cbbkrd-tech/ln-633-test-value-auditor

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.

Risk-Based Value Auditor (L3 Worker)

Specialized worker calculating Usefulness Score for each test.

Purpose & Scope

• Worker in ln-630 coordinator pipeline
• Audit Risk-Based Value (Category 3: Critical Priority)
• Calculate Usefulness Score = Impact × Probability
• Make KEEP/REVIEW/REMOVE decisions
• Calculate compliance score (X/10)

Inputs (from Coordinator)

Receives contextStore with Impact/Probability matrices, test file list.

Workflow

1. Parse context
2. For each test: calculate Usefulness Score
3. Classify: KEEP (≥15), REVIEW (10-14), REMOVE (<10)
4. Collect findings
5. Calculate score
6. Return JSON

Usefulness Score Calculation

Formula

Usefulness Score = Business Impact (1-5) × Failure Probability (1-5)

Impact Scoring (1-5)

| Score | Impact | Examples | |-------|--------|----------| | 5 | Critical | Money loss, security breach, data corruption | | 4 | High | Core flow breaks (checkout, login, registration) | | 3 | Medium | Feature partially broken, degraded UX | | 2 | Low | Minor UX issue, cosmetic bug | | 1 | Trivial | Cosmetic issue, no user impact |

Probability Scoring (1-5)

| Score | Probability | Indicators | |-------|-------------|------------| | 5 | Very High | Complex algorithm, new technology, many dependencies | | 4 | High | Multiple dependencies, concurrency, edge cases | | 3 | Medium | Standard CRUD, framework defaults, established patterns | | 2 | Low | Simple logic, well-established library, trivial operation | | 1 | Very Low | Trivial assignment, framework-generated, impossible to break |

Decision Thresholds

| Score Range | Decision | Action | |-------------|----------|--------| | ≥15 | KEEP | Test is valuable, maintain it | | 10-14 | REVIEW | Consider if E2E already covers this | | <10 | REMOVE | Delete test, not worth maintenance cost |

Scoring Examples

Example 1: Payment Processing Test

Test: "processPayment calculates discount correctly"
Impact: 5 (Critical — money calculation)
Probability: 4 (High — complex algorithm, multiple payment gateways)
Usefulness Score = 5 × 4 = 20
Decision: KEEP

Example 2: Email Validation Test

Test: "validateEmail returns true for valid email"
Impact: 2 (Low — minor UX issue if broken)
Probability: 2 (Low — simple regex, well-tested library)
Usefulness Score = 2 × 2 = 4
Decision: REMOVE (likely already covered by E2E registration test)

Example 3: Login Flow Test

Test: "login with valid credentials returns JWT"
Impact: 4 (High — core flow)
Probability: 3 (Medium — standard auth flow)
Usefulness Score = 4 × 3 = 12
Decision: REVIEW (if E2E covers, remove; else keep)

Audit Rules

1. Calculate Score for Each Test

Process:

• Read test file, extract test name/description
• Analyze code under test (CUT)
• Determine Impact (1-5)
• Determine Probability (1-5)
• Calculate Usefulness Score

2. Classify Decisions

KEEP (≥15):

• High-value tests (money, security, data integrity)
• Core flows (checkout, login)
• Complex algorithms

REVIEW (10-14):

• Medium-value tests
• Question: "Is this already covered by E2E?"
• If yes → REMOVE; if no → KEEP

REMOVE (<10):

• Low-value tests (cosmetic, trivial)
• Framework/library tests
• Duplicates of E2E tests

3. Identify Patterns

Common low-value tests (<10):

• Testing framework behavior
• Testing trivial getters/setters
• Testing constant values
• Testing type annotations

Scoring Algorithm

MANDATORY READ: Load shared/references/audit_scoring.md for unified scoring formula.

Severity mapping by Usefulness Score:

• Score <5 → CRITICAL (test wastes significant maintenance effort)
• Score 5-9 → HIGH (test likely wasteful)
• Score 10-14 → MEDIUM (review needed)
• Score ≥15 → no issue (KEEP)

Output Format

Return JSON to coordinator:

{
  "category": "Risk-Based Value",
  "score": 7,
  "total_issues": 12,
  "critical": 2,
  "high": 5,
  "medium": 5,
  "low": 0,
  "checks": [
    {"id": "usefulness_score", "name": "Usefulness Score Analysis", "status": "warning", "details": "7 tests scored below threshold 15"},
    {"id": "remove_candidates", "name": "Remove Candidates", "status": "failed", "details": "2 tests with Score <10 should be removed"},
    {"id": "review_candidates", "name": "Review Candidates", "status": "warning", "details": "5 tests with Score 10-14 need review"}
  ],
  "findings": [
    {
      "severity": "CRITICAL",
      "location": "utils.test.ts:23-27",
      "issue": "Test 'validateEmail returns true' has Usefulness Score 4 (Impact 2 × Probability 2) — REMOVE",
      "principle": "Risk-Based Value / Low Priority Test",
      "recommendation": "Delete test — likely covered by E2E registration test",
      "effort": "S"
    },
    {
      "severity": "MEDIUM",
      "location": "auth.test.ts:12-25",
      "issue": "Test 'login with valid credentials returns JWT' has Usefulness Score 12 (Impact 4 × Probability 3) — REVIEW",
      "principle": "Risk-Based Value / Borderline Test",
      "recommendation": "If E2E login test exists → delete; otherwise keep",
      "effort": "S"
    }
  ]
}

Note: Tests with Usefulness Score ≥15 (KEEP) are NOT included in findings — only issues are reported.

Critical Rules

• Do not auto-fix: Report only
• Effort realism: S = <1h, M = 1-4h, L = >4h
• Score objectivity: Base Impact and Probability on code analysis, not assumptions
• KEEP tests not reported: Only REVIEW and REMOVE decisions appear in findings
• Cross-reference E2E: REVIEW decisions depend on whether E2E already covers the scenario

Definition of Done

• contextStore parsed (Impact/Probability matrices, test file list)
• Usefulness Score calculated for each test (Impact x Probability)
• Decisions classified: KEEP (>=15), REVIEW (10-14), REMOVE (<10)
• Findings collected with severity, location, effort, recommendation
• Score calculated per shared/references/audit_scoring.md
• JSON returned to coordinator

Reference Files

• Audit scoring formula: shared/references/audit_scoring.md
• Audit output schema: shared/references/audit_output_schema.md

---

Version: 3.0.0 Last Updated: 2025-12-23