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. If shared/ is missing, fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path} .

Business Logic Focus Auditor (L3 Worker)

Type: L3 Worker

Specialized worker auditing tests for Business Logic Focus (Category 1).

Purpose & Scope

• Audit Business Logic Focus (Category 1: High Priority)

• Detect tests validating framework/library behavior (NOT our code)

• Calculate compliance score (X/10)

Inputs

MANDATORY READ: Load shared/references/audit_worker_core_contract.md .

Receives contextStore with: tech_stack , testFilesMetadata , codebase_root , output_dir .

Workflow

MANDATORY READ: Load shared/references/two_layer_detection.md for detection methodology.

• Parse Context: Extract tech stack, framework detection patterns, test file list, output_dir from contextStore

• Scan Codebase (Layer 1): Scan test files for framework/library tests (see Audit Rules below) 2b) Context Analysis (Layer 2 -- MANDATORY): For each candidate, read test code and ask:

• Does this test custom code that wraps a framework primitive (e.g., custom hook using useState)? -> KEEP (testing integration, not framework)

• Does this test ONLY call framework API with no custom logic? -> flag for removal

• Is this a test helper/utility that imports libraries for mocking setup? -> skip (not a test of framework behavior)

• Collect Findings: Record each violation with severity, location (file:line), effort estimate (S/M/L), recommendation

• Calculate Score: Count violations by severity, calculate compliance score (X/10)

• Write Report: Build full markdown report in memory per shared/templates/audit_worker_report_template.md , write to {output_dir}/ln-631--global.md in single Write call

• Return Summary: Return minimal summary to coordinator (see Output Format)

Audit Rules

1. Framework Tests Detection

What: Tests validating framework behavior (Express, Fastify, Koa) instead of OUR business logic

Detection Patterns:

• (express|fastify|koa).(use|get|post|put|delete|patch)

• Test names: "middleware is called", "route handler works", "Express app listens"

Severity: MEDIUM

Recommendation: Consider removing IF test only validates framework behavior. If testing integration of custom code with framework -> KEEP

Effort: S (delete test file or test block)

2. ORM/Database Library Tests

What: Tests validating Prisma/Mongoose/Sequelize/TypeORM behavior

Detection Patterns:

• (prisma|mongoose|sequelize|typeorm).(find|findMany|create|update|delete|upsert)

• Test names: "Prisma findMany returns array", "Mongoose save works"

Severity: MEDIUM

Recommendation: Consider removing IF test only validates ORM behavior. If testing custom query logic or repository patterns -> KEEP

Effort: S

3. Crypto/Hashing Library Tests

What: Tests validating bcrypt/argon2 hashing behavior

Detection Patterns:

• (bcrypt|argon2).(hash|compare|verify|hashSync)

• Test names: "bcrypt hashes password", "argon2 compares correctly"

Severity: MEDIUM

Recommendation: Consider removing IF test only validates library behavior. If testing custom password policy or hashing wrapper -> KEEP

Effort: S

4. JWT/Token Library Tests

What: Tests validating JWT signing/verification

Detection Patterns:

• (jwt|jsonwebtoken).(sign|verify|decode)

• Test names: "JWT signs token", "JWT verifies signature"

Severity: MEDIUM

Recommendation: Consider removing IF test only validates JWT library. If testing custom token payload, claims logic, or auth flow -> KEEP

Effort: S

5. HTTP Client Library Tests

What: Tests validating axios/fetch/got behavior

Detection Patterns:

• (axios|fetch|got|request).(get|post|put|delete|patch)

• Test names: "axios makes GET request", "fetch returns data"

Severity: MEDIUM

Recommendation: Consider removing IF test only validates HTTP client behavior. If testing custom API wrapper, retry logic, or error mapping -> KEEP

Effort: S

6. React Hooks/Framework Tests

What: Tests validating React hooks behavior (useState, useEffect, etc.)

Detection Patterns:

• (useState|useEffect|useContext|useReducer|useMemo|useCallback)

• Test names: "useState updates state", "useEffect runs on mount"

Severity: LOW (acceptable if testing OUR custom hook logic)

Recommendation: REVIEW -- if testing framework behavior -> DELETE; if testing custom hook -> KEEP

Effort: S-M

Scoring Algorithm

MANDATORY READ: Load shared/references/audit_worker_core_contract.md and shared/references/audit_scoring.md .

Output Format

MANDATORY READ: Load shared/references/audit_worker_core_contract.md and shared/templates/audit_worker_report_template.md .

Write JSON summary per shared/references/audit_summary_contract.md . In managed mode the caller passes both runId and summaryArtifactPath ; in standalone mode the worker generates its own run-scoped artifact path per shared contract.

Write report to {output_dir}/ln-631--global.md with category: "Business Logic Focus" and checks: framework_tests, orm_tests, crypto_tests, jwt_tests, http_client_tests, react_hooks_tests.

Return summary per shared/references/audit_summary_contract.md .

When summaryArtifactPath is absent, write the standalone runtime summary under .hex-skills/runtime-artifacts/runs/{run_id}/evaluation-worker/{worker}--{identifier}.json and optionally echo the same summary in structured output.

Report written: .hex-skills/runtime-artifacts/runs/{run_id}/audit-report/ln-631--global.md Score: X.X/10 | Issues: N (C:N H:N M:N L:N)

Critical Rules

MANDATORY READ: Load shared/references/audit_worker_core_contract.md .

• Do not auto-fix: Report only

• Framework-specific patterns: Match detection patterns to project's actual tech stack

• Effort realism: S = <1h, M = 1-4h, L = >4h

• Context-aware: Custom wrappers around libraries (e.g., custom hook using useState) are OUR code -- do not flag

• Exclude test helpers: Do not flag shared test utilities that import libraries for mocking setup

Definition of Done

MANDATORY READ: Load shared/references/audit_worker_core_contract.md .

• contextStore parsed successfully (including output_dir)

• All 6 checks completed (framework, ORM, crypto, JWT, HTTP client, React hooks)

• Findings collected with severity, location, effort, recommendation

• Score calculated using penalty algorithm

• Report written to {output_dir}/ln-631--global.md (atomic single Write call)

• Summary written per contract

Reference Files

• Audit output schema: shared/references/audit_output_schema.md

Version: 3.0.0 Last Updated: 2025-12-23