@relipa/ai-flow-kit 0.0.4-beta.2 → 0.0.4-beta.3

package/AIFLOW.md

@@ -83,7 +83,7 @@ claude                           # open Claude → AI auto-starts Gate 1
 
 | Step | Action | Purpose |
 |------|--------|---------|
-| 1 | Load ticket from `.claude/context/current.json` | Get PM's requirements, comments |
+| 1 | Load ticket from `.aiflow/context/current.json` | Get PM's requirements, comments |
 | 2 | Read `CLAUDE.md` + source code | Understand architecture, tech stack, patterns |
 | 3 | Investigate related files & data flow | Identify affected areas, dependencies |
 | 4 | Ask clarifying questions (one at a time) | Ensure full understanding |
@@ -415,7 +415,7 @@ aiflow guide                          # view quickstart guide
 
 ## Multi-AI Environment Setup
 
-One of the core strengths of `ai-flow-kit` is that the **Gate Workflow** is tool-agnostic. Since state is saved in `.claude/context/current.json` and the `plan/` directory, you can switch tools mid-task.
+One of the core strengths of `ai-flow-kit` is that the **Gate Workflow** is tool-agnostic. Since state is saved in `.aiflow/context/current.json` and the `plan/` directory, you can switch tools mid-task.
 
 ### How to Switch Tools
 1. **Analyze (Gate 1)** using Claude Code CLI (great for deep codebase scans).

package/CHANGELOG.md

@@ -9,7 +9,10 @@ Versioning follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
 
-> Changes that are merged but not yet released.
+### Changed
+- Neutralized project structure by moving shared ticket context to `.aiflow/context/current.json`.
+- Updated all AI templates (Claude, Cursor, Gemini, Copilot) to point to the new shared context location.
+- Updated `aiflow use` and `aiflow prompt` to work with the new neutral path.
 
 ---
 

package/QUICK_START.md

@@ -103,7 +103,7 @@ claude                        # AI auto-starts Gate 1 immediately
 > **Multi-Tool Support:**
 > - If using **Cursor**: Gate Workflow is enforced via `.cursorrules`.
 > - If using **Gemini CLI**: Rules are loaded from `GEMINI.md`.
-> - The AI will automatically detect if you are mid-task by reading `.claude/context/current.json`.
+> - The AI will automatically detect if you are mid-task by reading `.aiflow/context/current.json`.
 
 ### Step 3: GATE 1 — AI Analyzes Requirement
 
@@ -111,7 +111,7 @@ claude                        # AI auto-starts Gate 1 immediately
 
 When you open Claude, AI will **automatically** start analyzing:
 
-1. **Read ticket** from `.claude/context/current.json`
+1. **Read ticket** from `.aiflow/context/current.json`
 2. **Read source code** — understand architecture, related files, data flow
 3. **Ask clarifying questions** (one at a time) if anything is unclear
 4. **Output** `plan/PROJ-33/requirement.md` containing:

package/README.md

@@ -154,7 +154,7 @@ aiflow init --framework spring-boot,reactjs --adapter backlog,jira
 
 ### `aiflow use <ticket>`
 
-Load ticket context into `.claude/context/current.json`.
+Load ticket context into `.aiflow/context/current.json`.
 
 ```bash
 # Backlog

package/custom/skills/investigate-bug/SKILL.md

@@ -24,7 +24,7 @@ keywords: bug, fix, error, crash, broken
 
 ### 1. Read context from ticket (if available)
 
-Check `.claude/context/current.json`:
+Check `.aiflow/context/current.json`:
 - `description` — bug description from the ticket
 - `comments` — discussions, additional info
 - `context.files` — related files mentioned

package/custom/skills/validate-ticket/SKILL.md

@@ -16,7 +16,7 @@ keywords: ticket, validate, context, requirement, backlog, jira, analyze, unders
 
 ### Step 1: Load Ticket & Read Source Code
 
-1. Read `.claude/context/current.json` — ticket info from Backlog/Jira
+1. Read `.aiflow/context/current.json` — ticket info from Backlog/Jira
 2. Read `CLAUDE.md` — understand project architecture, tech stack, conventions
 3. Read related source files — trace data flow, identify patterns, dependencies
 4. Read ticket comments — additional context from PM/team

package/custom/templates/shared/gate-workflow.md

@@ -3,7 +3,7 @@
 > **Absolute Rule: Complete Gate N before entering Gate N+1.**
 > **Do not skip, shorten, or merge Gates.**
 
-You have superpowers. When a ticket context exists in `.claude/context/current.json`:
+You have superpowers. When a ticket context exists in `.aiflow/context/current.json`:
 - **AUTO-START Gate 1 immediately** — do NOT wait for the developer to ask.
 - Read instructions and follow the gate sequence below — NO EXCEPTIONS.
 
@@ -14,7 +14,7 @@ You have superpowers. When a ticket context exists in `.claude/context/current.j
 **INVOKE:** `validate-ticket` skill
 
 AI actively reads ticket + source code to understand the requirement:
-1. Read `.claude/context/current.json` — ticket info
+1. Read `.aiflow/context/current.json` — ticket info
 2. Read source code — architecture, related files, data flow
 3. If anything is unclear — ask ONE question at a time, wait for reply
 4. Output `plan/[ticket-id]/requirement.md` with:

package/custom/templates/tools/copilot.md

@@ -3,6 +3,6 @@
 You are an expert AI assistant specialized in this project's stack. Follow the Gate Workflow and Team Rules strictly.
 
 > [!IMPORTANT]
-> Always check for context in `.claude/context/current.json` and progress in the `plan/` folder before suggesting changes.
+> Always check for context in `.aiflow/context/current.json` and progress in the `plan/` folder before suggesting changes.
 
 If the Gate Workflow hasn't started, wait for the developer to type **"start"** or **"Gate 1"**.

package/custom/templates/tools/cursor.md

@@ -3,6 +3,6 @@
 You are an expert AI assistant specialized in this project's stack. Follow the Gate Workflow and Team Rules strictly.
 
 > [!IMPORTANT]
-> Always check `.claude/context/current.json` and the `plan/` directory before starting any task to understand current context and progress.
+> Always check `.aiflow/context/current.json` and the `plan/` directory before starting any task to understand current context and progress.
 
 If Gate 1 doesn't auto-start, wait for the developer to type **"start"**, **"Gate 1"** or **"Analyze ticket"**.

package/custom/templates/tools/gemini.md

@@ -3,6 +3,6 @@
 You are an expert AI assistant specialized in this project's stack. Follow the Gate Workflow and Team Rules strictly.
 
 > [!IMPORTANT]
-> When starting a session, always read `.claude/context/current.json` to load ticket context and check the `plan/` directory for existing progress.
+> When starting a session, always read `.aiflow/context/current.json` to load ticket context and check the `plan/` directory for existing progress.
 
 If no instructions are automatically followed, wait for the developer to type **"start"** or **"Gate 1"** to start the analysis.

package/custom/templates/tools/generic.md

@@ -3,7 +3,7 @@
 You are an expert AI assistant. Follow the project's Gate Workflow and Team Rules strictly.
 
 ## Context Awareness
-- **Ticket context**: `.claude/context/current.json`
+- **Ticket context**: `.aiflow/context/current.json`
 - **Task progress**: `plan/[ticket-id]/`
 - **Rules**: `.rules/`
 

package/docs/ai-integration.md

@@ -24,7 +24,7 @@ When you run `aiflow init`, it generates a `.cursorrules` file.
 
 ### 2. Gemini CLI
 Pass `GEMINI.md` as system instructions to your Gemini session.
-- **Tip**: Always ensure the AI reads `.claude/context/current.json` first to load the ticket context.
+- **Tip**: Always ensure the AI reads `.aiflow/context/current.json` first to load the ticket context.
 - Gemini is excellent for large context analysis during Gate 1.
 
 ### 3. GitHub Copilot / Codex
@@ -36,7 +36,7 @@ Copilot uses `.github/copilot-instructions.md` to guide its suggestions.
 ## Cross-Tool State Resumption
 The "Secret Sauce" of `ai-flow-kit` is its file-based state management:
 
-1. **Context**: Saved in `.claude/context/current.json`.
+1. **Context**: Saved in `.aiflow/context/current.json`.
 2. **Progress**: Saved as Markdown docs in `plan/[ticket-id]/`.
 3. **Rules**: Saved in `.rules/`.
 

package/docs/architecture.md

@@ -233,7 +233,7 @@ aiflow use JIRA-123
 [Load from MCP Adapter]
   - Fetch issue from Jira
   - Parse description, criteria
-  - Save to .claude/context/current.json
+  - Save to .aiflow/context/current.json
   ↓
 aiflow prompt bug-fix
   ↓

package/docs/cli-reference.md

@@ -80,7 +80,7 @@ aiflow use 1.0.0
 **What it does:**
 1. Fetches context from MCP adapter (if applicable)
 2. Parses and validates context
-3. Saves to `.claude/context/current.json`
+3. Saves to `.aiflow/context/current.json`
 4. Updates state tracking
 
 **Example:**
@@ -90,7 +90,7 @@ Fetching context from Jira...
 ✓ Title: Fix payment processing error
 ✓ Description: 2000+ words pulled
 ✓ Acceptance criteria: 3 items
-✓ Saved to .claude/context/current.json
+✓ Saved to .aiflow/context/current.json
 
 Ready to prompt! Run: aiflow prompt bug-fix
 ```

package/docs/troubleshooting.md

@@ -171,7 +171,7 @@ Options are overridden in this order:
 
 ```bash
 # Check context exists
-ls .claude/context/
+ls .aiflow/context/
 
 # If missing, reload context
 aiflow use JIRA-123  # Reload from ticket

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@relipa/ai-flow-kit",
-  "version": "0.0.4-beta.2",
+  "version": "0.0.4-beta.3",
   "description": "All-in-one AI Flow Kit for team development with Claude AI - skills, templates, and MCP adapters",
   "author": "Relipa AI Team",
   "publishConfig": {

package/scripts/hooks/session-start.js

@@ -14,7 +14,7 @@ const path = require('path');
 // Project root is 3 levels up
 const projectRoot = path.resolve(__dirname, '..', '..', '..');
 const skillPath = path.join(projectRoot, '.claude', 'skills', 'using-superpowers', 'SKILL.md');
-const contextPath = path.join(projectRoot, '.claude', 'context', 'current.json');
+const contextPath = path.join(projectRoot, '.aiflow', 'context', 'current.json');
 
 // ── 1. Load superpowers skill ──────────────────────────────────
 let skillContent = '';

package/scripts/prompt.js

@@ -3,7 +3,7 @@ const path = require('path');
 const chalk = require('chalk');
 
 const PROJECT_DIR  = process.cwd();
-const CURRENT_FILE = path.join(PROJECT_DIR, '.claude', 'context', 'current.json');
+const CURRENT_FILE = path.join(PROJECT_DIR, '.aiflow', 'context', 'current.json');
 const RULES_DIR    = path.join(PROJECT_DIR, '.rules');
 
 // Prompt templates per task type

package/scripts/use.js

@@ -7,7 +7,7 @@ const { select, input } = require('@inquirer/prompts');
 const PROJECT_DIR = process.cwd();
 const AIFLOW_DIR = path.join(PROJECT_DIR, '.aiflow');
 const STATE_FILE = path.join(AIFLOW_DIR, 'state.json');
-const CONTEXT_DIR = path.join(PROJECT_DIR, '.claude', 'context');
+const CONTEXT_DIR = path.join(PROJECT_DIR, '.aiflow', 'context');
 
 // ──────────────────────────────────────────────────────────────
 // Entry point