@jakkrichm/create-nexus-devflow 2.6.1 → 2.7.0

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

@@ -1,21 +1,21 @@
 ---
 name: report-html
-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}"
+description: "[devflow] Standalone HTML Report Generator - render an interactive standalone HTML dashboard from current-feature.md or history archives on demand."
+argument-hint: "[{running-id or workspace path}]"
 ---
 
 # Standalone: Report HTML
 
 $ARGUMENTS
 
-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`.
+Standalone companion command to generate an interactive, self-contained HTML report dashboard on demand from `current-feature.md`, task-specific context `devflow/context/{xxx-slug}/spec.md`, or archived history files in `devflow/history/`.
 
 > [!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.
+> HTML reports are **never automatically generated** during normal mainline stages (`/complete`). Use this command whenever you or stakeholders wish to view or share an interactive web report.
 
 ## Invocations & Aliases
 
-- `/report:html`: Generate HTML report for the active or most recent run
+- `/report:html`: Generate HTML report for the active run
 - `/report:html {running-id}`: Generate HTML report for the specified running ID
 - `npm run report:html -- {running-id}`: CLI npm script invocation
 - `$report:html`: Codex CLI invocation
@@ -25,21 +25,21 @@ Standalone companion command to generate an interactive, self-contained HTML rep
 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}/current-feature.md` (or `spec.md` / `blueprint.md`)
-   - Deep-Track Report Digest: `devflow/runs/{RUNNING_ID}/60-report.md`
+1. Locate target markdown document:
+   - Active Living Spec: `devflow/context/current-feature.md` or `devflow/context/{xxx-slug}/spec.md`
+   - Archived History: `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`
+2. Parse spec sections, checklist steps, QA evidence, and verification logs.
 
 ### 2. Render Interactive HTML Dashboard
-Execute the HTML generation engine:
+Execute the HTML generation engine or script:
 ```bash
 npm run report:html -- {RUNNING_ID}
 ```
-Or execute the renderer to transform Markdown into a styled, standalone HTML document:
-- Path: `devflow/runs/{RUNNING_ID}/report.html`
+Or transform Markdown into a styled, standalone HTML document:
+- Output: `devflow/reports/{RUNNING_ID}-report.html` (or adjacent `{xxx-slug}.html`)
 
 ### 3. Output
 Provide:
-- Generated HTML file path: `file:///devflow/runs/{RUNNING_ID}/report.html`
+- Generated HTML file path: `file:///devflow/reports/{RUNNING_ID}-report.html`
 - Summary of sections rendered (Spec, Plan, Progress, QA Evidence, Release Notes)
 - Instructions to open the file in any browser

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

@@ -81,14 +81,14 @@ For browser and UI features, unit tests alone are insufficient:
 
 ## 6. Test Generation & Persistent Execution Reports
 
-When generating or logging test runs during `40-execute` or `50-verify`:
+When generating or logging test runs during `/implement` or `/check`:
 - Save summary reports to `devflow/reports/{date}-test-report-{slug}.md`
 - Include: Target, Test Cases (Happy Path, Error, Edge Cases), Pass/Fail statistics, and gaps/risks.
 
 ---
 
-## Relationship To DevFlow 2.0
+## Relationship To DevFlow 2.6.x
 
 - **Classification**: Companion command & Engineering standard
-- **Mainline stages**: `30-plan` (TDD decisions), `40-execute` (TDD execution), `50-verify` (QA gate)
-- **Handoff**: `50-verify`, `Debug`, `autopilot`
+- **Mainline stages**: `feature` / `fix` (TDD decisions), `implement` (TDD execution), `check` (QA gate)
+- **Handoff**: `check`, `debug`, `autopilot`

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

@@ -58,5 +58,5 @@ Construct a structured evaluation table:
 
 ## Next Workflow Recommendation
 
-- **Primary**: `discovery {discovery_id}` (if resuming discovery) or `10-define` / `feature` (if ready to specify)
+- **Primary**: `discovery {discovery_id}` (if resuming discovery) or `feature` (if ready to specify)
 - **Inbox**: `idea` to record into `devflow/ideas.md`

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

@@ -0,0 +1,118 @@
+---
+name: continuous
+description: "[devflow] Autonomous multi-feature delivery loop in Nexus-DevFlow: completes planned features serially from devflow/build-plan.md without review pauses. Maintains safety boundaries, Single Living Spec (current-feature.md), branch isolation, TDD verification, quality gates, and local squash-merges into main. Use when running /continuous, $continuous, or executing Continuous Mode."
+argument-hint: "[{resume, max-features, or start-feature}]"
+---
+
+# continuous - Complete the Build Plan One Local Feature at a Time
+
+Where this sits in the workflow:
+
+```text
+/status  ──▶  [continuous]  ──▶  Final Review Packet
+(ready)       (Serial Loop:      (Local main only,
+               Spec ➔ TDD ➔       never pushed)
+               Gates ➔ Merge)
+```
+
+`/continuous` (หรือ `$continuous`) คือโหมดการทำงานแบบ Autonomous Multi-Feature Delivery Loop สำหรับจัดส่งฟีเจอร์ที่อยู่ใน `devflow/build-plan.md` ต่อเนื่องทีละฟีเจอร์ในเครื่อง Local โดยไม่ต้องหยุดรอ Manual Review Prompts ในแต่ละขั้นตอนย่อย แต่ยังคงรักษาความเข้มงวดของ **The 3-Pillars Model & Single Living Spec (`current-feature.md`)**, การทำ TDD, การตรวจ Quality Gates, การบันทึก Findings Ledger, และการ Squash-merge ลง Local Main Commit ทีละฟีเจอร์อย่างปลอดภัย 100%
+
+### ขอบเขตสิทธิ์ที่ได้รับอนุญาตเฉพาะในเครื่อง Local:
+- สร้างและสลับ Feature Branch ในเครื่อง Local
+- บันทึก Checkpoint Commits ย่อยบน Branch
+- บันทึก Feature Commit สุดท้าย
+- Squash-merge ฟีเจอร์ที่เสร็จสมบูรณ์ลง Default Branch ของ Local
+- ลบ Feature Branch เฉพาะใน Local หลังรวมโค้ดสำเร็จ
+- วนลูปเริ่มทำฟีเจอร์ที่ยังไม่ได้เช็ค (`- [ ]`) รายการถัดไปใน `build-plan.md`
+
+### ข้อจำกัดความปลอดภัยเด็ดขาด (Strict Safety Boundaries):
+- **ห้าม** Push ขึ้น Remote Repository
+- **ห้าม** Deploy หรือเผยแพร่ (Publish) สู่ภายนอก
+- **ห้าม** ลบข้อมูลจริง, ทำลาย Database, หรือรัน Destructive Migration
+- **ห้าม** กด Accept Finding หรือเพิกเฉยต่อ Failing Quality Gate แทนมนุษย์
+
+---
+
+## Input & Target Selection
+
+- **ไม่ระบุ Argument (`/continuous`)**:
+  1. หากมีฟีเจอร์ค้างอยู่ใน `devflow/context/current-feature.md` ให้ทำต่อจากขั้นตอนย่อยแรกที่ยังไม่ได้เช็ค (`- [ ]`)
+  2. หากไม่มี ให้เลือกฟีเจอร์แรกที่ยังไม่ได้เช็ค (`- [ ]`) ใน `devflow/build-plan.md`
+  3. วนลูปทำต่อเนื่องตามลำดับใน `build-plan.md` จนกว่าจะหมด หรือครบตามจำนวน `continuous.maxFeatures` ใน `devflow/config.json`
+- **ระบุ `resume` (`/continuous resume`)**: ทำงานต่อจากฟีเจอร์และขั้นตอนย่อยที่ค้างอยู่ทันที
+- **ระบุชื่อหรือหมายเลขฟีเจอร์ (`/continuous 13`)**: เริ่มต้นจากฟีเจอร์ที่ระบุ แล้ววนลูปต่อไปยังฟีเจอร์ถัดไป
+
+---
+
+## Step 1: Preflight Safety Check (ตรวจสอบความพร้อมก่อนเริ่ม)
+
+อ่านบริบทตั้งต้น:
+- `AGENTS.md`
+- `devflow/config.json` (หากไม่มี ให้ใช้ค่า Defaults อย่างปลอดภัย; หาก Invalid ให้หยุดและชี้ไปที่ `/doctor`)
+- `devflow/project-plan.md` และ `devflow/build-plan.md`
+- `devflow/context/project-overview.md`
+- `devflow/context/current-feature.md` และ `devflow/context/current-stage.md`
+- `devflow/context/findings.md`
+- `devflow/context/coding-standards.md` และ `devflow/context/ai-interaction.md`
+- สถานะ Git (`git status`, `git branch`, recent log)
+
+### กฎการเริ่มงาน (Start Conditions):
+1. สถานะ Git Working Tree สะอาด (Clean) บน Default Branch หรือมีเฉพาะ Diff ของฟีเจอร์ปัจจุบัน
+2. `devflow/build-plan.md` มีฟีเจอร์ที่ยังไม่ได้ทำเหลืออยู่
+3. ไม่มี Finding ระดับ P0 หรือ P1 ค้างในสถานะ `open` หรือ `fixed`
+4. บันทึก Commit SHA ตั้งต้นของ Default Branch ไว้สำหรับสรุปผลในรายงานสุดท้าย
+
+---
+
+## Step 2: Serial Feature Lifecycle (วงจรการส่งมอบทีละฟีเจอร์)
+
+ดำเนินงานวนลูปทีละ 1 ฟีเจอร์ตามลำดับ:
+
+### 2.1 Select & Spec (เลือกและร่างสเปก)
+- หาก Resuming: ใช้ Spec เดิมใน `current-feature.md`
+- หากเป็นฟีเจอร์ใหม่: ถอดความต้องการจาก `build-plan.md` และสร้าง Single Living Spec ลงใน `devflow/context/current-feature.md` พร้อมวิเคราะห์ Red-team ก่อนเริ่มโค้ด
+
+### 2.2 Create / Resume Feature Branch
+- สร้าง Branch ตาม Prefix ใน Config (เช่น `feature/060-slug`) จาก Default Branch
+
+### 2.3 Implement Small Steps with Strict TDD
+- ดำเนินการสร้างฟังก์ชันทีละ Task ตาม Checklist ใน Spec:
+  1. `[TDD-Red]`: เขียน Unit Test ก่อน
+  2. `[TDD-Green]`: เขียนโค้ดขั้นต่ำให้ Test ผ่าน
+  3. `[TDD-Refactor]`: ปรับแต่งโค้ดให้สะอาดและรัน Verification ผ่าน
+  4. ทำเครื่องหมาย `- [x]` ใน Spec และบันทึก Checkpoint Commit บน Branch (หาก `workflow.checkpointCommits: "enabled"`)
+
+### 2.4 Apply Continuous Quality Gates
+ตรวจสอบตามการตั้งค่า `qualityGates.continuous` ใน `devflow/config.json`:
+- **Audit**: `manual` (ข้ามอัตโนมัติ), `when-sensitive` (รันเมื่อแตะ Auth/Security/Database/Secrets), `always` (รันทุกฟีเจอร์)
+- **Check**: `manual` (ข้ามอัตโนมัติ), `when-behavioral` (รันเมื่อมี Runtime Behavior เช่น UI/CLI/API), `always` (รันทุกฟีเจอร์)
+- **Try Guide**: `manual` (ข้ามอัตโนมัติ), `when-user-facing` (สร้าง Try Guide เมื่อเป็น UI/CLI), `always` (สร้างทุกฟีเจอร์)
+
+### 2.5 Repair Findings
+- ซ่อมแซม Finding ระดับ P0/P1 ที่เกิดขึ้นจากฟีเจอร์นี้โดยอัตโนมัติ (ไม่เกิน `continuous.maxRepairAttempts` ครั้ง)
+- หากไม่สามารถซ่อมแซมได้ หรือมี P0/P1 ค้างอยู่ ให้หยุดการทำงานทันที
+
+### 2.6 Complete Locally Like a Human
+- รัน Verification ขั้นสุดท้าย
+- ย้ายและ Archive เอกสารไปที่ `devflow/history/features/{xxx-slug}.md`
+- อัปเดตเช็คบ็อกซ์ใน `devflow/build-plan.md`
+- รีเซ็ต `devflow/context/current-feature.md` กลับสู่ Stub
+- Squash-merge Feature Branch เข้าสู่ Local Main และลบ Feature Branch ใน Local
+- นับจำนวนฟีเจอร์ที่สำเร็จเพิ่มขึ้น 1
+
+---
+
+## Step 3: Optional Final Integration Audit
+
+เมื่อครบกำหนดจำนวนฟีเจอร์หรือหมด `build-plan.md` หาก `continuous.finalIntegrationAudit: true` ให้รันการตรวจสอบความเข้ากันได้แบบบูรณาการ (Cross-Feature Contracts & Seams) จากจุดเริ่มต้นถึง HEAD ปัจจุบัน
+
+---
+
+## Step 4: Stop & Report (สรุปรายงานผลลัพธ์)
+
+เมื่อการทำงานสิ้นสุด (ไม่ว่าจะสำเร็จครบถ้วน หรือหยุดเนื่องจากติดเงื่อนไขความปลอดภัย) ให้รายงานสรุปเป็นภาษาไทย:
+- Commit เริ่มต้น และ Commit สุดท้ายของ Default Branch
+- รายชื่อฟีเจอร์ที่จัดส่งสำเร็จในรอบนี้ พร้อม Commit Hash
+- ผลการรัน Quality Gates และการซ่อมแซม Findings (ถ้ามี)
+- ความคืบหน้าภาพรวมของ `build-plan.md` และฟีเจอร์ถัดไป
+- ย้ำเตือนชัดเจนว่า **ไม่มีการ Push ใดๆ ขึ้น Remote Repository**

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

@@ -48,6 +48,14 @@ Gather these, then summarize. Do not dump file contents.
    - If `.gitignore` marks DevFlow workflow files as local-only, still require
      the files to exist on disk. Ignored but present is healthy; ignored and
      missing means the local workflow needs to be restored.
+   - Read `devflow/config.json` when present. Missing is healthy and means
+     built-in defaults. When present, require a regular non-symbolic-link JSON
+     file with `schemaVersion: 1`. Reject unknown keys and unsupported values.
+     Report the effective workflow, git, verification, regular quality-gate,
+     Continuous quality-gate, and Continuous Mode settings. Confirm each audit,
+     check, and try-guide gate uses its supported values and defaults to `manual`.
+     An invalid config is a setup blocker for mutating workflow skills because
+     they must not guess which policy to follow.
 2. **Tool adapters**
    - Read `.nexus/nexus-devflow.json` when present and report its exact
      logical adapters: Codex, Claude Code, GitHub Copilot, Antigravity, and OpenCode.

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

@@ -89,5 +89,5 @@ Allocate the next sequential ID (`ADR-001`, `ADR-002`, ...) and create `devflow/
 When all design branches are resolved:
 1. Summarize settled domain terms and created ADRs.
 2. Provide explicit next command recommendations:
-   - **Fast-Track (Standard Features/Fixes)**: Run `/feature {topic}` or `/fix {topic}` to immediately start the living spec.
-   - **Deep-Track (Large Architectural Epics)**: Run `10-define` or `/discovery` with the discovery context.
+   - **Living Spec (Standard Delivery)**: Run `/feature {topic}` or `/fix {topic}` to immediately start the living spec.
+   - **Pre-Flight Discovery**: Run `/discovery {topic}` to conduct comprehensive discovery exploration before specification.

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

@@ -44,7 +44,7 @@ Insert the new idea block directly under `## 📌 Pending Ideas` in `devflow/ide
 - **Quick Seed (กันลืม)**:
   1. {ประเด็นสำคัญที่ 1}
   2. {ประเด็นสำคัญที่ 2}
-- **สถานะ**: `Pending` (หยิบไปทำได้ด้วย `/spec IDEA-001` หรือ `/00-explore IDEA-001`)
+- **สถานะ**: `Pending` (หยิบไปทำได้ด้วย `/feature IDEA-001` หรือ `/discovery IDEA-001`)
 ```
 
 *(หากมีข้อความ `*(ยังไม่มีไอเดียค้างอยู่...)*` ให้ลบออกเมื่อมีไอเดียแรก)*
@@ -54,4 +54,4 @@ Report to the user:
 - Allocated Idea ID: `[IDEA-xxx]`
 - Summary of Feasibility & Value analysis
 - Seed points saved
-- Instructions for promotion: "เมื่อพร้อมลงมือทำ สามารถพิมพ์ `/spec IDEA-xxx` หรือ `/00-explore IDEA-xxx` ได้ทันที"
+- Instructions for promotion: "เมื่อพร้อมลงมือทำ สามารถพิมพ์ `/feature IDEA-xxx` หรือ `/discovery IDEA-xxx` ได้ทันที"

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

@@ -1,21 +1,21 @@
 ---
 name: report-html
-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}"
+description: "[devflow] Standalone HTML Report Generator - render an interactive standalone HTML dashboard from current-feature.md or history archives on demand."
+argument-hint: "[{running-id or workspace path}]"
 ---
 
 # Standalone: Report HTML
 
 $ARGUMENTS
 
-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`.
+Standalone companion command to generate an interactive, self-contained HTML report dashboard on demand from `current-feature.md`, task-specific context `devflow/context/{xxx-slug}/spec.md`, or archived history files in `devflow/history/`.
 
 > [!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.
+> HTML reports are **never automatically generated** during normal mainline stages (`/complete`). Use this command whenever you or stakeholders wish to view or share an interactive web report.
 
 ## Invocations & Aliases
 
-- `/report:html`: Generate HTML report for the active or most recent run
+- `/report:html`: Generate HTML report for the active run
 - `/report:html {running-id}`: Generate HTML report for the specified running ID
 - `npm run report:html -- {running-id}`: CLI npm script invocation
 - `$report:html`: Codex CLI invocation
@@ -25,21 +25,21 @@ Standalone companion command to generate an interactive, self-contained HTML rep
 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}/current-feature.md` (or `spec.md` / `blueprint.md`)
-   - Deep-Track Report Digest: `devflow/runs/{RUNNING_ID}/60-report.md`
+1. Locate target markdown document:
+   - Active Living Spec: `devflow/context/current-feature.md` or `devflow/context/{xxx-slug}/spec.md`
+   - Archived History: `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`
+2. Parse spec sections, checklist steps, QA evidence, and verification logs.
 
 ### 2. Render Interactive HTML Dashboard
-Execute the HTML generation engine:
+Execute the HTML generation engine or script:
 ```bash
 npm run report:html -- {RUNNING_ID}
 ```
-Or execute the renderer to transform Markdown into a styled, standalone HTML document:
-- Path: `devflow/runs/{RUNNING_ID}/report.html`
+Or transform Markdown into a styled, standalone HTML document:
+- Output: `devflow/reports/{RUNNING_ID}-report.html` (or adjacent `{xxx-slug}.html`)
 
 ### 3. Output
 Provide:
-- Generated HTML file path: `file:///devflow/runs/{RUNNING_ID}/report.html`
+- Generated HTML file path: `file:///devflow/reports/{RUNNING_ID}-report.html`
 - Summary of sections rendered (Spec, Plan, Progress, QA Evidence, Release Notes)
 - Instructions to open the file in any browser

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

@@ -81,14 +81,14 @@ For browser and UI features, unit tests alone are insufficient:
 
 ## 6. Test Generation & Persistent Execution Reports
 
-When generating or logging test runs during `40-execute` or `50-verify`:
+When generating or logging test runs during `/implement` or `/check`:
 - Save summary reports to `devflow/reports/{date}-test-report-{slug}.md`
 - Include: Target, Test Cases (Happy Path, Error, Edge Cases), Pass/Fail statistics, and gaps/risks.
 
 ---
 
-## Relationship To DevFlow 2.0
+## Relationship To DevFlow 2.6.x
 
 - **Classification**: Companion command & Engineering standard
-- **Mainline stages**: `30-plan` (TDD decisions), `40-execute` (TDD execution), `50-verify` (QA gate)
-- **Handoff**: `50-verify`, `Debug`, `autopilot`
+- **Mainline stages**: `feature` / `fix` (TDD decisions), `implement` (TDD execution), `check` (QA gate)
+- **Handoff**: `check`, `debug`, `autopilot`

package/template/AGENTS.md

@@ -1,4 +1,4 @@
-# Nexus-DevFlow 2.6.1 (The 3-Pillars & Single Living Spec Model)
+# Nexus-DevFlow 2.7.0 (The 3-Pillars & Single Living Spec 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.
 
@@ -13,6 +13,7 @@ To start a new project, scaffold the application first in an empty folder, then
 
 ## Read these for full context
 
+- `devflow/config.json` - deterministic project workflow settings
 - `devflow/context/project-overview.md` - the project's source of truth
 - `devflow/context/coding-standards.md` - engineering conventions & rules to follow
 - `devflow/context/ai-interaction.md` - how to interact with the user on this project
@@ -20,6 +21,12 @@ To start a new project, scaffold the application first in an empty folder, then
 - `devflow/context/findings.md` - quality, security, and verification ledger
 - `devflow/context/glossary.md` - domain terms & architecture definitions
 
+## Project configuration
+
+`devflow/config.json` is the user-owned, machine-readable workflow policy for this project. Workflow skills read the relevant settings before acting. A missing file means built-in defaults. An invalid file falls back to defaults for read-only status reporting, but mutating workflow commands stop and point to `/doctor` instead of guessing.
+
+`qualityGates.regular` controls automatic audit, check, and try-guide behavior for the normal workflow and Autopilot. `qualityGates.continuous` controls the same per-feature gates for Continuous Mode. Every gate defaults to `manual`.
+
 ## Tool-Specific Adapters & Execution Rules
 
 The workflow and skills are exposed through tool-specific adapters:
@@ -32,10 +39,10 @@ Unused adapter families can be removed. Codex, Antigravity, GitHub Copilot, and
 
 ### Universal Invocation & Agent Directives:
 
-1. **Canonical Command Names & AI Provider Invocation**: Each workflow stage and companion tool has exactly **one Canonical Name** (e.g. `feature`, `fix`, `implement`, `check`, `complete`, `discovery`, `idea`, `grill`, `brainstorm`, `devflow`, `doctor`, `overview`, `debug`, `onboard`, `adopt`, `try`, `rollback`, `ci`, `test`, `tests`, `autopilot`, `prototype`, `report-html`, `brief`, `audit`, `release`). The way you invoke commands depends on your AI Provider / Tool:
-   - **Canonical Name (Plain text)**: Directly invoke or prompt the command by its standard name (e.g., `feature`, `implement`, `devflow`, `discovery`).
-   - **Slash Prefix (`/`)**: For tools supporting slash commands (Claude Code, Google Antigravity, Gemini CLI), e.g., `/feature`, `/fix`, `/implement`, `/devflow`, `/discovery`.
-   - **Dollar Prefix (`$`)**: For OpenAI Codex CLI or skill-invocation tools, e.g., `$feature`, `$fix`, `$devflow`, `$discovery`.
+1. **Canonical Command Names & AI Provider Invocation**: Each workflow stage and companion tool has exactly **one Canonical Name** (e.g. `feature`, `fix`, `implement`, `check`, `complete`, `continuous`, `discovery`, `idea`, `grill`, `brainstorm`, `devflow`, `doctor`, `overview`, `debug`, `onboard`, `adopt`, `try`, `rollback`, `ci`, `test`, `tests`, `autopilot`, `prototype`, `report-html`, `brief`, `audit`, `release`, `convert-any-to-md`). The way you invoke commands depends on your AI Provider / Tool:
+   - **Canonical Name (Plain text)**: Directly invoke or prompt the command by its standard name (e.g., `feature`, `implement`, `continuous`, `devflow`, `discovery`).
+   - **Slash Prefix (`/`)**: For tools supporting slash commands (Claude Code, Google Antigravity, Gemini CLI), e.g., `/feature`, `/fix`, `/implement`, `/continuous`, `/devflow`, `/discovery`.
+   - **Dollar Prefix (`$`)**: For OpenAI Codex CLI or skill-invocation tools, e.g., `$feature`, `$fix`, `$continuous`, `$devflow`, `$discovery`.
 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 context in `devflow/context/`.

package/template/devflow/build-plan.md

@@ -33,7 +33,7 @@
 
 - [x] **4. Just-In-Time (JIT) Dynamic Context Slicing Engine** `[Size: M]`
   - *Dependencies*: Feature 3
-  - *Scope*: สร้างตัวตัดตอนบริบท (Context Slicer) สำหรับสคิล `/implement`, `/check`, `/00-explore` เพื่อส่งเฉพาะข้อมูลที่จำเป็นและควบคุม Token Budget ลดการใช้ Token 60–70%
+  - *Scope*: สร้างตัวตัดตอนบริบท (Context Slicer) สำหรับสคิล `/implement`, `/check`, `/discovery` เพื่อส่งเฉพาะข้อมูลที่จำเป็นและควบคุม Token Budget ลดการใช้ Token 60–70%
 
 ---
 
@@ -92,8 +92,19 @@
   - *Dependencies*: Feature 10, Feature 3
   - *Scope*: แยกจัดเก็บ Task-Specific Context เป็นโฟลเดอร์ย่อยใน `devflow/context/{xxx-slug}/`, พัฒนา Context Resolver สำหรับสลับและเรียกใช้งาน `/implement <id>`, `/check <id>`, `/complete <id>` แบบระบุ Running ID หรือ Fuzzy Match, และอัปเกรด CLI/Dashboard/Skills ให้รองรับ Spec Queue หลายรันพร้อมกัน
 
+---
+
+## 🧹 Phase 12: Purge Legacy Deep-Track & Numbered Stage Artifacts
 
+- [x] **12. Purge Legacy Deep-Track & Numbered Stage Artifacts (`DISC-20260826-002`)** `[Size: M]`
+  - *Dependencies*: Feature 10, Feature 11
+  - *Scope*: ล้างโค้ดตกค้างของ Deep-Track (สเตจ 00-70 เช่น `40-execute`, `50-verify`, `60-report`, `70-deliver`, `10-define`, `20-spec`, `30-plan`) ออกจาก package engine (`status.ts`, `current-work.ts`, `history.ts`), agent skills (`.agents/`, `.claude/`), automation scripts & tests ใน `scripts/`, และเอกสาร/mockup ให้เป็นปัจจุบันสมบูรณ์
 
+---
 
+## 🔄 Phase 13: Upstream AI Blueprint v0.14.0 Synchronization & Deterministic Config Engine
 
+- [x] **13. Sync Upstream v0.14.0 (Deterministic Config & Continuous Mode)** `[Size: M]`
+  - *Dependencies*: Feature 12, DISC-20260826-003
+  - *Scope*: นำระบบ Deterministic Project Configuration (`devflow/config.json`) และสคิล Autonomous Multi-Feature Loop (`/continuous`) เข้าสู่ Nexus-DevFlow พร้อมอัปเกรด `project-config.ts`, `doctor`, `status`, `dashboard` และอัปเดต upstream baseline tracking สู่ v0.14.0
 

package/template/devflow/config.json

@@ -0,0 +1,33 @@
+{
+  "schemaVersion": 1,
+  "workflow": {
+    "stepReview": "every",
+    "checkpointCommits": "enabled"
+  },
+  "git": {
+    "featureBranchPrefix": "feature/",
+    "fixBranchPrefix": "fix/",
+    "rollbackBranchPrefix": "rollback/"
+  },
+  "verification": {
+    "logicTests": "when-configured",
+    "uiEvidence": "when-available"
+  },
+  "qualityGates": {
+    "regular": {
+      "audit": "manual",
+      "check": "manual",
+      "tryGuide": "manual"
+    },
+    "continuous": {
+      "audit": "manual",
+      "check": "manual",
+      "tryGuide": "manual"
+    }
+  },
+  "continuous": {
+    "maxFeatures": null,
+    "maxRepairAttempts": 2,
+    "finalIntegrationAudit": false
+  }
+}

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

@@ -139,7 +139,7 @@ Progress lives in persistent files, not in transient chat history:
 
 ## 9. Socratic Alignment & Grilling Discipline (`/grill`)
 
-- **Align Before You Build**: When plans, domain language, or architectural boundaries are fuzzy, invoke `/grill` (or use the Grilling Lens in `00-explore`) to conduct a structured interview before creating specifications.
+- **Align Before You Build**: When plans, domain language, or architectural boundaries are fuzzy, invoke `/grill` (or use the Grilling Lens in `/discovery`) to conduct a structured interview before creating specifications.
 - **Codebase-Grounded Inquiry**: Inspect existing context and code before asking questions. Never ask questions the codebase already answers.
 - **Turn Discipline**: Ask only 1–2 high-leverage questions per turn with clear recommended defaults. Never dump a wall of questions.
 - **Lazy Inline Persistence**:

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

@@ -88,7 +88,7 @@ nexus-devflow/
 ├── devflow/                    # Framework workspace context, history, and discoveries
 │   ├── context/                # Living source-of-truth context files
 │   ├── decisions/              # Architecture Decision Records (ADRs)
-│   ├── discoveries/            # Pre-delivery discovery records (00-explore.md)
+│   ├── discoveries/            # Pre-delivery discovery records (discovery.md)
 │   ├── history/                # Master delivery archive (features/, fixes/, rollbacks/, HISTORY.md)
 │   └── ideas.md                # Idea Inbox and backlog
 ├── packages/
@@ -104,7 +104,7 @@ nexus-devflow/
 ## 6. Naming Conventions
 
 - **Files & Directories**:
-  - Skills and command directories: `kebab-case` (e.g. `00-explore`, `report-html`, `sync-upstream`).
+  - Skills and command directories: `kebab-case` (e.g. `discovery`, `report-html`, `convert-any-to-md`).
   - 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**:

package/template/devflow/decisions/README.md

@@ -1,6 +1,6 @@
 # 🏛️ Architecture Decision Records (ADRs)
 
-This directory stores durable Architecture Decision Records (ADRs) produced during `/grill`, `00-explore`, or high-stakes architectural design sessions.
+This directory stores durable Architecture Decision Records (ADRs) produced during `/grill`, `/discovery`, or high-stakes architectural design sessions.
 
 ---
 

package/template/devflow/history/features/README.md

@@ -1,5 +1,5 @@
 # Completed Features Archive
 
-Finished feature specs, enhancements, architecture migrations, and tooling runs are archived here as `xxx-name.md` (for Fast-Track single living specs) or `xxx-name/` (for Deep-Track stage runs).
+Finished feature specs, enhancements, architecture migrations, and tooling runs are archived here as `{xxx-slug}.md`.
 
 Together they form the project's permanent feature build history, recording what was built, why, and how it was verified.

package/template/devflow/history/fixes/README.md

@@ -1,5 +1,5 @@
 # Completed Fixes Archive
 
-Finished bug fixes, hotfixes, regressions, security patches, and performance optimizations are archived here as `xxx-name.md` (for Fast-Track single living specs) or `xxx-name/` (for Deep-Track stage runs).
+Finished bug fixes, hotfixes, regressions, security patches, and performance optimizations are archived here as `{xxx-slug}.md`.
 
 Together they form the project's permanent bug resolution history, recording root causes, TDD test decisions, and empirical proof.

package/template/devflow/history/rollbacks/README.md

@@ -1,5 +1,5 @@
 # Completed Rollbacks Archive
 
-Safely reversed features and rollback execution records are archived here as `YYYY-MM-DD-xxx-name.md` (or `YYYY-MM-DD-xxx-name/`).
+Safely reversed features and rollback execution records are archived here as `YYYY-MM-DD-{xxx-slug}.md`.
 
 Together they form the project's safe feature reversal ledger, documenting target commits, dependency review, and post-reversal verification.

package/template/devflow/reference/mockup.html

@@ -221,22 +221,21 @@ footer a{color:var(--cyan);text-decoration:none}
         <span class="badge violet">Track: Idle</span>
       </div>
     </div>
-    <dl class="tb-table">
-      <dt>Package</dt><dd>@jakkrichm/create-nexus-devflow</dd>
-      <dt>Adapters</dt><dd>4 detected</dd>
-      <dt>Branch</dt><dd>main</dd>
-      <dt>Revision</dt><dd>2026-08-22</dd>
-    </dl>
+    <div class="meta">
+      <div class="meta-item"><span class="meta-label">Package</span><span class="meta-val">@jakkrichm/create-nexus-devflow</span></div>
+      <div class="meta-item"><span class="meta-label">Adapters</span><span class="meta-val">antigravity, claude, codex, copilot, opencode</span></div>
+      <div class="meta-item"><span class="meta-label">Branch</span><span class="meta-val">main</span></div>
+      <div class="meta-item"><span class="meta-label">Snapshot</span><span class="meta-val">2026-08-26 10:45</span></div>
+    </div>
   </header>
   <div class="live-wrap"><span class="live-dot"></span><span class="muted" style="font:11px var(--font-mono)">Status snapshot · health OK · npx @jakkrichm/create-nexus-devflow status</span></div>
 
-  <!-- Dual-Track Delivery Model -->
+  <!-- Unified Living Spec Model -->
   <section class="pipeline">
     <div class="pipeline-head">
-      <span class="pipeline-title">Dual-Track Delivery Model</span>
+      <span class="pipeline-title">Unified Living Spec Model (Nexus-DevFlow 2.6.x)</span>
       <div class="track-tabs" id="track-tabs">
-        <button class="tab on" data-t="fast">🏎️ Fast-Track · 4 steps</button>
-        <button class="tab" data-t="deep">🏗️ Deep-Track · 8 stages</button>
+        <button class="tab on" data-t="fast">⚡ Living Spec · 4 steps</button>
       </div>
     </div>
 
@@ -245,23 +244,9 @@ footer a{color:var(--cyan);text-decoration:none}
         <div class="step"><span class="step-conn"></span><span class="step-dot">1</span><div class="step-name">feature / fix</div><div class="step-cmd">/feature · /fix</div></div>
         <div class="step"><span class="step-conn"></span><span class="step-dot">2</span><div class="step-name">implement</div><div class="step-cmd">/implement</div></div>
         <div class="step"><span class="step-conn"></span><span class="step-dot">3</span><div class="step-name">check</div><div class="step-cmd">/check</div></div>
-        <div class="step"><span class="step-dot">4</span><div class="step-name">complete</div><div class="step-cmd">/complete</div></div>
-      </div>
-      <div class="track-note"><b>Idle:</b> no active Fast-Track run. Use <code>/feature</code> or <code>/fix</code> to create the Single Living Spec in <code>devflow/context/current-feature.md</code>. Recommended for about 85% of daily engineering work.</div>
-    </div>
-
-    <div class="track-view" id="view-deep">
-      <div class="stepper">
-        <div class="step"><span class="step-conn"></span><span class="step-dot">00</span><div class="step-name">00-explore</div></div>
-        <div class="step"><span class="step-conn"></span><span class="step-dot">10</span><div class="step-name">10-define</div></div>
-        <div class="step"><span class="step-conn"></span><span class="step-dot">20</span><div class="step-name">20-spec</div></div>
-        <div class="step"><span class="step-conn"></span><span class="step-dot">30</span><div class="step-name">30-plan</div></div>
-        <div class="step"><span class="step-conn"></span><span class="step-dot">40</span><div class="step-name">40-execute</div></div>
-        <div class="step"><span class="step-conn"></span><span class="step-dot">50</span><div class="step-name">50-verify</div></div>
-        <div class="step"><span class="step-conn"></span><span class="step-dot">60</span><div class="step-name">60-report</div></div>
-        <div class="step"><span class="step-dot">70</span><div class="step-name">70-deliver</div></div>
+        <div class="step"><span class="step-conn"></span><span class="step-dot">4</span><div class="step-name">complete</div><div class="step-cmd">/complete</div></div>
       </div>
-      <div class="track-note"><b>Reference model:</b> no active Deep-Track run. Recommended for architectural epics, database migrations, security audits, and multi-agent coordination. Progress lives in <code>devflow/context/current-run/</code> and is archived on <code>/70-deliver</code>.</div>
+      <div class="track-note"><b>Single Living Spec:</b> <code>/feature</code>, <code>/implement</code>, <code>/check</code>, <code>/complete</code> with TDD Discipline, Multi-Lane QA, and Durably Categorized History.</div>
     </div>
   </section>
 
@@ -274,7 +259,7 @@ footer a{color:var(--cyan);text-decoration:none}
       </button>
     </div>
     <div class="command" id="next-command">/feature</div>
-    <div class="muted">Workspace is idle and ready for new work. Start a Fast-Track feature, or use <code>/00-explore</code> when the scope needs deeper discovery first.</div>
+    <div class="muted">Workspace is idle and ready for new work. Start a living feature, or use <code>/discovery</code> when the scope needs deeper exploration first.</div>
   </section>
 
   <section class="stats">
@@ -291,7 +276,7 @@ footer a{color:var(--cyan);text-decoration:none}
       <div class="facts">
         <div class="fact"><span>Installed / latest</span><span>v2.0.25 / v2.0.25</span></div>
         <div class="fact"><span>Adapters</span><span>antigravity, codex, claude, copilot</span></div>
-        <div class="fact"><span>Architecture</span><span>3-Pillars + Dual-Track</span></div>
+        <div class="fact"><span>Architecture</span><span>3-Pillars + Living Spec</span></div>
       </div>
     </article>
 
@@ -350,7 +335,7 @@ footer a{color:var(--cyan);text-decoration:none}
       <div class="card-head"><span class="label">Discoveries</span><span class="value">0</span></div>
       <div class="disc-item">
         <div class="disc-id">NO ACTIVE DISCOVERY</div>
-        <div class="disc-title">Use /00-explore to investigate a request before delivery commitment.</div>
+        <div class="disc-title">Use /discovery to investigate a request before delivery commitment.</div>
         <div class="disc-status" style="color:var(--mint)">workspace ready</div>
       </div>
     </article>
@@ -372,7 +357,7 @@ footer a{color:var(--cyan);text-decoration:none}
       <button class="cmdp" data-cmd="rollback" data-tip="Plan a safe reversal with dependency and regression risk analysis.">rollback</button>
       <button class="cmdp" data-cmd="ci" data-tip="Set up the GitHub Actions verification workflow for the project.">ci</button>
       <button class="cmdp" data-cmd="test" data-tip="Inspect test suites and verify the test runner configuration.">test</button>
-      <button class="cmdp" data-cmd="autopilot" data-tip="Run a bounded Fast-Track or Deep-Track execution loop with quality gates.">autopilot</button>
+      <button class="cmdp" data-cmd="autopilot" data-tip="Run a bounded spec/build/check execution loop with quality gates.">autopilot</button>
       <button class="cmdp" data-cmd="prototype" data-tip="Create a throwaway static HTML/CSS mockup to settle UI direction before build.">prototype</button>
       <button class="cmdp" data-cmd="report-html" data-tip="Generate the optional standalone interactive HTML delivery report.">report-html</button>
     </div>
@@ -412,7 +397,7 @@ footer a{color:var(--cyan);text-decoration:none}
       <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 039</span><span class="hist-title">Dynamic Project Overview Compiler (/overview) พร้อม Living Context Sync</span></div>
       <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 038</span><span class="hist-title">Sub-Feature Automatic Splitting Engine และ Sub-Feature ID Contract</span></div>
       <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 037</span><span class="hist-title">Feature Briefing &amp; Deep Scope Assessment Skill (/brief)</span></div>
-      <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 036</span><span class="hist-title">Cloud Deployment Readiness Skill (/release) และ 70-deliver</span></div>
+      <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 036</span><span class="hist-title">Cloud Deployment Readiness Skill (/release)</span></div>
       <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 035</span><span class="hist-title">Guided Project Discovery Interview Skill (/discovery)</span></div>
       <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 034</span><span class="hist-title">Dedicated Code &amp; Security Audit Skill (/audit)</span></div>
       <div class="hist-item"><span class="hist-bar feature"></span><span class="hist-type">feature 033</span><span class="hist-title">User-Owned Planning Documents (project-plan.md &amp; build-plan.md)</span></div>