proagents 1.4.0 → 1.6.0

package/{proagents → .proagents}/AI_INSTRUCTIONS.md

@@ -9,32 +9,32 @@ This project uses ProAgents - an AI-agnostic development workflow framework.
 ### Before executing ANY `pa:` command:
 
 1. **Read fresh state from files** - Never rely on previous knowledge
-2. **Read project context** - Read `./proagents/context.md` for persistent project knowledge
-3. **Check the activity log** - Read `./proagents/activity.log` to see recent AI actions
+2. **Read project context** - Read `./.proagents/context.md` for persistent project knowledge
+3. **Check the activity log** - Read `./.proagents/activity.log` to see recent AI actions
 4. **Key files to check:**
-   - `./proagents/context.md` - Persistent project context (READ FIRST!)
-   - `./proagents/activity.log` - Recent AI activity
-   - `./proagents/watchlist.yaml` - Files requiring confirmation before changes
-   - `./proagents/proagents.config.yaml` - Project and platform config
-   - `./proagents/active-features/` - Active feature status
+   - `./.proagents/context.md` - Persistent project context (READ FIRST!)
+   - `./.proagents/activity.log` - Recent AI activity
+   - `./.proagents/watchlist.yaml` - Files requiring confirmation before changes
+   - `./.proagents/proagents.config.yaml` - Project and platform config
+   - `./.proagents/active-features/` - Active feature status
    - `./CHANGELOG.md` - Recent changes
-   - `./proagents/feedback.md` - Past corrections and preferences (LEARN FROM THESE!)
+   - `./.proagents/feedback.md` - Past corrections and preferences (LEARN FROM THESE!)
 
 ### AI Feedback & Learning
 
-Before starting work, check `./proagents/feedback.md` for:
+Before starting work, check `./.proagents/feedback.md` for:
 - **Corrections**: Mistakes other AIs made - don't repeat them!
 - **Preferences**: How the user/team prefers things done
 - **Patterns**: What worked well in this project
 
 When you receive feedback or correction from the user:
-1. Log it in `./proagents/feedback.md` using `pa:feedback`
+1. Log it in `./.proagents/feedback.md` using `pa:feedback`
 2. Apply the learning to your current work
 3. Avoid making the same mistake again
 
 ### File Watch List
 
-Before modifying ANY file, check `./proagents/watchlist.yaml`:
+Before modifying ANY file, check `./.proagents/watchlist.yaml`:
 
 - **critical**: Ask user for confirmation before modifying
 - **review_required**: Warn user and explain changes before modifying
@@ -48,7 +48,7 @@ If a file matches a pattern, inform the user:
 
 ### After completing ANY `pa:` command:
 
-**ALWAYS log your activity** to `./proagents/activity.log`:
+**ALWAYS log your activity** to `./.proagents/activity.log`:
 
 ```
 [TIMESTAMP] [AI_PLATFORM:MODEL] [COMMAND] Description
@@ -68,7 +68,7 @@ Keep log entries concise (one line). Other AIs will read this to understand rece
 
 ### Command History
 
-Also log commands to `./proagents/history.log` with their results:
+Also log commands to `./.proagents/history.log` with their results:
 
 ```
 [TIMESTAMP] [AI:MODEL] COMMAND → RESULT
@@ -86,7 +86,7 @@ This helps track what commands were run and their outcomes.
 
 ### Lock File for Active Work
 
-When starting a major task (feature, large fix, refactoring), create a lock file at `./proagents/.lock`:
+When starting a major task (feature, large fix, refactoring), create a lock file at `./.proagents/.lock`:
 
 ```yaml
 locked_by: Claude        # Your AI platform
@@ -101,12 +101,12 @@ expires: 2024-03-06T17:10:00  # Auto-expires after 2 hours
 ```
 
 **Before starting major work:**
-1. Check if `./proagents/.lock` exists
+1. Check if `./.proagents/.lock` exists
 2. If locked by another AI, inform user: "Project is locked by [AI] working on [task]. Wait or ask user to override."
 3. If lock is expired (past `expires` time), you may delete it and proceed
 
 **After completing work:**
-1. Delete the `./proagents/.lock` file
+1. Delete the `./.proagents/.lock` file
 2. Log completion in activity.log
 
 ### Conflict Detection
@@ -145,7 +145,7 @@ This helps other AIs detect conflicts.
 
 ### Handoff Notes
 
-When ending a session or switching to another AI, create handoff notes at `./proagents/handoff.md`:
+When ending a session or switching to another AI, create handoff notes at `./.proagents/handoff.md`:
 
 **For `pa:handoff`** - Create/update handoff notes:
 ```markdown
@@ -190,7 +190,7 @@ Updated: 2024-03-06 15:30 by Claude (opus-4)
 
 ### Session Summary
 
-**For `pa:session-end`** - Generate and save a session summary to `./proagents/sessions/`:
+**For `pa:session-end`** - Generate and save a session summary to `./.proagents/sessions/`:
 
 ```markdown
 # Session Summary
@@ -222,7 +222,7 @@ AI: Claude (opus-4)
 3. Write integration tests
 ```
 
-Save to: `./proagents/sessions/YYYY-MM-DD-HHMMSS.md`
+Save to: `./.proagents/sessions/YYYY-MM-DD-HHMMSS.md`
 
 ## Command Recognition
 
@@ -280,31 +280,31 @@ Run individual phases of the development workflow:
 **How to execute Workflow Phase commands:**
 
 For `pa:analyze`:
-1. Read `./proagents/prompts/01-analysis.md` for analysis workflow
+1. Read `./.proagents/prompts/01-analysis.md` for analysis workflow
 2. Scan project structure, dependencies, patterns
-3. Cache results in `./proagents/cache/`
+3. Cache results in `./.proagents/cache/`
 4. Output analysis report
 
 For `pa:requirements`:
-1. Read `./proagents/prompts/02-requirements.md`
-2. If feature name provided, create `./proagents/active-features/feature-{name}/requirements.md`
+1. Read `./.proagents/prompts/02-requirements.md`
+2. If feature name provided, create `./.proagents/active-features/feature-{name}/requirements.md`
 3. Gather user stories, acceptance criteria, constraints
 4. Output requirements document
 
 For `pa:design`:
-1. Read `./proagents/prompts/03-ui-design.md`
+1. Read `./.proagents/prompts/03-ui-design.md`
 2. Check for design inputs (Figma, sketches, exports)
 3. Create component specifications
 4. Output design document
 
 For `pa:plan`:
-1. Read `./proagents/prompts/04-planning.md`
+1. Read `./.proagents/prompts/04-planning.md`
 2. Create implementation plan with task breakdown
 3. Identify dependencies and risks
-4. Save to `./proagents/active-features/feature-{name}/implementation-plan.md`
+4. Save to `./.proagents/active-features/feature-{name}/implementation-plan.md`
 
 For `pa:implement`:
-1. Read `./proagents/prompts/05-implementation.md`
+1. Read `./.proagents/prompts/05-implementation.md`
 2. Follow existing project patterns
 3. Implement code changes
 4. Log progress to activity.log
@@ -349,15 +349,15 @@ For `pa:implement`:
 **How to execute Navigation commands:**
 
 For `pa:next`:
-1. Read `./proagents/active-features/*/status.json` to find current feature
+1. Read `./.proagents/active-features/*/status.json` to find current feature
 2. Identify current phase from status
 3. Show what the next step/phase is
 4. Provide guidance for the next action
 
 For `pa:resume`:
-1. Read `./proagents/active-features/` to find paused features
+1. Read `./.proagents/active-features/` to find paused features
 2. Read feature's `status.json` for last phase and progress
-3. Read `./proagents/handoff.md` for context
+3. Read `./.proagents/handoff.md` for context
 4. Continue from where it was left off
 
 For `pa:skip`:
@@ -374,7 +374,7 @@ For `pa:back`:
 4. Reload context from previous phase
 
 For `pa:progress`:
-1. Read `./proagents/active-features/*/status.json`
+1. Read `./.proagents/active-features/*/status.json`
 2. Calculate percentage complete (current_phase / total_phases)
 3. Display visual progress bar:
    ```
@@ -399,24 +399,24 @@ For `pa:progress`:
 **How to execute Context & History commands:**
 
 For `pa:context`:
-1. Read `./proagents/context.md`
+1. Read `./.proagents/context.md`
 2. Display current project context summary
 3. Show last updated timestamp
 
 For `pa:diff`:
-1. Read `./proagents/activity.log` for last session timestamp
+1. Read `./.proagents/activity.log` for last session timestamp
 2. Run `git diff` from that point
 3. Summarize changes by file/module
 4. Highlight significant changes
 
 For `pa:history`:
-1. Read `./proagents/history.log`
+1. Read `./.proagents/history.log`
 2. Show recent commands with their results
 3. Format: `[timestamp] command → result`
 
 For `pa:checkpoint`:
 1. Create git commit with message "checkpoint: [description]"
-2. Save checkpoint info to `./proagents/checkpoints.json`:
+2. Save checkpoint info to `./.proagents/checkpoints.json`:
    ```json
    {
      "checkpoints": [
@@ -434,7 +434,7 @@ For `pa:checkpoint`:
 3. Log to activity.log
 
 For `pa:undo`:
-1. Read last action from `./proagents/activity.log`
+1. Read last action from `./.proagents/activity.log`
 2. If file changes, run `git checkout` to revert
 3. If multiple files, offer selective undo
 4. Update activity.log with undo entry
@@ -452,7 +452,7 @@ For `pa:undo`:
 **How to execute Sprint commands:**
 
 For `pa:sprint-start`:
-1. Create `./proagents/sprints/sprint-{number}.json`:
+1. Create `./.proagents/sprints/sprint-{number}.json`:
    ```json
    {
      "sprint_number": 1,
@@ -469,7 +469,7 @@ For `pa:sprint-start`:
 For `pa:sprint-end`:
 1. Read current sprint file
 2. Calculate metrics (completed features, velocity)
-3. Generate sprint summary → `./proagents/sprints/sprint-{n}-summary.md`
+3. Generate sprint summary → `./.proagents/sprints/sprint-{n}-summary.md`
 4. Archive sprint
 
 For `pa:estimate`:
@@ -479,7 +479,7 @@ For `pa:estimate`:
 4. Save estimate to feature status.json
 
 For `pa:velocity`:
-1. Read completed sprints from `./proagents/sprints/`
+1. Read completed sprints from `./.proagents/sprints/`
 2. Calculate average story points per sprint
 3. Show velocity chart/trend
 
@@ -539,7 +539,7 @@ For `pa:metrics`:
    - Cyclomatic complexity
    - Code duplication
    - Function/file sizes
-2. Save to `./proagents/metrics/latest.json`
+2. Save to `./.proagents/metrics/latest.json`
 3. Display summary with warnings for issues
 
 For `pa:coverage`:
@@ -585,8 +585,8 @@ For `pa:deps-security`:
 **How to execute Code Generation commands:**
 
 For `pa:generate-component`:
-1. Read project type and patterns from `./proagents/cache/patterns.json`
-2. Use template from `./proagents/scaffolding/` matching project type
+1. Read project type and patterns from `./.proagents/cache/patterns.json`
+2. Use template from `./.proagents/scaffolding/` matching project type
 3. Apply project naming conventions
 4. Create component file with:
    - Component code
@@ -666,7 +666,7 @@ For `pa:cleanup`:
 **How to execute Time Tracking commands:**
 
 For `pa:time-start`:
-1. Create/update `./proagents/time-tracking.json`:
+1. Create/update `./.proagents/time-tracking.json`:
    ```json
    {
      "current": {
@@ -862,8 +862,8 @@ For `pa:import`:
 4. Report what was imported
 
 For `pa:backup`:
-1. Create timestamped backup of entire proagents/ folder
-2. Save to `./proagents/backups/` or specified location
+1. Create timestamped backup of entire .proagents/ folder
+2. Save to `./.proagents/backups/` or specified location
 3. Compress if large
 4. Maintain rolling backups (keep last N)
 
@@ -880,7 +880,7 @@ For `pa:backup`:
 
 For `pa:learn`:
 1. Parse the pattern description
-2. Add to `./proagents/.learning/`:
+2. Add to `./.proagents/.learning/`:
    ```json
    {
      "pattern": "Always use React Query for API calls",
@@ -1975,6 +1975,435 @@ For `pa:alias-add`:
    Runs: pa:test && pa:build && pa:deploy
    ```
 
+### Mobile Test Suite (React Native / Mobile Apps)
+| Command | Action |
+|---------|--------|
+| `pa:test-mobile` | Run full mobile test suite |
+| `pa:test-mobile "feature"` | Test specific feature |
+| `pa:test-visual` | Visual/design comparison testing |
+| `pa:test-auto-fix` | Auto-fix failing tests |
+| `pa:test-loop` | Test → Fix → Retest loop until success |
+| `pa:compare-figma` | Compare UI against Figma design |
+| `pa:compare-image "path"` | Compare UI against image/sketch |
+| `pa:screenshot` | Take app screenshots for comparison |
+
+**How to execute Mobile Test Suite commands:**
+
+For `pa:test-mobile`:
+1. Run comprehensive mobile test suite:
+   ```
+   Mobile Test Suite
+   ═════════════════
+
+   Running full test suite for: feature/user-auth
+
+   Phase 1: Unit Tests
+   ───────────────────
+   ✓ AuthService.login() - 5 tests passed
+   ✓ AuthService.logout() - 3 tests passed
+   ✓ TokenManager - 8 tests passed
+   ✓ UserStore - 12 tests passed
+
+   Phase 2: Component Tests
+   ────────────────────────
+   ✓ LoginScreen - renders correctly
+   ✓ LoginScreen - validates email format
+   ✓ LoginScreen - shows error on invalid credentials
+   ✓ SignupScreen - all fields required
+   ✓ ProfileScreen - displays user data
+
+   Phase 3: Integration Tests
+   ──────────────────────────
+   ✓ Login flow end-to-end
+   ✓ Token refresh on expiry
+   ✓ Logout clears all data
+   ✗ FAILED: Password reset flow
+     → Error: Reset email not sent
+
+   Phase 4: E2E Tests (Maestro/Detox)
+   ──────────────────────────────────
+   ✓ User can login with valid credentials
+   ✓ User sees error with invalid password
+   ✗ FAILED: User can reset password
+     → Button not found: "Send Reset Email"
+
+   Phase 5: Visual Tests
+   ─────────────────────
+   ✓ LoginScreen matches design
+   ✗ FAILED: SignupScreen has visual differences
+     → Button color: expected #007AFF, got #0066CC
+     → Font size: expected 16px, got 14px
+
+   ══════════════════════════════════════════
+   RESULTS: 35/38 tests passed (3 failed)
+   ══════════════════════════════════════════
+
+   Failed Tests:
+   1. Integration: Password reset flow
+   2. E2E: User can reset password
+   3. Visual: SignupScreen design mismatch
+
+   Run `pa:test-auto-fix` to automatically fix these issues.
+   ```
+
+2. Generate detailed test report at `./.proagents/test-reports/mobile-{timestamp}.md`
+
+For `pa:test-visual`:
+1. Take screenshots of all screens/components
+2. Compare against design references:
+   ```
+   Visual Design Testing
+   ═════════════════════
+
+   Comparing app UI against design references...
+
+   Design Source: ./designs/ (Figma exports)
+
+   Screen: LoginScreen
+   ───────────────────
+   ✓ Layout matches design
+   ✓ Colors match design tokens
+   ✓ Typography correct
+   ✓ Spacing/padding correct
+   ✓ Button styles match
+
+   Screen: SignupScreen
+   ────────────────────
+   ✗ MISMATCH DETECTED
+
+   Differences found:
+   ┌─────────────────┬──────────────┬──────────────┐
+   │ Element         │ Expected     │ Actual       │
+   ├─────────────────┼──────────────┼──────────────┤
+   │ Submit Button   │ #007AFF      │ #0066CC      │
+   │ Title Font      │ 24px Bold    │ 22px Regular │
+   │ Input Height    │ 48px         │ 44px         │
+   │ Bottom Margin   │ 16px         │ 12px         │
+   └─────────────────┴──────────────┴──────────────┘
+
+   Screenshot saved: ./.proagents/test-reports/visual/signup-diff.png
+
+   Screen: ProfileScreen
+   ─────────────────────
+   ✓ All elements match design
+
+   ══════════════════════════════════════════
+   VISUAL TEST RESULTS: 2/3 screens passed
+   ══════════════════════════════════════════
+
+   Run `pa:test-auto-fix` to fix visual issues automatically.
+   ```
+
+For `pa:test-auto-fix`:
+1. Analyze failing tests
+2. Identify root cause
+3. Generate and apply fixes:
+   ```
+   Auto-Fix Mode
+   ═════════════
+
+   Analyzing 3 failing tests...
+
+   Fix 1: Password reset flow
+   ──────────────────────────
+   Root Cause: API endpoint missing in AuthService
+
+   Applying fix to: src/services/AuthService.ts
+   + async resetPassword(email: string): Promise<void> {
+   +   const response = await api.post('/auth/reset-password', { email });
+   +   if (!response.ok) throw new Error('Reset failed');
+   + }
+
+   ✓ Fix applied
+
+   Fix 2: Reset button not found
+   ─────────────────────────────
+   Root Cause: Button testID missing
+
+   Applying fix to: src/screens/ResetPasswordScreen.tsx
+   - <Button title="Send Reset Email" onPress={handleReset} />
+   + <Button
+   +   testID="send-reset-email-button"
+   +   title="Send Reset Email"
+   +   onPress={handleReset}
+   + />
+
+   ✓ Fix applied
+
+   Fix 3: SignupScreen visual mismatch
+   ────────────────────────────────────
+   Root Cause: Style values don't match design tokens
+
+   Applying fix to: src/screens/SignupScreen.styles.ts
+   - submitButton: { backgroundColor: '#0066CC' }
+   + submitButton: { backgroundColor: '#007AFF' }
+
+   - title: { fontSize: 22, fontWeight: 'normal' }
+   + title: { fontSize: 24, fontWeight: 'bold' }
+
+   - input: { height: 44, marginBottom: 12 }
+   + input: { height: 48, marginBottom: 16 }
+
+   ✓ Fix applied
+
+   ══════════════════════════════════════════
+   AUTO-FIX COMPLETE: 3/3 issues fixed
+   ══════════════════════════════════════════
+
+   Running verification tests...
+   ```
+
+For `pa:test-loop`:
+1. Run complete Test → Fix → Retest cycle:
+   ```
+   Test Loop Mode
+   ══════════════
+
+   Starting automated test-fix-retest cycle...
+   Max iterations: 5
+
+   ┌─────────────────────────────────────────────────────┐
+   │ ITERATION 1                                         │
+   ├─────────────────────────────────────────────────────┤
+   │ Running tests...                                    │
+   │ Results: 35/38 passed (3 failed)                   │
+   │                                                     │
+   │ Analyzing failures...                               │
+   │ Applying auto-fixes...                              │
+   │ Fixes applied: 3                                    │
+   └─────────────────────────────────────────────────────┘
+
+   ┌─────────────────────────────────────────────────────┐
+   │ ITERATION 2                                         │
+   ├─────────────────────────────────────────────────────┤
+   │ Running tests...                                    │
+   │ Results: 37/38 passed (1 failed)                   │
+   │                                                     │
+   │ Analyzing failures...                               │
+   │ New issue: TypeScript type error after fix         │
+   │ Applying auto-fixes...                              │
+   │ Fixes applied: 1                                    │
+   └─────────────────────────────────────────────────────┘
+
+   ┌─────────────────────────────────────────────────────┐
+   │ ITERATION 3                                         │
+   ├─────────────────────────────────────────────────────┤
+   │ Running tests...                                    │
+   │ Results: 38/38 passed (0 failed)                   │
+   │                                                     │
+   │ ✓ ALL TESTS PASSING!                               │
+   └─────────────────────────────────────────────────────┘
+
+   ══════════════════════════════════════════════════════
+   TEST LOOP COMPLETE
+   ══════════════════════════════════════════════════════
+
+   Summary:
+   ────────
+   Iterations: 3
+   Initial failures: 3
+   Fixes applied: 4
+   Final status: ALL PASSING ✓
+
+   Files modified:
+   • src/services/AuthService.ts
+   • src/screens/ResetPasswordScreen.tsx
+   • src/screens/SignupScreen.styles.ts
+   • src/types/auth.ts
+
+   Test report: ./.proagents/test-reports/test-loop-{timestamp}.md
+
+   Ready for commit? (y/n)
+   ```
+
+For `pa:compare-figma`:
+1. Connect to Figma API or use exported frames
+2. Extract design specifications
+3. Compare with actual app:
+   ```
+   Figma Design Comparison
+   ═══════════════════════
+
+   Design Source: [Figma Link or ./designs/figma-export/]
+
+   Extracting design tokens from Figma...
+   ✓ Colors extracted
+   ✓ Typography extracted
+   ✓ Spacing system extracted
+   ✓ Component specs extracted
+
+   Comparing: LoginScreen
+   ──────────────────────
+
+   Layout Comparison:
+   ┌────────────────────┬────────────────────┐
+   │   Figma Design     │   App Screenshot   │
+   │   ┌──────────┐     │   ┌──────────┐     │
+   │   │  Logo    │     │   │  Logo    │ ✓   │
+   │   ├──────────┤     │   ├──────────┤     │
+   │   │  Email   │     │   │  Email   │ ✓   │
+   │   │  Input   │     │   │  Input   │     │
+   │   ├──────────┤     │   ├──────────┤     │
+   │   │ Password │     │   │ Password │ ✓   │
+   │   │  Input   │     │   │  Input   │     │
+   │   ├──────────┤     │   ├──────────┤     │
+   │   │  Login   │     │   │  Login   │ ✗   │
+   │   │  Button  │     │   │  Button  │     │
+   │   └──────────┘     │   └──────────┘     │
+   └────────────────────┴────────────────────┘
+
+   Detailed Comparison:
+   ┌───────────────┬─────────────┬─────────────┬────────┐
+   │ Element       │ Figma       │ App         │ Status │
+   ├───────────────┼─────────────┼─────────────┼────────┤
+   │ Logo Size     │ 120x40      │ 120x40      │ ✓      │
+   │ Input Height  │ 48px        │ 48px        │ ✓      │
+   │ Input Border  │ 1px #E0E0E0 │ 1px #E0E0E0 │ ✓      │
+   │ Button Color  │ #007AFF     │ #0056B3     │ ✗      │
+   │ Button Radius │ 8px         │ 4px         │ ✗      │
+   │ Button Height │ 52px        │ 48px        │ ✗      │
+   │ Vertical Gap  │ 16px        │ 12px        │ ✗      │
+   └───────────────┴─────────────┴─────────────┴────────┘
+
+   Issues Found: 4
+
+   Auto-fix available? Yes
+   Run `pa:test-auto-fix` to apply design corrections.
+   ```
+
+For `pa:compare-image "path"`:
+1. Load reference image (sketch, screenshot, mockup)
+2. Use visual comparison:
+   ```
+   Image Comparison
+   ════════════════
+
+   Reference: ./designs/sketch-login.png
+   App Screen: LoginScreen
+
+   Analyzing reference image...
+   ✓ Detected UI elements
+   ✓ Extracted layout structure
+   ✓ Identified colors and typography
+
+   Taking app screenshot...
+   ✓ Screenshot captured
+
+   Visual Diff Analysis:
+   ─────────────────────
+
+   Overall Match: 87%
+
+   Differences Detected:
+
+   1. Header Section (Region: 0,0 to 375,100)
+      • Logo position: slightly lower than reference
+      • Background: matches ✓
+
+   2. Form Section (Region: 0,100 to 375,350)
+      • Input fields: match ✓
+      • Labels: font slightly smaller
+      • Spacing: compressed by ~4px
+
+   3. Button Section (Region: 0,350 to 375,450)
+      • Color: differs by 15% (darker in app)
+      • Corner radius: sharper in app
+      • Shadow: missing in app
+
+   Diff image saved: ./.proagents/test-reports/visual/login-diff-overlay.png
+
+   ┌─────────────────────────────────────────────┐
+   │ [Reference]        │ [App]        │ [Diff] │
+   │ Expected design    │ Actual app   │ Δ      │
+   └─────────────────────────────────────────────┘
+
+   Suggested fixes generated.
+   Run `pa:test-auto-fix` to apply.
+   ```
+
+For `pa:screenshot`:
+1. Capture screenshots of all app screens:
+   ```
+   Screenshot Capture
+   ══════════════════
+
+   Detecting available screens...
+
+   Found 12 screens in navigation:
+
+   Capturing screenshots...
+
+   ✓ LoginScreen → ./.proagents/screenshots/LoginScreen.png
+   ✓ SignupScreen → ./.proagents/screenshots/SignupScreen.png
+   ✓ HomeScreen → ./.proagents/screenshots/HomeScreen.png
+   ✓ ProfileScreen → ./.proagents/screenshots/ProfileScreen.png
+   ✓ SettingsScreen → ./.proagents/screenshots/SettingsScreen.png
+   ✓ NotificationsScreen → ./.proagents/screenshots/NotificationsScreen.png
+   ... (6 more)
+
+   Component screenshots:
+   ✓ Button variants → ./.proagents/screenshots/components/Button.png
+   ✓ Input variants → ./.proagents/screenshots/components/Input.png
+   ✓ Card variants → ./.proagents/screenshots/components/Card.png
+
+   ══════════════════════════════════════════
+   Screenshots saved: 15 images
+   Location: ./.proagents/screenshots/
+   ══════════════════════════════════════════
+
+   Use these for:
+   • Visual regression testing
+   • Design comparison with `pa:compare-image`
+   • Documentation
+   ```
+
+**Mobile Test Configuration:**
+Add to `proagents.config.yaml`:
+```yaml
+mobile_testing:
+  platform: react-native  # or flutter, native
+
+  test_frameworks:
+    unit: jest
+    component: "@testing-library/react-native"
+    e2e: maestro  # or detox, appium
+
+  visual_testing:
+    enabled: true
+    design_source: figma  # or ./designs/
+    figma_file_id: "your-figma-file-id"  # if using Figma
+    threshold: 0.95  # 95% match required
+
+  auto_fix:
+    enabled: true
+    max_iterations: 5
+    require_approval: false  # true = ask before applying fixes
+
+  screenshot:
+    output_dir: ./.proagents/screenshots
+    devices:
+      - iPhone 14 Pro
+      - Pixel 7
+
+  test_on:
+    feature_complete: true  # auto-run tests when feature done
+    bug_fix: true  # auto-run tests after bug fix
+    pre_commit: false  # run before git commit
+```
+
+**Test Report Structure:**
+```
+./.proagents/test-reports/
+├── mobile-2024-03-06-1500.md      # Full test report
+├── visual/
+│   ├── LoginScreen-diff.png       # Visual diff images
+│   ├── SignupScreen-diff.png
+│   └── comparison-report.md
+├── coverage/
+│   └── coverage-report.html       # Test coverage
+└── auto-fix-log.md                # Log of all auto-fixes
+```
+
 ### AI Platform Management
 | Command | Action |
 |---------|--------|
@@ -1986,7 +2415,7 @@ For `pa:alias-add`:
 **How to execute AI Platform commands:**
 
 For `pa:ai-list`:
-- Read `./proagents/proagents.config.yaml` and show the `platforms` array
+- Read `./.proagents/proagents.config.yaml` and show the `platforms` array
 - Show which AI instruction files exist in project root
 
 For `pa:ai-add`:
@@ -2008,7 +2437,7 @@ For `pa:ai-add`:
 
 2. Ask user which platforms to add
 3. For each selected platform:
-   - Copy content from `./proagents/{PLATFORM}.md` (e.g., `./proagents/CLAUDE.md`)
+   - Copy content from `./.proagents/{PLATFORM}.md` (e.g., `./.proagents/CLAUDE.md`)
    - If target file exists, wrap new content with markers and append:
      ```
      <!-- PROAGENTS:START -->
@@ -2016,10 +2445,10 @@ For `pa:ai-add`:
      <!-- PROAGENTS:END -->
      ```
    - If target file doesn't exist, create it with the content wrapped in markers
-4. Update `./proagents/proagents.config.yaml` to add platform to `platforms` array
+4. Update `./.proagents/proagents.config.yaml` to add platform to `platforms` array
 
 For `pa:ai-remove`:
-1. Read `./proagents/proagents.config.yaml` to get current platforms
+1. Read `./.proagents/proagents.config.yaml` to get current platforms
 2. Show list and ask which to remove
 3. For each selected:
    - Remove the PROAGENTS section (between markers) from the file, OR delete the file if it only contains ProAgents content
@@ -2027,7 +2456,7 @@ For `pa:ai-remove`:
 
 For `pa:ai-sync`:
 1. Scan project root for AI instruction files
-2. Read current config from `./proagents/proagents.config.yaml`
+2. Read current config from `./.proagents/proagents.config.yaml`
 3. Compare and show differences:
    - Files that exist but not in config
    - Config entries that don't have matching files
@@ -2063,7 +2492,7 @@ For `pa:ai-sync`:
 
 ### Custom Commands
 
-Check `./proagents/custom-commands.yaml` for project-specific commands.
+Check `./.proagents/custom-commands.yaml` for project-specific commands.
 
 Built-in custom commands:
 | Command | Action |
@@ -2102,26 +2531,26 @@ Users can add their own commands in `custom-commands.yaml`.
 
 When user types a `pa:` command:
 
-1. **Read the corresponding prompt file** from `./proagents/prompts/`
+1. **Read the corresponding prompt file** from `./.proagents/prompts/`
 2. **Follow the workflow** defined in that prompt
-3. **Use project context** from `./proagents/` folder
+3. **Use project context** from `./.proagents/` folder
 
 ### Prompt File Mapping
-- `pa:feature` → `./proagents/prompts/00-init.md` + workflow
-- `pa:fix` → `./proagents/workflow-modes/entry-modes.md` (Bug Fix section)
-- `pa:doc*` → `./proagents/prompts/07-documentation.md`
-- `pa:qa` → `./proagents/checklists/code-quality.md`
-- `pa:test` → `./proagents/prompts/06-testing.md`
-- `pa:deploy` → `./proagents/prompts/08-deployment.md`
-- `pa:release` → `./proagents/prompts/07-documentation.md` (Release Notes section)
+- `pa:feature` → `./.proagents/prompts/00-init.md` + workflow
+- `pa:fix` → `./.proagents/workflow-modes/entry-modes.md` (Bug Fix section)
+- `pa:doc*` → `./.proagents/prompts/07-documentation.md`
+- `pa:qa` → `./.proagents/checklists/code-quality.md`
+- `pa:test` → `./.proagents/prompts/06-testing.md`
+- `pa:deploy` → `./.proagents/prompts/08-deployment.md`
+- `pa:release` → `./.proagents/prompts/07-documentation.md` (Release Notes section)
 
 ## Workflow Reference
 
-Full workflow documentation: `./proagents/WORKFLOW.md`
-Quick command reference: `./proagents/PROAGENTS.md`
+Full workflow documentation: `./.proagents/WORKFLOW.md`
+Quick command reference: `./.proagents/PROAGENTS.md`
 
 ## Important
 
-- Always check `./proagents/` folder for project-specific configurations
+- Always check `./.proagents/` folder for project-specific configurations
 - Preserve user's `proagents.config.yaml` settings
 - Follow existing code patterns found in the project