
+
+_Nothing in progress. Run /feature, /fix, or /rollback to start._