architext 0.0.5 → 0.0.6

package/dist/templates/en/briefs/_base.md

@@ -18,14 +18,14 @@
 
 ---
 
-## Core Tasks
+## Functional Requirements
 
-> Must-have tasks, each in one paragraph describing expected behavior.
-> Detailed specs are defined in `/archi.plan`; here just clarify "what to build."
+> Core capabilities to implement—describe "what" not "how."
+> AI will decompose these into implementation tasks; here just clarify the business goal.
 
-1.
-2.
-3.
+-
+-
+-
 
 ---
 
@@ -84,6 +84,13 @@
 **Directory structure**: [already defined → describe key dirs / none (AI generates based on pattern)]
 **Branching strategy**: [e.g.: Trunk-based / Git Flow / GitHub Flow]
 **Commit convention**: [e.g.: Conventional Commits (feat/fix/chore) / custom → describe]
+
+**AI Git Workflow** (Git conventions when AI runs `/archi.code`):
+- **Auto commit**: [Yes - auto git commit after each Task / No - generate commit message only, user commits manually]
+- **Commit granularity**: [Per Task / Per Phase / As needed]
+- **Branching**: [Work directly on main / Create branch per Task `feat/{task-id}`]
+- **Auto push**: [Yes / No]
+
 **Testing preference**: [e.g.: Vitest / Jest / pytest / no special requirements]
 
 ---

package/dist/templates/en/briefs/_modules.md

@@ -10,7 +10,7 @@
 
 > If you already know core data entities and relationships, describe them here. No need for full schema—list entity names and key fields.
 > AI will generate detailed data model in `/archi.plan`; here just clarify "what data exists."
-> Leave blank if not applicable; AI will derive from core tasks.
+> Leave blank if not applicable; AI will derive from core features.
 
 <!-- Format reference:
 - **User**: email, name, role (admin/user), avatar
@@ -71,7 +71,7 @@
 
 ### Visual Reference
 
-> Provides aesthetic input for AI—directly impacts `ui_concept.html` visual quality.
+> Provides aesthetic input for AI—directly impacts visual quality of screen prototypes in the `screens/` directory.
 > Any field below is valid; the more you fill, the better AI can match your expected style.
 
 **Competitor/inspiration screenshots**: [paste image / Figma link / URL]

package/dist/templates/en/docs/global/error_memory.json

@@ -0,0 +1,40 @@
+{
+  "errorPatterns": {
+    "_comment": "Error patterns: { id: unique identifier, watchFor: [scenarios to watch before execution], matchWhen: [keywords to match after error], cause: root cause, solution: solution, lesson: lesson/principle }. AI appends here after resolving errors",
+    "examples": [
+      {
+        "id": "build-vite-config-missing",
+        "watchFor": ["Run npm run build", "Modify vite.config.ts"],
+        "matchWhen": ["ENOENT", "vite.config", "Cannot find module"],
+        "cause": "Config file deleted or node_modules not installed",
+        "solution": "Check file existence, run npm install to reinstall deps",
+        "lesson": "Backup before modifying configs, regularly verify node_modules integrity"
+      },
+      {
+        "id": "type-import-assertion-deprecated",
+        "watchFor": ["Import JSON files"],
+        "matchWhen": ["assert", "SyntaxError", "import", "type"],
+        "cause": "Node.js 18+ deprecated import assert syntax, use import attributes instead",
+        "solution": "Change assert { type: 'json' } to with { type: 'json' }",
+        "lesson": "Watch Node.js version updates, verify import JSON syntax for your version"
+      }
+    ]
+  },
+  "checkpoints": {
+    "_comment": "Checkpoints: { before: operation description to match before execution, check: [list of errorPatterns.id to check] }. AI auto-generates from watchFor scenarios",
+    "examples": [
+      {
+        "before": "Run npm run build",
+        "check": ["build-vite-config-missing"]
+      },
+      {
+        "before": "Modify config files",
+        "check": ["build-vite-config-missing"]
+      },
+      {
+        "before": "Import JSON files",
+        "check": ["type-import-assertion-deprecated"]
+      }
+    ]
+  }
+}

package/dist/templates/en/docs/global/map.json

@@ -1,99 +1,55 @@
 {
-  "governance": {
-    "coreRules": [
+  "directoryMapping": {
+    "_comment": "Code directory ↔ module mapping: { path: directory path, module: module name, responsibility: responsibility description }",
+    "examples": [
       {
-        "file": "00_system.md",
-        "role": "System Role",
-        "when": "At the start of every session (Identity, Core Principles)"
+        "path": "src/features/auth",
+        "module": "auth",
+        "responsibility": "User authentication, login, registration"
       },
       {
-        "file": "01_workflow.md",
-        "role": "SOP",
-        "when": "Decides current task flow (Task vs Fix) & Acceptance Criteria"
-      },
-      {
-        "file": "02_tech_stack.md",
-        "role": "Tech Stack",
-        "when": "Tech choices, coding standards, engineering governance"
-      },
-      {
-        "file": "03_data_governance.md",
-        "role": "Data Governance",
-        "when": "When reading/writing global JSON data files"
-      },
-      {
-        "file": "04_cli_tools.md",
-        "role": "CLI Reference",
-        "when": "When executing Terminal Gate commands (npx archi task/plan/render syntax reference)"
-      },
-      {
-        "file": "99_context_glue.md",
-        "role": "Context Bridge",
-        "when": "Automatically links context docs when touching code"
+        "path": "src/features/todos",
+        "module": "todo",
+        "responsibility": "Todo CRUD operations"
       }
-    ],
-    "globalReference": [
-      {
-        "file": "roadmap.json",
-        "role": "Roadmap",
-        "content": "Progress tracking, milestones, technical debt management"
-      },
-      {
-        "file": "vision.md",
-        "role": "Vision",
-        "content": "Vision, North Star Metric, Design Philosophy"
-      },
-      {
-        "file": "map.json",
-        "role": "Map (This file)",
-        "content": "Directory structure, file index, logical topology"
-      },
-      {
-        "file": "dictionary.json",
-        "role": "Dictionary",
-        "content": "Business glossary, shared component registry"
-      },
-      {
-        "file": "design_tokens.json",
-        "role": "Visuals [?UI]",
-        "content": "Colors, typography, spacing variables"
-      },
-      {
-        "file": "data_snapshot.json",
-        "role": "Data [?Data]",
-        "content": "Database Schema snapshot"
-      },
-      {
-        "file": "error_codes.json",
-        "role": "Errors",
-        "content": "Error codes & protocol contracts"
+    ]
+  },
+  "logicalTopology": {
+    "_comment": "Logical topology: { module: module name, layer: layer(layer/domain/interface/infrastructure), depends: [dependent modules] }",
+    "examples": [
+      { "module": "auth", "layer": "domain", "depends": ["user-repo"] },
+      { "module": "todo", "layer": "domain", "depends": ["auth", "todo-repo"] }
+    ]
+  },
+  "criticalUserJourneys": {
+    "_comment": "Critical user journeys: { journey: journey name, steps: [steps], owner: owning task ID }",
+    "examples": [
+      {
+        "journey": "User Registration & Login",
+        "steps": [
+          "Visit homepage",
+          "Click register",
+          "Fill form",
+          "Submit",
+          "Login success"
+        ],
+        "owner": "FEAT-AUTH"
       }
     ]
   },
-  "featureDocs": [
-    {
-      "file": "spec.md",
-      "category": "Specification",
-      "purpose": "Business Logic, Algorithms, Acceptance Criteria (Logic)"
-    },
-    {
-      "file": "ui.md",
-      "category": "UI/UX",
-      "purpose": "Task-level UI scope declaration — references screen IDs from ui_context.md to define this task's screen/component scope"
-    },
-    {
-      "file": "design.md",
-      "category": "Technical Design",
-      "purpose": "[?Complex] Technical design — state machine/pipeline/protocol definitions, parameter table, invariants"
-    },
-    {
-      "file": "plan.json",
-      "category": "Plan",
-      "purpose": "Detailed Step Breakdown & Test Cases (Execution)"
-    }
-  ],
-  "directoryMapping": [],
-  "logicalTopology": [],
-  "criticalUserJourneys": [],
-  "featureRelations": []
+  "featureRelations": {
+    "_comment": "Impact relations organized as networks: { group: network name, members: [member files], rule: change rule }",
+    "examples": [
+      {
+        "group": "Tech Specs",
+        "members": [
+          "tech_stack.md",
+          "prompts/code.md",
+          "prompts/audit.md",
+          "rules/00_system.md"
+        ],
+        "rule": "Tech stack changes need to sync protocol docs"
+      }
+    ]
+  }
 }

package/dist/templates/en/{rules/04_cli_tools.md → docs/global/references/cli_reference.md}

@@ -1,13 +1,6 @@
----
-description: CLI Reference Manual. Working directory rule and command syntax for npx archi task/plan/render.
-globs: **/*
-applyTo: **/*
-alwaysApply: true
----
-
 # CLI Reference
 
-> **Role**: Command quick-reference. Provides syntax and parameters for `npx archi` commands, for use during Terminal Gate execution.
+> **Role**: Command reference manual. Provides syntax and parameters for `npx archi` commands, for use during Terminal Gate execution.
 
 ## ⛔ Working Directory Gate
 
@@ -16,7 +9,7 @@ alwaysApply: true
 | Check | Pass Condition |
 |:---|:---|
 | Current directory | Must be project root (directory containing `[[__DOCS_DIR__]]/`) |
-| If unsure | Confirm current directory first; forbidden to guess |
+| When uncertain | Confirm current directory first; do not guess |
 | In subdirectory | Must `cd` to root before executing |
 
 ---
@@ -27,7 +20,7 @@ alwaysApply: true
 
 | Subcommand | Purpose | Example |
 |:---|:---|:---|
-| `npx archi task` | List all tasks with progress | `npx archi task` |
+| `npx archi task` | List all tasks and progress | `npx archi task` |
 | `npx archi task <ID> --status <s>` | Update task status | `npx archi task INF-001 --status done` |
 | `npx archi task --check` | Check Roadmap consistency | `npx archi task --check` |
 
@@ -37,7 +30,7 @@ alwaysApply: true
 
 | Subcommand | Purpose | Example |
 |:---|:---|:---|
-| `npx archi plan <ID>` | Check Task's Plan completion | `npx archi plan SUB-01` |
+| `npx archi plan <ID>` | Check Task Plan completion | `npx archi plan SUB-01` |
 
 Automatically identifies Manual Verification sections and excludes them from automated statistics.
 
@@ -45,6 +38,6 @@ Automatically identifies Manual Verification sections and excludes them from aut
 
 | Subcommand | Purpose | Example |
 |:---|:---|:---|
-| `npx archi render` | Render all JSON data files into human-readable `.md` views | `npx archi render` |
+| `npx archi render` | Render all JSON data files as human-readable `.md` views | `npx archi render` |
 
-> `.md` views are auto-generated; forbidden to edit directly. Modifications must go through `.json` source files.
+> `.md` views are auto-generated; do not edit directly. Modifications must go through the `.json` source files.

package/dist/templates/en/{rules/02_tech_stack.md → docs/global/tech_stack.md}

@@ -1,10 +1,3 @@
----
-description: Technical Standards & Technology Stack. Contains language versions, framework choices, coding conventions, naming rules, and forbidden patterns. Consult when writing code.
-globs: **/*
-applyTo: **/*
-alwaysApply: true
----
-
 # Tech Stack & Engineering Standards: [Project Name]
 
 > **Role:** The "Law" of the codebase. Defines tools, structure, and engineering workflows.
@@ -53,23 +46,19 @@ alwaysApply: true
 
 ---
 
-## 4. UI Protocol: ITP v3.0 (Dual-Artifact) [Optional - Only for UI Projects]
+## 4. UI Protocol: ITP v3.0 (Tri-Artifact) [Optional - Only for UI Projects]
 <!-- Core UI Description Protocol -->
 > **Note:** If project has no UI (e.g. CLI, Backend API, Library), remove this section.
 
-### 4.1 Dual-Artifact Strategy
-
-UI artifact hierarchy:
+### 4.1 Tri-Artifact Strategy
 
 | Artifact | Format | Reader | Responsibility |
 |:---|:---|:---|:---|
-| `ui_concept.html` | Single-file HTML | Human (browser) | **Global visual source of truth** — wireframes/styled screens for the entire project |
-| `ui_context.md` | Structured Markdown | AI (plan/code/audit/edit) | **AI screen index** — lightweight list of screen IDs / routes / states / navigation graph / shared components |
-| `ui.md` | ITP v3.0 DSL | AI (code/audit) | Task-level UI scope declaration — which screens/components this task covers |
-- `ui_concept.html` is generated by the `archi-ui-wireframe` Skill, covering all user-visible screens; for human browser preview only
-- `ui_context.md` is generated by the same Skill simultaneously; it is the sole AI entry point for UI structure; do not edit manually
-- `ui.md` only declares "which screens/states in ui_context.md this task is responsible for"; do not redefine global layout
-- Code phase uses `ui.md` (task design) + `ui_context.md` (structure/navigation) + `design_tokens.json` (visual constraints) as source; also uses `ui_concept.html` as **read-only visual reference** to calibrate layout; implement equivalent visual effect with the **project's own tech stack**
+| `screens/` | Multi-file HTML (`index.html` + `S-XX.html` + `_shared.css`) | Human (browser) | **Global visual source of truth** — triggered by `/archi.ui` Skill; each screen independently previewable |
+| `ui_context.md` | Structured Markdown | AI (plan/code/audit/edit) | **AI screen index** — sole AI entry point for UI structure; generated by same Skill; do not edit manually |
+| `ui.md` | ITP v3.0 DSL | AI (code/audit) | Task-level UI scope declaration — only declares which screens/states this task covers; do not redefine global layout |
+
+- Code phase uses `ui.md` + `ui_context.md` + `design_tokens.json` as source; `screens/S-XX.html` as **read-only visual reference**; implement equivalent visual effect with **project's own tech stack**
 
 ### 4.2 Naming (PrefixFunction)
 Component naming must follow `Prefix+Function` format:

package/dist/templates/en/docs/global/vision.md

@@ -77,6 +77,6 @@ description: Project Constitution: Vision, Personas, Principles & Boundaries.
 **Trigger**: Only modify during project initialization (`/archi.start`) or major strategic pivot (`/archi.revise`).
 
 **Action**:
-1.  **Alignment**: Ensure Section 3 (Principles) conflicts with technology choices in `02_tech_stack.md`.
+1.  **Alignment**: Ensure Section 3 (Principles) conflicts with technology choices in `tech_stack.md`.
 2.  **Completeness**: Must fill all `[ ]` placeholders, strictly no "Example" text remaining.
 3.  **Consistency**: All Task Specs (`.spec.md`) must reference the Vision in this file to ensure alignment.

package/dist/templates/en/docs/prompts/audit.md

@@ -33,10 +33,10 @@
         | `pending` | Reject — no code to review |
         | `blocked` | Reject — upstream deps incomplete |
 
-    3.  **Load**: vision.md (direction anchor) + task docs (spec/plan/ui) + prior audit.md (for comparison) + project context (tech_stack/design_tokens/data_snapshot/ui_context/ui_concept). Read all code files for this task.
+    3.  **Load**: vision.md (direction anchor) + task docs (spec/plan/ui) + prior audit.md (for comparison) + project context (tech_stack/design_tokens/data_snapshot/ui_context/screens/). Read all code files for this task.
 
     **Project-level — Load Overview**:
-    1.  Read vision.md, roadmap.json, map.json, 02_tech_stack.md.
+    1.  Read vision.md, roadmap.json, map.json, tech_stack.md.
     2.  Scan tasks/ directory structure.
     3.  Read project code entry points and key modules.
 
@@ -57,15 +57,15 @@
     | 4 | **Logic correctness** | Business logic errors, contradictions, missing branches, state machine defects |
     | 5 | **Bug hunting** | null/undefined, race conditions, resource leaks, infinite loops, off-by-one |
     | 6 | **Error handling** | Swallowing, silent failure, error propagation chain, user-visible feedback |
-    | 7 | **Tech Stack compliance** | Per `02_tech_stack.md`: forbidden patterns, outdated API, hardcoding |
+    | 7 | **Tech Stack compliance** | Per `tech_stack.md`: forbidden patterns, outdated API, hardcoding |
     | 8 | **Security** | Sensitive info leak, unvalidated input, injection risk, permission checks |
     | 9 | **Performance** | Unnecessary full imports, large loops, dead computation, memory leaks, N+1 queries |
-    | 10 | (When this task involves UI) **Design compliance** | Token usage; no hardcoded magic values; visual consistency with `ui_concept.html` |
+    | 10 | (When this task involves UI) **Design compliance** | Token usage; no hardcoded magic values; visual consistency with `screens/S-XX.html` |
     | 11 | (When this task involves data) **Data consistency** | Field names/types match `data_snapshot.json` |
     | 12 | (i18n projects only) **I18n compliance** | No hardcoded strings; must use Key/dictionary refs |
     | 13 | **Orphan .gitkeep** | `.gitkeep` exists when dir has other files — remove |
     | 14 | **Spec-Code drift** | Interface/type/behavior match `spec.md`; manual changes synced to docs |
-    | 15 | (When this task involves UI) **UI ref completeness** | `ui.md` `ref: ui_concept.html#S-XX` pointers still valid |
+    | 15 | (When this task involves UI) **UI ref completeness** | `ui.md` `ref: screens/S-XX.html` pointers still valid |
 
     **Output**: Finding list grouped by dimension; each with level, location, description. Enter step_3_report.
 </step_2a_task>

package/dist/templates/en/docs/prompts/code.md

@@ -1,6 +1,6 @@
 <protocol_code>
   **Trigger**: `/archi.code <id>` | Auto-loaded by Workflow Dispatch on natural language trigger
-  **Goal**: Complete feature development per `tasks/<id>_<Slug>/plan.json` task list; follow `02_tech_stack.md` (UI projects only: also follow `design_tokens.json`); pass build, types, Lint, format, tests and audit.
+  **Goal**: Complete feature development per `tasks/<id>_<Slug>/plan.json` task list; follow `tech_stack.md` (UI projects only: also follow `design_tokens.json`); pass build, types, Lint, format, tests and audit.
 
 <meta>
     <style>Deterministic, Type-Safe, SOTA-First</style>
@@ -29,7 +29,7 @@
         | `blocked` | Reject — upstream deps incomplete |
         | `done` | Reject — already done; use `/archi.edit <ID>` for changes |
 
-    3.  **Load**: task docs (spec/ui/design/plan) + project context (tech_stack/design_tokens/data_snapshot/ui_context/ui_concept) + refs (match by tags; load only matched files).
+    3.  **Load**: task docs (spec/ui/design/plan) + project context (tech_stack/design_tokens/data_snapshot/ui_context/screens/) + refs (match by tags; load only matched files).
 
     **Output**: Atomic task list to implement with dependencies and order.
 </step_1_resolve>
@@ -49,10 +49,10 @@
 <step_3_implement>
     **Protocol**:
     - **Read First**: Must read target file before modify; follow existing project code style.
-    - **Use Existing Stack**: Use only tech and libs declared in `02_tech_stack.md`.
-    - (When this task involves UI) **Design Tokens Only**: Styles strictly use Token/Preset; no hardcoded magic values.
+    - **Use Existing Stack**: Use only tech and libs declared in `tech_stack.md`.
+    - (When this task involves UI) [[INCLUDE: shared/ui-redlines.md]]
     - **Type-Safe**: Complete type definitions; use project type system to guard boundaries.
-    - **Code Organization**: Follow `02_tech_stack.md` architecture and file placement.
+    - **Code Organization**: Follow `tech_stack.md` architecture and file placement.
     - **Comments**: Explain Why, not What.
     - **Naming**: Self-explanatory names; no meaningless names.
     - Complex tasks only: **Design Adherence**: When `design.md` exists, implementation must strictly follow its state machine/pipeline/protocol; params reference § 3 values; must satisfy all § 4 Invariants.
@@ -68,9 +68,13 @@
 </step_3_implement>
 
 <step_4_validate>
-    **Action** (on failure fix and re-run; commands per `02_tech_stack.md` Section 5):
+    **Action** (on failure fix and re-run; commands per `tech_stack.md` Section 5):
 
-    **Automated Check**: Run `[[__DOCS_DIR__]]/scripts/validate` (if exists); otherwise execute checklist:
+    **Automated Check**: Check `scripts/validate`:
+    - **Exists** → Must run, results per script output
+    - **Not exists** → Execute checklist below
+
+    > **Scripts Check**: If `scripts/` directory does not exist → Suggest running `/archi.script` to generate automation scripts first.
 
     | Phase | Check | Requirement |
     |:---|:---|:---|
@@ -111,7 +115,7 @@
     [[SUBAGENT: archi-feature-relations|mode: check, context: Compare implemented feature with featureRelations sources semantically]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-feature-relations/SKILL.md`, follow mode: check logic)]]
 
     **5C. Data governance sync**:
-    [[SUBAGENT: archi-data-sync|context: Scan new business entities/error codes/Schema from implementation; incrementally sync per 03_data_governance.md]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-data-sync/SKILL.md` and follow its protocol)]]
+    [[SUBAGENT: archi-data-sync|context: Scan new business entities/error codes/Schema from implementation; incrementally sync per 00_system.md]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-data-sync/SKILL.md` and follow its protocol)]]
 
     [[INCLUDE: shared/verify-result-handling.md]]
 </step_5_verify>
@@ -128,7 +132,7 @@
     1.  Confirm `plan.json` each task `done` flag updated.
     2.  **Drift Warning**: Compare code changes with `spec.md` key points. If beyond spec coverage → mark `⚠️ Spec drift`, suggest `/archi.edit <ID>`.
     3.  Output completed task list and patch links.
-    4.  Provide next steps and Git Commit Suggestion (Conventional Commits).
+    4.  Provide next steps.
 
     **Pre-signoff Checklist** (confirm each item before Output):
     □ plan.json — every task done flag updated in real-time (not batch-updated at signoff)
@@ -136,13 +140,21 @@
     □ Step 4 — Task Verification executed for each project type with Evidence attached
     □ Step 5A Silent Audit — executed, all CRITICAL issues resolved
     □ Step 5B featureRelations check — executed
-    □ Step 5C data governance sync — executed
+      - Check if modified files affect other linked files
+    □ Step 5C data governance sync — executed:
+      - dictionary.json + error_codes.json + env_registry.json — required
+      - (UI projects only) design_tokens.json + ui_context.md
+      - (Data projects only) data_snapshot.json
+      - (API projects only) api_snapshot.json
+      - (CLI projects only) command_api.json
+      - (Lib projects only) public_api.json
     □ Terminal Gate — npx archi plan <ID> all complete (exempt items only)
 
-    **Output**: Completion summary with completed tasks, exempt items (if any), Git Commit suggestion, Next Steps:
+    **Output**: Completion summary with completed tasks, exempt items (if any), Next Steps:
 
     | Priority | Action | Notes |
     |:---|:---|:---|
+    | (If no scripts/) | `/archi.script` | Generate automation scripts (validate/dev-up/dev-reset) |
     | Recommended | `/archi.audit <ID>` | Independent review of implementation |
     | (If Spec drift) | `/archi.edit <ID>` | Update docs before continuing |
     | (If next pending task) | `/archi.plan <next pending ID>` | Plan the next task |

package/dist/templates/en/docs/prompts/edit.md

@@ -41,14 +41,14 @@
 <step_2_refine_docs>
     **Action**:
     - Modify spec.md and ui.md per `[context]`.
-    - (UI modified) [[SKILL: archi-ui-wireframe|Follow the skill protocol to sync `ui_concept.html` + `ui_context.md`]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-ui-wireframe/SKILL.md`)]]:
+    - (UI modified) [[SKILL: archi-ui-wireframe|Follow the skill protocol to sync `screens/S-XX.html` + `ui_context.md`]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-ui-wireframe/SKILL.md`)]]:
 
       | Change Type | Criteria | Handling |
       |:---|:---|:---|
       | No screen impact | Logic/data change only | Update spec.md only |
-      | Minor UI tweak | New/modified state, popup, local area | Call skill to update; output `MODIFIED: S-XX` |
+      | Minor UI tweak | New/modified state, popup, local area | Call skill to update; output `MODIFIED: screens/S-XX.html` |
       | Screen structure change | Layout refactor, new screen, navigation change | Call skill to update |
-      | Task reduction | Screen/region removed entirely | Call skill to remove; output `REMOVED: S-XX` |
+      | Task reduction | Screen/region removed entirely | Call skill to remove; output `REMOVED: screens/S-XX.html` |
 
     - Ask user when requirements are vague.
 
@@ -65,9 +65,15 @@
     |:---|:---|:---|
     | 3 | [when status=done] `npx archi task <ID> --status active` | Status reset |
 
-    **Output**: plan.json with new tasks appended; if status transition performed, output `MODIFIED: roadmap.json <ID>.status done→active`. Enter step_4_verify.
+    **Output**: plan.json with new tasks appended; if status transition performed, output `MODIFIED: roadmap.json <ID>.status done→active`. Enter step_4_data_sync.
 </step_3_update_plan>
 
+<step_4_data_sync>
+    **Data governance sync**:
+
+    [[SUBAGENT: archi-data-sync|context: Scan new business entities/error codes/Schema/endpoints/commands/exports from requirement changes, incrementally sync per 00_system.md]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-data-sync/SKILL.md`, follow its execution protocol)]]
+</step_4_data_sync>
+
 <step_4_verify>
     **Role**: Independent Reviewer
 
@@ -76,17 +82,25 @@
     [[INCLUDE: shared/verify-result-handling.md]]
 </step_4_verify>
 
-<step_5_summary>
+<step_6_summary>
     **Pre-signoff Checklist** (confirm each item before Output):
     □ spec.md — updated per context, changes tracked
-    □ (if UI changed) ui.md + ui_concept.html + ui_context.md — synced
+    □ (if UI changed) ui.md + screens/S-XX.html + ui_context.md — synced
     □ plan.json — new Phase appended (history tasks fully preserved)
     □ (if original status=done) roadmap.json — status reset to active
+    □ Global files — related JSON files synced for changes:
+      - dictionary.json + error_codes.json + env_registry.json — required
+      - (UI projects only) design_tokens.json + ui_context.md
+      - (Data projects only) data_snapshot.json
+      - (API projects only) api_snapshot.json
+      - (CLI projects only) command_api.json
+      - (Lib projects only) public_api.json
+    □ Step 4 Data Sync — archi-data-sync executed
     □ Step 4 Silent Audit — executed, all CRITICAL issues resolved
     □ Terminal Gate — task --check no ERROR (executed in step_3)
 
     **Action** (Gate must complete in step_3):
     **Output**: Task update summary with Spec/UI/Plan change overview and Next Steps table. Recommend running `/archi.code <ID>`.
-</step_5_summary>
+</step_6_summary>
 
 </protocol_edit>

package/dist/templates/en/docs/prompts/fix.md

@@ -23,7 +23,7 @@
         - Without `<id>`: Analyze `[context]` to find most relevant module.
           Single match → auto lock | Multiple matches → list candidates and ask | Cannot locate → error, request ID.
     2.  Read all docs and related code in target directory.
-    3.  Read 02_tech_stack.md (tech red lines) and vision.md (direction anchor).
+    3.  Read tech_stack.md (tech red lines) and vision.md (direction anchor).
     4.  Analyze `[context]` with code logic to locate potential fault points.
     5.  **Hypothesis**: Propose 1–3 root cause hypotheses.
 
@@ -50,6 +50,7 @@
     **Terminal Gate** (do not skip):
     | Step | Command | Pass Condition |
     |:---|:---|:---|
+    | 0 | Check `scripts/validate` | If exists, must run; results per script |
     | 1 | Run build command | Build success |
     | 2 | Run type check | Zero type errors |
     | 3 | Run Lint/Format | Pass |
@@ -63,6 +64,12 @@
     [[INCLUDE: shared/verify-result-handling.md]]
 </step_4_verify>
 
+<step_4_5_data_sync>
+    **Data governance sync**:
+
+    [[SUBAGENT: archi-data-sync|context: Scan new business entities/error codes/Schema from Bug fix, incrementally sync per 00_system.md]][[NO-SKILL: (Skill not installed: read `[[__DOCS_DIR__]]/skills/archi-data-sync/SKILL.md`, follow its execution protocol)]]
+</step_4_5_data_sync>
+
 <step_5_plan_update>
     **Action**:
     1. Update plan.json Bugfix Phase completed tasks `done: true`.
@@ -78,6 +85,7 @@
     □ plan.json — Bugfix Phase appended (step_2)
     □ Reproduction test created and verified (Red → Green)
     □ Code fix targets Bug only, no opportunistic refactoring
+    □ Step 4.5 Data Sync — archi-data-sync executed
     □ Step 4 Terminal Gate — Build / type check / Lint / tests all passed
     □ Step 4 Silent Audit — executed, all CRITICAL issues resolved
     □ plan.json Bugfix Phase — done flags updated (step_5)
@@ -86,8 +94,9 @@
 
     | Priority | Action | Notes |
     |:---|:---|:---|
+    | (If no scripts/) | `/archi.script` | Generate automation validation scripts |
     | Recommended | `/archi.audit <ID>` | Re-audit to confirm fix complete |
     | Optional | `/archi.code <ID>` | If incomplete items, continue implementation |
-</step_5_summary>
+</step_6_summary>
 
 </protocol_fix>