Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

Test Suite Auditor (L2 Coordinator)

Coordinates comprehensive test suite audit across 6 quality categories using 5 specialized workers.

Purpose & Scope

• L2 Coordinator that delegates to L3 specialized audit workers
• Audits all tests against 6 quality categories (via 5 workers)
• Calculates Usefulness Score for each test (Keep/Remove/Refactor)
• Identifies missing tests for critical business logic
• Detects anti-patterns and isolation issues
• Aggregates results into unified report
• Write report to docs/project/test_audit.md (file-based, no task creation)
• Manual invocation by user; not part of Story pipeline

Core Philosophy

"Write tests. Not too many. Mostly integration." — Kent Beck "Test based on risk, not coverage." — ISO 29119

Key Principles:

1. Test business logic, not frameworks — bcrypt/Prisma/Express already tested
2. No performance/load/stress tests — Tests infrastructure, not code correctness (use k6/JMeter separately)
3. Risk-based prioritization — Priority ≥15 or remove
4. E2E for critical paths only — Money/Security/Data (Priority ≥20)
5. Usefulness over quantity — One useful test > 10 useless tests
6. Every test must justify existence — Impact × Probability ≥15

Workflow

Phase 1: Discovery (Automated)

Inputs: Codebase root directory

Actions:

1. Find all test files using Glob:
   • **/*.test.* (Jest, Vitest)
   • **/*.spec.* (Mocha, Jasmine)
   • **/__tests__/**/* (Jest convention)
2. Parse test file structure (test names, assertions count)
3. Auto-discover Team ID from docs/tasks/kanban_board.md

Output: testFilesMetadata — list of test files with basic stats

Phase 2: Research Best Practices (ONCE)

Goal: Gather testing best practices context ONCE, share with all workers

Actions:

1. Use MCP Ref/Context7 to research testing best practices for detected tech stack
2. Load ../shared/references/risk_based_testing_guide.md
3. Build contextStore with:
   • Testing philosophy (E2E primary, Unit supplementary)
   • Usefulness Score formulas (Impact × Probability)
   • Anti-patterns catalog
   • Framework detection patterns

Add output_dir to contextStore:

{
  "output_dir": "docs/project/.audit/ln-630/{YYYY-MM-DD}"
}

Output: contextStore — shared context for all workers

Key Benefit: Context gathered ONCE → passed to all workers → token-efficient

Phase 2.5: Prepare Output Directory

mkdir -p {output_dir}   # No deletion — date folders preserve history

Phase 3: Domain Discovery (NEW)

Purpose: Detect project domains from production code folder structure for domain-aware coverage analysis.

Algorithm: (same as ln-360-codebase-auditor)

1. Priority 1: Explicit domain folders

   • Check for: src/domains/*/, src/features/*/, src/modules/*/
   • Monorepo patterns: packages/*/, libs/*/, apps/*/
   • If found (>1 match) → use as domains

2. Priority 2: Top-level src/ folders*

   • List folders: src/users/, src/orders/, src/payments/
   • Exclude infrastructure: utils, shared, common, lib, helpers, config, types, interfaces, constants, middleware, infrastructure, core
   • If remaining >1 → use as domains

3. Priority 3: Fallback to global mode

   • If <2 domains detected → domain_mode = "global"
   • All workers scan entire codebase (backward-compatible behavior)

Heuristics for domain detection:

Output:

{
  "domain_mode": "domain-aware",
  "all_domains": [
    {"name": "users", "path": "src/users", "file_count": 45},
    {"name": "orders", "path": "src/orders", "file_count": 32},
    {"name": "shared", "path": "src/shared", "file_count": 15, "is_shared": true}
  ]
}

Shared folder handling:

• Folders named shared, common, utils, lib, core → mark is_shared: true
• Shared code audited but grouped separately in report

Phase 4: Delegate to Workers

CRITICAL: All delegations use Task tool with subagent_type: "general-purpose" for context isolation.

Prompt template:

Task(description: "Test audit via ln-63X",
     prompt: "Execute ln-63X-{worker}. Read skill from ln-63X-{worker}/SKILL.md. Context: {contextStore}",
     subagent_type: "general-purpose")

Anti-Patterns:

• ❌ Direct Skill tool invocation without Task wrapper
• ❌ Any execution bypassing subagent context isolation

Phase 4a: Global Workers (PARALLEL)

Global workers scan entire test suite (not domain-aware):

Invocation (4 workers in PARALLEL):

FOR EACH worker IN [ln-631, ln-632, ln-633, ln-635]:
  Task(description: "Test audit via " + worker,
       prompt: "Execute " + worker + ". Read skill. Context: " + JSON.stringify(contextStore),
       subagent_type: "general-purpose")

Phase 4b: Domain-Aware Worker (PARALLEL per domain)

Domain-aware worker runs once per domain:

Invocation:

IF domain_mode == "domain-aware":
  FOR EACH domain IN all_domains:
    domain_context = {
      ...contextStore,
      domain_mode: "domain-aware",
      current_domain: { name: domain.name, path: domain.path }
    }
    Task(description: "Test audit coverage " + domain.name + " via ln-634",
         prompt: "Execute ln-634-test-coverage-auditor. Read skill. Context: " + JSON.stringify(domain_context),
         subagent_type: "general-purpose")
ELSE:
  // Fallback: invoke once for entire codebase (global mode)
  Task(description: "Test audit coverage via ln-634",
       prompt: "Execute ln-634-test-coverage-auditor. Read skill. Context: " + JSON.stringify(contextStore),
       subagent_type: "general-purpose")

Parallelism strategy:

• Phase 4a: All 4 global workers run in PARALLEL
• Phase 4b: All N domain-aware invocations run in PARALLEL
• Example: 3 domains → 3 ln-634 invocations in single message

Worker Output Contract (File-Based):

Workers write full report to {output_dir}/{worker_id}.md per shared/templates/audit_worker_report_template.md.

Workers return minimal summary in-context (~50 tokens):

Report written: docs/project/.audit/ln-630/{YYYY-MM-DD}/631-business-logic.md
Score: 7.5/10 | Issues: 5 (C:0 H:2 M:2 L:1)

Coordinator extracts score/counts from return values. Full findings stay in files.

Unified Scoring Formula (all workers):

penalty = (critical × 2.0) + (high × 1.0) + (medium × 0.5) + (low × 0.2)
score = max(0, 10 - penalty)

Domain-aware workers add optional fields: domain, scan_path

Phase 5: Aggregate Results (File-Based)

Goal: Merge all worker results into unified Test Suite Audit Report

Workers wrote reports to {output_dir}/ and returned minimal summaries. Aggregation uses return values for numbers and file reads for findings tables.

Aggregation Algorithm:

1. Parse scores/counts from worker return strings (already in context)
2. Read worker report files from {output_dir}/ for findings tables
3. Sum severity counts across all workers
4. Calculate Overall Score: average of 5 worker scores
5. Sort findings by severity: CRITICAL → HIGH → MEDIUM → LOW
6. Group findings by category for report sections

Actions:

1. Parse return values from all workers for scores/counts
2. Read worker files from {output_dir}/ for detailed findings
3. Sum severity counts across all workers
4. Calculate overall score = average of 5 worker scores
5. Domain-aware worker (ln-634) → group by domain.name if domain_mode="domain-aware"
6. Generate Executive Summary (2-3 sentences)
7. Write report to docs/project/test_audit.md
8. Return summary to user

Findings grouping:

• Categories 1-3, 5-6 (Business Logic, E2E, Value, Isolation, Anti-Patterns) → single tables (global)
• Category 4 (Coverage Gaps) → subtables per domain (if domain_mode="domain-aware")

Context Validation (Post-Filter):

MANDATORY READ: Load shared/references/context_validation.md

Apply Rules 1, 5 + test-specific filters to merged findings:

FOR EACH finding WHERE severity IN (HIGH, MEDIUM):
  # Rule 1: ADR/Planned Override
  IF finding matches ADR → advisory "[Planned: ADR-XXX]"

  # Rule 5: Locality/Single-Consumer
  IF "extract shared helper" suggestion AND consumer_count == 1 → advisory

  # Test-specific: Custom wrapper detection
  IF "framework test" finding (ln-631) AND test imports custom wrapper class:
    → advisory (tests custom logic, not framework)

  # Test-specific: Setup/fixture code
  IF "The Liar" finding (ln-635) AND file is conftest/fixture/setup:
    → advisory (setup code, no assertions expected)

  # Test-specific: Parameterized test
  IF "The Giant" finding (ln-635) AND test is parameterized/data-driven:
    → severity -= 1 (size from data, not complexity)

Downgraded findings → "Advisory Findings" section in report.
Recalculate scores excluding advisory findings from penalty.

Exempt: Coverage gap CRITICAL findings (ln-634), risk-value scores (ln-633).

Output Format

## Test Suite Audit Report - [DATE]

### Executive Summary
[2-3 sentences: test suite health, major issues, key recommendations]

### Severity Summary

| Severity | Count |
|----------|-------|
| Critical | X |
| High | X |
| Medium | X |
| Low | X |
| **Total** | **X** |

### Compliance Score

| Category | Score | Notes |
|----------|-------|-------|
| Business Logic Focus | X/10 | X framework tests found |
| E2E Critical Coverage | X/10 | X critical paths missing E2E |
| Risk-Based Value | X/10 | X low-value tests |
| Coverage Gaps | X/10 | X critical paths untested |
| Isolation & Anti-Patterns | X/10 | X isolation + anti-pattern issues |
| **Overall** | **X/10** | Average of 5 categories |

### Domain Coverage Summary (NEW - if domain_mode="domain-aware")

| Domain | Critical Paths | Tested | Coverage % | Gaps |
|--------|---------------|--------|------------|------|
| users | 8 | 6 | 75% | 2 |
| orders | 12 | 8 | 67% | 4 |
| payments | 6 | 5 | 83% | 1 |
| **Total** | **26** | **19** | **73%** | **7** |

### Audit Findings

| Severity | Location | Issue | Principle | Recommendation | Effort |
|----------|----------|-------|-----------|----------------|--------|
| **CRITICAL** | routes/payment.ts:45 | Missing E2E for payment processing (Priority 25) | E2E Critical Coverage / Money Flow | Add E2E: successful payment + discount edge cases | M |
| **HIGH** | auth.test.ts:45-52 | Test 'bcrypt hashes password' validates library behavior | Business Logic Focus / Crypto Testing | Delete — bcrypt already tested by maintainers | S |
| **HIGH** | db.test.ts:78-85 | Test 'Prisma findMany returns array' validates ORM | Business Logic Focus / ORM Testing | Delete — Prisma already tested | S |
| **HIGH** | user.test.ts:45 | Anti-pattern 'The Liar' — no assertions | Anti-Patterns / The Liar | Add specific assertions or delete test | S |
| **MEDIUM** | utils.test.ts:23-27 | Test 'validateEmail' has Usefulness Score 4 | Risk-Based Value / Low Priority | Delete — likely covered by E2E registration | S |
| **MEDIUM** | order.test.ts:200-350 | Anti-pattern 'The Giant' — 150 lines | Anti-Patterns / The Giant | Split into focused tests | M |
| **LOW** | payment.test.ts | Anti-pattern 'Happy Path Only' — no error tests | Anti-Patterns / Happy Path | Add negative tests | M |

### Coverage Gaps by Domain (if domain_mode="domain-aware")

#### Domain: users (src/users/)

| Severity | Category | Missing Test | Location | Priority | Effort |
|----------|----------|--------------|----------|----------|--------|
| CRITICAL | Money | E2E: processRefund() | services/user.ts:120 | 20 | M |
| HIGH | Security | Unit: validatePermissions() | middleware/auth.ts:45 | 18 | S |

#### Domain: orders (src/orders/)

| Severity | Category | Missing Test | Location | Priority | Effort |
|----------|----------|--------------|----------|----------|--------|
| CRITICAL | Money | E2E: applyDiscount() | services/order.ts:45 | 25 | M |
| HIGH | Data | Integration: orderTransaction() | repositories/order.ts:78 | 16 | M |

Worker Architecture

Each worker:

• Receives contextStore with testing best practices
• Receives testFilesMetadata with test file list
• Loads full test file contents when analyzing
• Returns structured JSON with category findings
• Operates independently (failure in one doesn't block others)

Token Efficiency:

• Coordinator: metadata only (~1000 tokens)
• Workers: full test file contents when needed (~5000-10000 tokens each)
• Context gathered ONCE, shared with all workers

Critical Rules

• Two-stage delegation: Global workers (4) + Domain-aware worker (ln-634 × N domains)
• Domain discovery: Auto-detect domains from folder structure; fallback to global mode if <2 domains
• Parallel execution: All workers (global + domain-aware) run in PARALLEL
• Domain-grouped output: Coverage Gaps findings grouped by domain (if domain_mode="domain-aware")
• Delete > Archive: Remove useless tests, don't comment out
• E2E baseline: Every endpoint needs 2 E2E (positive + negative)
• Justify each test: If can't explain Priority ≥15, remove it
• Trust frameworks: Don't test Express/Prisma/bcrypt behavior
• No performance/load tests: Flag and REMOVE tests measuring throughput/latency/memory (DevOps Epic territory)
• Code is truth: If test contradicts code behavior, update test
• Language preservation: Report in project's language (EN/RU)

Definition of Done

• All test files discovered via Glob
• Context gathered from testing best practices (MCP Ref/Context7)
• Domain discovery completed (domain_mode determined)
• contextStore built with test metadata + domain info
• Global workers (4) invoked in PARALLEL
• Domain-aware worker (ln-634) invoked per domain in PARALLEL
• All workers completed successfully (or reported errors)
• Results aggregated with domain grouping (if domain_mode="domain-aware")
• Domain Coverage Summary built (if domain_mode="domain-aware")
• Compliance scores calculated (6 categories)
• Keep/Remove/Refactor decisions for each test
• Missing tests identified with Priority (grouped by domain if applicable)
• Anti-patterns catalogued
• Report written to docs/project/test_audit.md
• Summary returned to user

Reference Files

• Orchestrator lifecycle: shared/references/orchestrator_pattern.md
• Risk-based testing methodology: shared/references/risk_based_testing_guide.md
• Task delegation pattern: shared/references/task_delegation_pattern.md
• Audit scoring formula: shared/references/audit_scoring.md
• Audit output schema: shared/references/audit_output_schema.md

Related Skills

• Workers:

  • ln-631-test-business-logic-auditor — Framework tests detection
  • ln-632-test-e2e-priority-auditor — E2E baseline validation
  • ln-633-test-value-auditor — Usefulness Score calculation
  • ln-634-test-coverage-auditor — Coverage gaps identification
  • ln-635-test-isolation-auditor — Isolation + Anti-Patterns

• Reference:

  • ../shared/references/risk_based_testing_guide.md — Risk-Based Testing Guide
  • ../ln-620-codebase-auditor — Codebase audit coordinator (similar pattern)

Version: 4.0.0 Last Updated: 2025-12-23