@jakkrichm/create-nexus-devflow 2.7.0 → 2.9.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -2
- package/dist/bin/create-nexus-devflow.d.ts +2 -2
- package/dist/bin/create-nexus-devflow.js +130 -0
- package/dist/bin/create-nexus-devflow.js.map +1 -1
- package/dist/lib/branch-context.d.ts +1 -0
- package/dist/lib/branch-context.js +14 -9
- package/dist/lib/branch-context.js.map +1 -1
- package/dist/lib/current-work.js +10 -22
- package/dist/lib/current-work.js.map +1 -1
- package/dist/lib/doctor.js +44 -6
- package/dist/lib/doctor.js.map +1 -1
- package/dist/lib/findings.js +14 -10
- package/dist/lib/findings.js.map +1 -1
- package/dist/lib/mcp.js +3 -3
- package/dist/lib/mcp.js.map +1 -1
- package/dist/lib/skill-manager.d.ts +50 -0
- package/dist/lib/skill-manager.js +372 -0
- package/dist/lib/skill-manager.js.map +1 -0
- package/dist/lib/swarm-orchestrator.js +14 -8
- package/dist/lib/swarm-orchestrator.js.map +1 -1
- package/dist/lib/workflow-state.js +3 -1
- package/dist/lib/workflow-state.js.map +1 -1
- package/dist/scripts/prepare-template.js +0 -19
- package/dist/scripts/prepare-template.js.map +1 -1
- package/package.json +2 -2
- package/template/.agents/skills/audit/SKILL.md +7 -7
- package/template/.agents/skills/autopilot/SKILL.md +34 -58
- package/template/.agents/skills/brief/SKILL.md +1 -1
- package/template/.agents/skills/check/SKILL.md +4 -4
- package/template/.agents/skills/complete/SKILL.md +13 -46
- package/template/.agents/skills/continuous/SKILL.md +8 -9
- package/template/.agents/skills/devflow/SKILL.md +18 -13
- package/template/.agents/skills/discovery/SKILL.md +8 -3
- package/template/.agents/skills/doctor/SKILL.md +7 -11
- package/template/.agents/skills/feature/SKILL.md +5 -6
- package/template/.agents/skills/fix/SKILL.md +2 -2
- package/template/.agents/skills/implement/SKILL.md +11 -12
- package/template/.agents/skills/release/SKILL.md +1 -1
- package/template/.agents/skills/report-html/SKILL.md +3 -3
- package/template/.agents/skills/rollback/SKILL.md +4 -6
- package/template/.agents/skills/status/SKILL.md +20 -27
- package/template/.agents/skills/try/SKILL.md +5 -6
- package/template/.claude/skills/audit/SKILL.md +7 -7
- package/template/.claude/skills/autopilot/SKILL.md +34 -58
- package/template/.claude/skills/brief/SKILL.md +1 -1
- package/template/.claude/skills/check/SKILL.md +4 -4
- package/template/.claude/skills/complete/SKILL.md +13 -46
- package/template/.claude/skills/continuous/SKILL.md +8 -9
- package/template/.claude/skills/devflow/SKILL.md +18 -13
- package/template/.claude/skills/discovery/SKILL.md +8 -3
- package/template/.claude/skills/doctor/SKILL.md +7 -11
- package/template/.claude/skills/feature/SKILL.md +5 -6
- package/template/.claude/skills/fix/SKILL.md +2 -2
- package/template/.claude/skills/implement/SKILL.md +11 -12
- package/template/.claude/skills/release/SKILL.md +1 -1
- package/template/.claude/skills/report-html/SKILL.md +3 -3
- package/template/.claude/skills/rollback/SKILL.md +4 -6
- package/template/.claude/skills/status/SKILL.md +20 -27
- package/template/.claude/skills/try/SKILL.md +5 -6
- package/template/AGENTS.md +18 -19
- package/template/devflow/build-plan.md +9 -0
- package/template/devflow/context/ai-interaction.md +55 -16
- package/template/devflow/reference/feature-spec-template.md +2 -2
- package/template/devflow/reference/running-id-contract.md +0 -3
- package/template/devflow/context/current-feature.md +0 -3
- package/template/devflow/context/current-stage.md +0 -11
- package/template/devflow/context/findings.md +0 -10
package/template/AGENTS.md
CHANGED
|
@@ -1,12 +1,12 @@
|
|
|
1
|
-
# Nexus-DevFlow
|
|
1
|
+
# Nexus-DevFlow (The 3-Pillars & Pure Task-Isolated Living Spec Model)
|
|
2
2
|
|
|
3
3
|
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.
|
|
4
4
|
|
|
5
5
|
## What this is
|
|
6
6
|
|
|
7
|
-
This project uses **Nexus-DevFlow**, an agentic workflow layer supporting **The 3-Pillars Workspace Architecture &
|
|
8
|
-
1. **🔮 Future (Backlog)**: `devflow/ideas.md` — Centralized Idea Inbox
|
|
9
|
-
2. **⚡ Present (Active Context)**: `devflow/context/` —
|
|
7
|
+
This project uses **Nexus-DevFlow**, an agentic workflow layer supporting **The 3-Pillars Workspace Architecture & Pure Task-Isolated Living Spec Model**:
|
|
8
|
+
1. **🔮 Future (Backlog)**: `devflow/ideas.md`, `devflow/project-plan.md`, `devflow/build-plan.md` — Centralized Idea Inbox & Master Build Plan.
|
|
9
|
+
2. **⚡ Present (Active Context)**: `devflow/context/` — Global Shared Source of Truth (`project-overview.md`, `coding-standards.md`, `ai-interaction.md`, `glossary.md`) & Active Task Workspaces (`devflow/context/{xxx-slug}/`).
|
|
10
10
|
3. **📦 Past (History Archive)**: `devflow/history/` — Categorized delivery archives (`features/`, `fixes/`, `rollbacks/`, and `HISTORY.md`).
|
|
11
11
|
|
|
12
12
|
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.
|
|
@@ -17,9 +17,8 @@ To start a new project, scaffold the application first in an empty folder, then
|
|
|
17
17
|
- `devflow/context/project-overview.md` - the project's source of truth
|
|
18
18
|
- `devflow/context/coding-standards.md` - engineering conventions & rules to follow
|
|
19
19
|
- `devflow/context/ai-interaction.md` - how to interact with the user on this project
|
|
20
|
-
- `devflow/context/current-stage.md` - active discovery or running delivery state
|
|
21
|
-
- `devflow/context/findings.md` - quality, security, and verification ledger
|
|
22
20
|
- `devflow/context/glossary.md` - domain terms & architecture definitions
|
|
21
|
+
- `devflow/context/{xxx-slug}/` - active task living spec, stage, and findings ledger
|
|
23
22
|
|
|
24
23
|
## Project configuration
|
|
25
24
|
|
|
@@ -45,28 +44,28 @@ Unused adapter families can be removed. Codex, Antigravity, GitHub Copilot, and
|
|
|
45
44
|
- **Dollar Prefix (`$`)**: For OpenAI Codex CLI or skill-invocation tools, e.g., `$feature`, `$fix`, `$continuous`, `$devflow`, `$discovery`.
|
|
46
45
|
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.
|
|
47
46
|
3. **Google Antigravity & Claude Code**: Native skill engines automatically discover and surface `.agents/skills/` and `.claude/skills/`.
|
|
48
|
-
4. **State-Aware Inspection**: When unsure what to do next, invoke `devflow` to automatically inspect `devflow/context/
|
|
49
|
-
5. **Default Artifact & Communication Language (Thai)**: All generated markdown stage artifacts (`
|
|
47
|
+
4. **State-Aware Inspection**: When unsure what to do next, invoke `devflow` to automatically inspect active task directories in `devflow/context/{xxx-slug}/`, `devflow/discoveries/`, and `devflow/ideas.md`.
|
|
48
|
+
5. **Default Artifact & Communication Language (Thai)**: All generated markdown stage artifacts (`spec.md`, `discovery.md`, etc.) and user communication MUST default to **Thai (`th`)**, while code, technical terms, file paths, and identifiers remain in English.
|
|
50
49
|
|
|
51
50
|
---
|
|
52
51
|
|
|
53
|
-
## ⚡ The Unified 4-Stage Living Spec Lifecycle
|
|
52
|
+
## ⚡ The Unified 4-Stage Task-Isolated Living Spec Lifecycle
|
|
54
53
|
|
|
55
|
-
All development tasks
|
|
54
|
+
All development tasks execute through the 4-step progressive lifecycle:
|
|
56
55
|
|
|
57
56
|
```text
|
|
58
57
|
/feature (หรือ /fix) ──▶ /implement ──▶ /check ──▶ /complete
|
|
59
58
|
```
|
|
60
59
|
|
|
61
|
-
1. **`feature` / `fix` (`/feature`, `/fix
|
|
62
|
-
- **Purpose**: Combines Discover, Define, Spec, and Plan into one unified step.
|
|
63
|
-
- **Artifact**: `devflow/context/
|
|
64
|
-
2. **`implement` (`/implement`)**:
|
|
65
|
-
- **Purpose**:
|
|
66
|
-
3. **`check` (`/check`)**:
|
|
67
|
-
- **Purpose**: Senior QA review, multi-lane verification matrix (Typecheck, Lint, Test suites, manual proof), and records empirical proof into `
|
|
68
|
-
4. **`complete` (`/complete`)**:
|
|
69
|
-
- **Purpose**: Final safety pass, records Release Digest, automatically archives to `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`,
|
|
60
|
+
1. **`feature` / `fix` (`/feature`, `/fix`)**:
|
|
61
|
+
- **Purpose**: Combines Discover, Define, Spec, and Plan into one unified step. Allocates sequential ID (`xxx-slug`) and initializes the **Task-Isolated Living Spec (`devflow/context/{xxx-slug}/spec.md`)**, stage pointer (`stage.md`), and dedicated audit ledger (`findings.md`).
|
|
62
|
+
- **Artifact**: `devflow/context/{xxx-slug}/spec.md`
|
|
63
|
+
2. **`implement` (`/implement [id]`)**:
|
|
64
|
+
- **Purpose**: Checks out `feature/{xxx-slug}` (or auto-detects from branch), incrementally executes checklist tasks in `devflow/context/{xxx-slug}/spec.md` with TDD discipline (Red-Green-Refactor), and appends diff evidence.
|
|
65
|
+
3. **`check` (`/check [id]`)**:
|
|
66
|
+
- **Purpose**: Senior QA review, multi-lane verification matrix (Typecheck, Lint, Test suites, manual proof), and records empirical proof into `devflow/context/{xxx-slug}/spec.md` and findings into `findings.md`.
|
|
67
|
+
4. **`complete` (`/complete [id]`)**:
|
|
68
|
+
- **Purpose**: Final safety pass, records Release Digest, automatically archives to `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`, cleanly removes `devflow/context/{xxx-slug}/`, updates `HISTORY.md` and `build-plan.md`, and performs git squash-merge.
|
|
70
69
|
|
|
71
70
|
---
|
|
72
71
|
|
|
@@ -108,3 +108,12 @@
|
|
|
108
108
|
- *Dependencies*: Feature 12, DISC-20260826-003
|
|
109
109
|
- *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
|
|
110
110
|
|
|
111
|
+
---
|
|
112
|
+
|
|
113
|
+
## ⚡ Phase 14: Pure Multi-Run Task-Isolated Architecture
|
|
114
|
+
|
|
115
|
+
- [x] **14. Pure Multi-Run Task-Isolated Architecture (`DISC-20260826-004`)** `[Size: M]`
|
|
116
|
+
- *Dependencies*: Feature 11, Feature 12, Feature 13
|
|
117
|
+
- *Scope*: ยกเลิกไฟล์ Single Living Spec ที่ Root (`current-feature.md`, `current-stage.md`, `findings.md`) อย่างสมบูรณ์ ปรับโครงสร้างสู่ Task-Isolated Subdirectories 100% (`devflow/context/{xxx-slug}/`), อัปเกรด Agent Directives, Core Context Resolver, Scaffolding Templates และ Workflow Skills ทั้งหมด
|
|
118
|
+
|
|
119
|
+
|
|
@@ -27,46 +27,60 @@ Format every response for fast scanning and readability:
|
|
|
27
27
|
|
|
28
28
|
---
|
|
29
29
|
|
|
30
|
-
## 3. The 3-Pillars Unified Architecture
|
|
30
|
+
## 3. The 3-Pillars Unified Architecture
|
|
31
31
|
|
|
32
32
|
```text
|
|
33
33
|
devflow/
|
|
34
|
-
├── 🔮 ideas.md
|
|
35
|
-
├──
|
|
36
|
-
|
|
34
|
+
├── 🔮 ideas.md # [Future] Idea Inbox with AI Feasibility Scoring
|
|
35
|
+
├── 🗺️ project-plan.md # [Future] Master Roadmap
|
|
36
|
+
├── 📋 build-plan.md # [Future] Master Build Plan & Sizing
|
|
37
|
+
│
|
|
38
|
+
├── ⚡ context/ # [Present] Living Source of Truth & Active Tasks
|
|
39
|
+
│ ├── project-overview.md # 🌐 Global Architecture & Stack
|
|
40
|
+
│ ├── coding-standards.md # 🌐 Global Coding & TDD Standards
|
|
41
|
+
│ ├── ai-interaction.md # 🌐 Global AI Interaction Rules
|
|
42
|
+
│ ├── glossary.md # 🌐 Domain Terms & Glossary
|
|
43
|
+
│ │
|
|
44
|
+
│ └── {xxx-slug}/ # ⚡ Active Task Workspace
|
|
45
|
+
│ ├── spec.md # Living Spec + TDD Checklist
|
|
46
|
+
│ ├── stage.md # Runtime Stage & Branch Reference
|
|
47
|
+
│ └── findings.md # Dedicated Audit Ledger (P0-P3)
|
|
48
|
+
│
|
|
49
|
+
└── 📦 history/ # [Past] features/, fixes/, rollbacks/, and HISTORY.md
|
|
37
50
|
```
|
|
38
51
|
|
|
39
|
-
### ⚡ The Unified 4-Stage Living Spec Lifecycle
|
|
40
|
-
|
|
52
|
+
### ⚡ The Unified 4-Stage Task-Isolated Living Spec Lifecycle
|
|
53
|
+
*ขับเคลื่อนการพัฒนาทุกระดับด้วย **Task-Isolated Living Spec (`devflow/context/{xxx-slug}/spec.md`)** ที่รวมความลึกระดับ Architect Mode เข้ากับความคล่องตัวระดับ Lean Velocity โดยแยก Workspace ของแต่ละงานออกจากกัน 100%:*
|
|
41
54
|
|
|
42
55
|
```text
|
|
43
56
|
/feature (หรือ /fix) ──▶ /implement ──▶ /check ──▶ /complete
|
|
44
57
|
```
|
|
45
58
|
|
|
46
59
|
1. **Stage 1: Spec (`/feature` หรือ `/fix`)**:
|
|
47
|
-
- ตรวจสอบ **Single Active Run Guardrail** (บล็อกการเปิดงานซ้อนถ้ามีงานที่ยังไม่เสร็จ)
|
|
48
60
|
- ดึงบริบทจาก `devflow/discoveries/`, `devflow/ideas.md`, หรือคำขอของผู้ใช้
|
|
49
|
-
- จัดสรร Running ID (`xxx-slug`)
|
|
50
|
-
- เขียน **
|
|
61
|
+
- จัดสรร Running ID (`xxx-slug`) และสร้างโฟลเดอร์ `devflow/context/{xxx-slug}/`
|
|
62
|
+
- เขียน **Task-Isolated Living Spec (`spec.md`)**, `stage.md`, และ `findings.md` ครอบคลุม:
|
|
51
63
|
- `## 🎯 1. Define & Boundaries` (Problem, In/Out Scope, Risks, Success Criteria)
|
|
52
64
|
- `## 📐 2. Technical Spec & Contracts` (Architecture, Models, Interface Contracts, Non-functional, ACs)
|
|
53
65
|
- `## 📋 3. Execution Plan & TDD Checklist` (Atomic tasks, `[TDD-Red/Green/Refactor]` Triplets)
|
|
54
66
|
|
|
55
|
-
2. **Stage 2: Implement (`/implement`)**:
|
|
67
|
+
2. **Stage 2: Implement (`/implement [id]`)**:
|
|
68
|
+
- สลับไปยัง Branch `feature/{xxx-slug}` (หรือ Auto-detect จาก Current Branch / Task Queue)
|
|
56
69
|
- ดำเนินการ Task-by-task ตาม Checklist อย่างเคร่งครัดด้วย **TDD (Red-Green-Refactor)**
|
|
57
|
-
- ติ๊กเครื่องหมาย `- [x]` และบันทึก `## ⚡ 4. Implementation Log & Evidence` (Diff summary, Checkpoints) ลงใน `
|
|
70
|
+
- ติ๊กเครื่องหมาย `- [x]` และบันทึก `## ⚡ 4. Implementation Log & Evidence` (Diff summary, Checkpoints) ลงใน `devflow/context/{xxx-slug}/spec.md`
|
|
58
71
|
|
|
59
|
-
3. **Stage 3: Check (`/check`)**:
|
|
72
|
+
3. **Stage 3: Check (`/check [id]`)**:
|
|
60
73
|
- Senior QA Multi-Lane Verification (Typecheck, Lint, Test Suites, Manual Proof)
|
|
61
|
-
- บันทึกผลการพิสูจน์เชิงประจักษ์ลงใน `## 🧪 5. Multi-Lane Verification Matrix` ใน `
|
|
74
|
+
- บันทึกผลการพิสูจน์เชิงประจักษ์ลงใน `## 🧪 5. Multi-Lane Verification Matrix` ใน `spec.md` และบันทึก Finding ลงใน `findings.md` เฉพาะงาน
|
|
62
75
|
|
|
63
|
-
4. **Stage 4: Complete (`/complete`)**:
|
|
76
|
+
4. **Stage 4: Complete (`/complete [id]`)**:
|
|
64
77
|
- สรุปผล `## 📦 6. Release Digest & Retrospective` (Changelog, Lessons Learned, ADRs)
|
|
65
|
-
- ทำการ Archive `
|
|
78
|
+
- ทำการ Archive `spec.md` ไปเป็นไฟล์เดี่ยวที่ `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`
|
|
79
|
+
- ลบโฟลเดอร์เฉพาะกิจ `devflow/context/{xxx-slug}/` ออกอย่างหมดจด
|
|
66
80
|
- **Mandatory Delivery Gate**: บังคับถามผู้ใช้ก่อนเสมอว่าต้องการ Delivery รูปแบบใด:
|
|
67
81
|
- **Option 1 (Team MR/PR Flow)**: Pull master/main ล่าสุดมารวมกับ Feature/Dev Branch แล้ว push branch ขึ้นไปเพื่อเปิด MR/PR (ไม่ merge เข้า main/master ในเครื่อง และไม่แตะ protected branch)
|
|
68
82
|
- **Option 2 (Direct Squash-Merge)**: ทำการ Squash-merge เข้า main/master ในเครื่องเฉพาะเมื่อผู้ใช้สั่งโดยตรงเท่านั้น
|
|
69
|
-
-
|
|
83
|
+
- อัปเดต `devflow/history/HISTORY.md` และ `devflow/build-plan.md` ให้เป็น `[x]` เรียบร้อย
|
|
70
84
|
|
|
71
85
|
---
|
|
72
86
|
|
|
@@ -145,3 +159,28 @@ Progress lives in persistent files, not in transient chat history:
|
|
|
145
159
|
- **Lazy Inline Persistence**:
|
|
146
160
|
- Immediately append resolved terms to `devflow/context/glossary.md`.
|
|
147
161
|
- Immediately record major, hard-to-reverse architectural decisions as Architecture Decision Records in `devflow/decisions/ADR-xxx-{slug}.md`.
|
|
162
|
+
|
|
163
|
+
---
|
|
164
|
+
|
|
165
|
+
## 10. Third-Party Skill Orchestration & Multi-Skill Delegation Protocol
|
|
166
|
+
|
|
167
|
+
Nexus-DevFlow natively supports extending workflow capabilities with **Third-Party Skills** (installed via `nexus-devflow skill add <repo-or-path>`):
|
|
168
|
+
|
|
169
|
+
### 🧩 1. Discovery & Inventory
|
|
170
|
+
- Core workflow commands and AI agents automatically inspect `.agents/skills/` (and `.claude/skills/`) or run `nexus-devflow skill list` to discover installed third-party capabilities.
|
|
171
|
+
- Installed third-party skills maintain their exact original directory structure, references, assets, scripts, and `SKILL.md`.
|
|
172
|
+
|
|
173
|
+
### 🎯 2. Cross-Command Delegation & Genuine Execution
|
|
174
|
+
- **Verbatim & Original Prompt Fidelity**: When a DevFlow stage requires specialized domain expertise (e.g., editorial diagramming, domain modeling, cloud provisioning, UI benchmarking), the AI agent must read the third-party skill's `SKILL.md` (e.g. `.agents/skills/diagram-design/SKILL.md`) and strictly follow its original instructions, philosophy, style guide gates, and complexity constraints.
|
|
175
|
+
- **Workflow Command Integration Map**:
|
|
176
|
+
- **`/discovery`**: When macro roadmap planning or micro pre-flight exploration involves system architecture, IT landscape, data pipelines, sequence flows, or user journeys, check for `diagram-design` and generate editorial HTML/SVG diagrams.
|
|
177
|
+
- **`/feature` & `/fix`**: In Section 2 (`## 📐 2. Technical Spec & Contracts`), invoke `diagram-design` for component diagrams, database ER models, or sequence flows.
|
|
178
|
+
- **`/brainstorm` & `/grill`**: Leverage visual trade-off matrices (Quadrant, Radar spider) or domain models (UML class, ER).
|
|
179
|
+
- **`/prototype` & `/report-html`**: Embed standalone HTML/SVG assets seamlessly.
|
|
180
|
+
- **`/devflow`**: Intent router surfaces installed third-party skills (e.g. `/diagram-design`) directly to the user.
|
|
181
|
+
|
|
182
|
+
### 📁 3. Generated Asset Storage Hierarchy
|
|
183
|
+
- **Discovery Stage**: `devflow/discoveries/{id}/diagrams/` (referenced in `discovery.md`).
|
|
184
|
+
- **Active Task Stage**: `devflow/context/{xxx-slug}/diagrams/` (referenced in `spec.md`).
|
|
185
|
+
- **Global / Reference**: `devflow/reference/diagrams/` or `devflow/reference/assets/`.
|
|
186
|
+
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
# [ID-slug] Feature Title
|
|
2
2
|
|
|
3
|
-
> **Template Type**:
|
|
4
|
-
> **Active Location**: `devflow/context/
|
|
3
|
+
> **Template Type**: Task-Isolated Living Spec
|
|
4
|
+
> **Active Location**: `devflow/context/{xxx-slug}/spec.md`
|
|
5
5
|
> **Archive Location**: `devflow/history/{features|fixes|rollbacks}/{ID-slug}.md`
|
|
6
6
|
|
|
7
7
|
- **Feature ID**: `{xxx-slug}`
|
|
@@ -15,9 +15,6 @@ devflow/
|
|
|
15
15
|
│ ├── coding-standards.md # Engineering, code quality, TDD, and testing standards
|
|
16
16
|
│ ├── ai-interaction.md # AI agent interaction rules, unified living spec flow, and Thai defaults
|
|
17
17
|
│ ├── glossary.md # Domain glossary and architecture vocabulary
|
|
18
|
-
│ ├── current-feature.md # Active Living Spec pointer / legacy fallback
|
|
19
|
-
│ ├── current-stage.md # Active state pointer and run tracker
|
|
20
|
-
│ ├── findings.md # Shared/default audit findings ledger (P0-P3)
|
|
21
18
|
│ │
|
|
22
19
|
│ ├── {xxx-slug}/ # Active Run Workspace & Spec Queue (Multi-Run Active Task)
|
|
23
20
|
│ │ ├── spec.md # Living Spec + Checklist for this run
|
|
@@ -1,11 +0,0 @@
|
|
|
1
|
-
# Current Stage
|
|
2
|
-
|
|
3
|
-
- Active Discovery ID: `None`
|
|
4
|
-
- Active Running ID: `None`
|
|
5
|
-
- Track: `idle`
|
|
6
|
-
- Current Stage: `idle`
|
|
7
|
-
- Active Branch: `main`
|
|
8
|
-
- Living Spec: `devflow/context/current-feature.md`
|
|
9
|
-
- Next Action: `Run /feature, /fix, or /discovery to start new work.`
|
|
10
|
-
- Last Completed Run: `None`
|
|
11
|
-
- Last Updated: `None`
|
|
@@ -1,10 +0,0 @@
|
|
|
1
|
-
# Findings
|
|
2
|
-
|
|
3
|
-
> **Generated file.** The findings ledger: review findings raised by `/audit`
|
|
4
|
-
> against the work in progress, each with a durable ID, severity (P0-P3), and
|
|
5
|
-
> status. `/implement` marks repaired findings `fixed`, a later `/audit` pass
|
|
6
|
-
> moves them to `closed`, and `/complete` refuses to merge while any P0 or P1
|
|
7
|
-
> finding is `open` or `fixed`, then archives resolved findings with the work
|
|
8
|
-
> and resets this file.
|
|
9
|
-
|
|
10
|
-
_No findings recorded. `/audit` appends findings here when it finds them._
|