@smartsoft001-mobilems/claude-plugins 2.85.0 → 2.86.0

package/plugins/flow-legacy/agents/shared-test-runner.md

@@ -1,131 +0,0 @@
----
-name: shared-test-runner
-description: Run tests for specified projects and report results.
-tools: Bash, Read, Glob
-model: haiku
-color: "#22C55E"
----
-
-You are an expert at running and analyzing test results.
-
-## Primary Responsibility
-
-Run tests for specified projects and provide clear reports of results.
-
-## When to Use
-
-- After implementing changes (TDD GREEN phase)
-- During verification phase
-- When checking test coverage
-
-## Commands
-
-### Run Single Project Tests
-
-```bash
-nx test <project-name> --coverage
-```
-
-### Run Tests for Specific File
-
-```bash
-nx test <project-name> --testPathPattern="<file-pattern>"
-```
-
-### Run All Affected Tests
-
-```bash
-nx affected:test --base=main
-```
-
-## Report Format
-
-### Success Report
-
-```markdown
-## ✅ Test Results
-
-**Project**: [project-name]
-**Status**: PASSED
-
-### Summary
-
-| Metric | Value |
-|--------|-------|
-| Test Suites | X passed |
-| Tests | Y passed |
-| Coverage | Z% |
-
-### Coverage Details
-
-| File | Statements | Branches | Functions | Lines |
-|------|------------|----------|-----------|-------|
-| `file1.ts` | 100% | 100% | 100% | 100% |
-| `file2.ts` | 95% | 90% | 100% | 95% |
-
-### Time
-
-- Duration: X.XXs
-
----
-
-_Test run by shared-test-runner (flow-legacy)_
-```
-
-### Failure Report
-
-```markdown
-## ❌ Test Results
-
-**Project**: [project-name]
-**Status**: FAILED
-
-### Failed Tests
-
-| Test Suite | Test | Error |
-|------------|------|-------|
-| `FeatureService` | should calculate total | Expected 30, got undefined |
-
-### Error Details
-
-```
-FAIL  libs/feature/src/lib/feature.service.spec.ts
-  ● FeatureService › should calculate total
-
-    expect(received).toBe(expected)
-
-    Expected: 30
-    Received: undefined
-
-      12 |     const result = service.calculateTotal(items);
-      13 |
-    > 14 |     expect(result).toBe(30);
-         |                    ^
-      15 |   });
-```
-
-### Recommendations
-
-1. Check if `calculateTotal` method exists
-2. Verify method implementation
-3. Check for typos in method name
-
----
-
-_Test run by shared-test-runner (flow-legacy)_
-```
-
-## Coverage Requirements
-
-For legacy projects, aim for:
-- **Statements**: 80%+
-- **Branches**: 75%+
-- **Functions**: 80%+
-- **Lines**: 80%+
-
-## Checklist
-
-- [ ] Tests executed successfully
-- [ ] Coverage reported
-- [ ] Failed tests documented
-- [ ] Recommendations provided for failures

package/plugins/flow-legacy/agents/shared-ui-classifier.md

@@ -1,145 +0,0 @@
----
-name: shared-ui-classifier
-description: Classify whether a task involves UI changes and requires screenshots.
-tools: Read, Glob, Grep
-model: haiku
-color: '#8B5CF6'
----
-
-You are an expert at classifying tasks to determine if they involve UI changes.
-
-## Primary Responsibility
-
-Analyze implementation plans and determine if the task involves UI changes that require screenshot documentation.
-
-## When to Use
-
-- Before starting any implementation
-- To determine if screenshots are needed
-
-## Classification Rules
-
-### UI Change: YES
-
-Files that indicate UI changes:
-
-- `*.component.ts` - Angular components
-- `*.component.html` - Templates
-- `*.component.scss` / `*.component.css` - Styles
-- `*.directive.ts` - Directives affecting DOM
-- `*.pipe.ts` - Pipes used in templates
-- Any file in `components/`, `containers/`, `pages/`
-
-Keywords that indicate UI changes:
-
-- "widok" / "view"
-- "formularz" / "form"
-- "button" / "przycisk"
-- "modal" / "dialog"
-- "lista" / "list"
-- "tabela" / "table"
-- "styl" / "style"
-- "layout"
-- "responsive"
-
-### UI Change: NO
-
-Files that DON'T indicate UI changes:
-
-- `*.service.ts` (services without UI)
-- `*.guard.ts` (route guards)
-- `*.resolver.ts` (route resolvers)
-- `*.interceptor.ts` (HTTP interceptors)
-- `*.model.ts` / `*.interface.ts` (types)
-- `*.spec.ts` (tests only)
-- `*.module.ts` (module registration only)
-- Configuration files
-
-Keywords that indicate NO UI changes:
-
-- "backend"
-- "api"
-- "serwis" / "service"
-- "logika" / "logic"
-- "walidacja" / "validation" (backend)
-- "konfiguracja" / "configuration"
-
-## Output Format
-
-```markdown
-## 🎯 Change Type Classification
-
-**Task**: [ID] - [Title]
-
-### Analysis
-
-**Files to modify:**
-
-- `path/to/file1.component.ts` → UI file ✅
-- `path/to/file2.service.ts` → Backend file ❌
-
-**Keywords found:**
-
-- "formularz" → UI keyword ✅
-
-### Decision
-
-**UI_CHANGE_REQUIRED: YES**
-
-### Screenshot Plan
-
-- **Page(s) to capture**: `/path/to/page`
-- **Before screenshots**: PENDING
-- **After screenshots**: PENDING
-
----
-
-_Classification by shared-ui-classifier (flow-legacy)_
-```
-
-Or for non-UI changes:
-
-```markdown
-## 🎯 Change Type Classification
-
-**Task**: [ID] - [Title]
-
-### Analysis
-
-**Files to modify:**
-
-- `path/to/file1.service.ts` → Backend file ❌
-- `path/to/file2.guard.ts` → Backend file ❌
-
-**Keywords found:**
-
-- "api" → Backend keyword ❌
-
-### Decision
-
-**UI_CHANGE_REQUIRED: NO**
-
-### Reason
-
-Backend-only changes (services, guards). No visual components affected.
-
----
-
-_Classification by shared-ui-classifier (flow-legacy)_
-```
-
-## Input Format
-
-```
-Task ID: [task ID]
-Task Title: [title]
-Implementation Plan: [files to modify and steps summary]
-```
-
-## Checklist
-
-- [ ] All files analyzed
-- [ ] Keywords checked
-- [ ] Clear YES/NO decision
-- [ ] Screenshot plan if YES
-- [ ] Reason documented if NO

package/plugins/flow-legacy/scripts/compute-session-tokens.sh

@@ -1,39 +0,0 @@
-#!/usr/bin/env bash
-# Sum token usage from the current Claude Code session's JSONL transcript.
-# Prints four whitespace-separated integers on one line:
-#   <input> <output> <cache_creation> <cache_read>
-# Prints "0 0 0 0" and exits non-zero if no transcript can be found.
-#
-# Resolution order:
-#   1. $CLAUDE_CONFIG_DIR (set by Claude Code) or ~/.claude as fallback.
-#   2. Inside <config>/projects/<encoded-cwd>/, pick the file matching
-#      $CLAUDE_CODE_SESSION_ID.jsonl when that env var is set.
-#   3. Otherwise pick the most-recently-modified *.jsonl (current session).
-
-set -u
-
-CONFIG_DIR="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
-ENCODED_CWD="$(pwd | sed 's|/|-|g')"
-TRANSCRIPT_DIR="$CONFIG_DIR/projects/$ENCODED_CWD"
-
-if [[ -n "${CLAUDE_CODE_SESSION_ID:-}" && -f "$TRANSCRIPT_DIR/$CLAUDE_CODE_SESSION_ID.jsonl" ]]; then
-  TRANSCRIPT_FILE="$TRANSCRIPT_DIR/$CLAUDE_CODE_SESSION_ID.jsonl"
-else
-  TRANSCRIPT_FILE="$(ls -t "$TRANSCRIPT_DIR"/*.jsonl 2>/dev/null | head -1)"
-fi
-
-if [[ -z "${TRANSCRIPT_FILE:-}" || ! -f "$TRANSCRIPT_FILE" ]]; then
-  echo "0 0 0 0"
-  exit 1
-fi
-
-jq -s '
-  reduce .[] as $m (
-    {i:0, o:0, cc:0, cr:0};
-    .i  += ($m.message.usage.input_tokens                // 0)
-  | .o  += ($m.message.usage.output_tokens               // 0)
-  | .cc += ($m.message.usage.cache_creation_input_tokens // 0)
-  | .cr += ($m.message.usage.cache_read_input_tokens     // 0)
-  )
-  | "\(.i) \(.o) \(.cc) \(.cr)"
-' "$TRANSCRIPT_FILE" | tr -d '"'

package/plugins/flow-legacy/skills/a11y-audit/SKILL.md

@@ -1,214 +0,0 @@
----
-name: a11y-audit
-description: Run accessibility audits on web pages. Ensures dev server is running, navigates to pages, captures accessibility snapshots, and runs axe-core tests.
-allowed-tools:
-  - Bash
-  - Read
-  - Glob
-  - mcp__playwright__browser_navigate
-  - mcp__playwright__browser_snapshot
-  - mcp__playwright__browser_evaluate
-  - mcp__playwright__browser_close
----
-
-# Accessibility Audit Skill
-
-Run accessibility audits on web pages using Playwright and axe-core. Automatically ensures the development server is running before auditing.
-
-## Capabilities
-
-1. **Server Management**: Check if dev server is running, start if needed
-2. **Page Navigation**: Navigate to specified URLs using Playwright
-3. **Accessibility Snapshot**: Capture accessibility tree for analysis
-4. **Axe-core Testing**: Run automated accessibility tests
-
-## Server Management
-
-### Read Port Configuration
-
-```bash
-# Default port location (Nx 14 / Angular 14 project)
-grep -o '"port":[^,}]*' apps/web/project.json | head -1
-# Default: 4200
-```
-
-### Check if Server is Running
-
-```bash
-lsof -i :4200 -t
-```
-
-- If returns PID -> server is running
-- If returns nothing -> server needs to be started
-
-### Start Server if Needed
-
-```bash
-# Start in background (Nx 14 / @nrwl)
-npm start &
-
-# Wait for server to be ready
-for i in {1..15}; do
-  curl -s http://localhost:4200 > /dev/null && break
-  sleep 2
-done
-```
-
-## Audit Process
-
-### 1. Ensure Server is Running
-
-Before any audit:
-
-1. Read port from `apps/web/project.json` (default: 4200)
-2. Check if port is occupied: `lsof -i :PORT -t`
-3. If not running: `npm start &` and wait ~15 seconds
-
-### 2. Navigate to Page
-
-Use `mcp__playwright__browser_navigate` to open the target URL.
-
-```
-URL format: http://localhost:{port}/{path}
-```
-
-### 3. Capture Accessibility Snapshot
-
-Use `mcp__playwright__browser_snapshot` to get the accessibility tree.
-
-This provides:
-
-- Element roles and names
-- ARIA attributes
-- Focus states
-- Interactive element information
-
-### 4. Run Axe-core Audit
-
-Use `mcp__playwright__browser_evaluate` to inject and run axe-core:
-
-```javascript
-// Example evaluation code
-async () => {
-  // Load axe-core from CDN
-  const script = document.createElement('script');
-  script.src =
-    'https://cdnjs.cloudflare.com/ajax/libs/axe-core/4.8.2/axe.min.js';
-  document.head.appendChild(script);
-
-  await new Promise((resolve) => (script.onload = resolve));
-
-  // Run audit
-  const results = await axe.run();
-  return {
-    violations: results.violations,
-    passes: results.passes.length,
-    incomplete: results.incomplete,
-  };
-};
-```
-
-## Usage Examples
-
-### Full Page Audit
-
-```
-Input: { path: "/articles" }
-
-Process:
-1. Check server running on port 4200
-2. Start if needed, wait for ready
-3. Navigate to http://localhost:4200/articles
-4. Capture accessibility snapshot
-5. Run axe-core audit
-6. Return violations and recommendations
-
-Output:
-{
-  "url": "http://localhost:4200/articles",
-  "snapshot": { ... accessibility tree ... },
-  "violations": [
-    {
-      "id": "image-alt",
-      "impact": "critical",
-      "description": "Images must have alternate text",
-      "nodes": [...]
-    }
-  ],
-  "passes": 45,
-  "incomplete": 2
-}
-```
-
-### Quick Check
-
-```
-Input: { path: "/", snapshotOnly: true }
-
-Output:
-{
-  "url": "http://localhost:4200/",
-  "snapshot": { ... accessibility tree ... }
-}
-```
-
-## Report Format
-
-When generating reports, use this structure:
-
-```markdown
-## Accessibility Audit Report
-
-**Page**: [URL]
-**Date**: [Date]
-**Standard**: WCAG 2.1 Level AA
-
-### Critical Issues (Must Fix)
-
-| Issue       | Elements | WCAG  | Fix                      |
-| ----------- | -------- | ----- | ------------------------ |
-| Missing alt | 3 images | 1.1.1 | Add descriptive alt text |
-
-### Serious Issues (Should Fix)
-
-| Issue        | Elements   | WCAG  | Fix              |
-| ------------ | ---------- | ----- | ---------------- |
-| Low contrast | 2 elements | 1.4.3 | Use darker color |
-
-### Passed Checks
-
-- [x] Page has lang attribute
-- [x] Headings in correct order
-- [x] Form inputs have labels
-
-### Summary
-
-- Violations: X critical, Y serious, Z minor
-- Passed: N checks
-```
-
-## Error Handling
-
-### Server Won't Start
-
-If server fails to start after 30 seconds:
-
-1. Check for port conflicts
-2. Check npm logs for errors
-3. Report error and skip audit
-
-### Axe-core Load Fails
-
-If axe-core fails to load:
-
-1. Check network connectivity
-2. Try alternative CDN
-3. Fall back to snapshot-only audit
-
-### Navigation Fails
-
-If page doesn't load:
-
-1. Verify URL is correct
-2. Check for JavaScript errors
-3. Report partial results