with one click
ln-634-test-coverage-auditor
// Identifies missing tests for critical paths (money, security, data integrity, core flows). Use when auditing test coverage gaps.
// Identifies missing tests for critical paths (money, security, data integrity, core flows). Use when auditing test coverage gaps.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | ln-634-test-coverage-auditor |
| description | Identifies missing tests for critical paths (money, security, data integrity, core flows). Use when auditing test coverage gaps. |
| allowed-tools | Read, Grep, Glob, Bash, mcp__hex-graph__audit_workspace, mcp__hex-line__read_file, mcp__hex-line__grep_search, mcp__hex-line__outline |
| license | MIT |
| model | claude-haiku-4-5 |
Paths: File paths (
references/,../ln-*) are relative to this skill directory.
Type: L3 Worker
Specialized worker identifying missing tests for critical business logic.
MANDATORY READ: Load references/audit_worker_core_contract.md.
Tool policy: follow host AGENTS.md MCP preferences; load references/mcp_tool_preferences.md and references/mcp_integration_patterns.md only when host policy is absent or MCP behavior is unclear.
Receives contextStore with: tech_stack, testFilesMetadata, codebase_root, output_dir.
Domain-aware: Supports domain_mode + current_domain (see audit_output_schema.md#domain-aware-worker-output).
Use hex-graph first when hotspots materially improve coverage-gap discovery. Use hex-line first for local code and test reads when available. If MCP is unavailable, unsupported, or not indexed, continue with built-in Read/Grep/Glob/Bash and state the fallback in the report.
Detection policy: use two-layer detection (candidate scan, then context verification); load references/two_layer_detection.md only when the verification method is ambiguous.
Parse context -- extract fields, determine scan_path (domain-aware if specified)
ELSE:
scan_path = codebase_root
domain_name = null
Identify critical paths in scan_path (not entire codebase)
scan_path for money/security/data keywordsscan_path (not codebase_root)Grep(pattern="payment|refund|discount", path=scan_path)Check test coverage for each critical path (Layer 1)
paymentIcon() is UI, not payment logic)? -> skipCollect missing tests
domain: domain_name (if domain-aware)Calculate Score: Count violations by severity, calculate compliance score (X/10)
Write Report: Build full markdown report in memory per references/templates/audit_worker_report_template.md, write to {output_dir}/ln-634--{identifier}.md (or {output_dir}/ln-634--{identifier}.md if domain-aware) in single Write call
Return Summary: Return minimal summary to coordinator (see Output Format)
What: Any code handling financial transactions
Examples:
/payment, processPayment())calculateDiscount(), applyPromoCode())calculateTax(), getTaxRate())processRefund(), /refund)generateInvoice(), createBill())convertCurrency())Min Priority: 20
Why Critical: Money loss, fraud, legal compliance
What: Authentication, authorization, encryption
Examples:
/login, authenticate())/refresh-token, refreshAccessToken())/forgot-password, resetPassword())checkPermission(), hasRole())validateApiKey())Min Priority: 20
Why Critical: Security breach, data leak, unauthorized access
What: CRUD operations, transactions, validation
Examples:
createUser(), deleteOrder(), updateProduct())withTransaction())runMigration())checkDuplicateEmail())Min Priority: 15
Why Critical: Data corruption, lost data, inconsistent state
What: Multi-step flows critical to business
Examples:
Min Priority: 15
Why Critical: Broken user flow = lost customers
Process:
payment, refund, discount, tax, price, currencyauth, login, password, token, permission, encrypttransaction, validation, migration, constraintFor each critical path:
Severity by Priority:
For each missing test:
MANDATORY READ: Load references/audit_scoring.md.
Severity mapping by Priority:
MANDATORY READ: Load references/templates/audit_worker_report_template.md.
Write JSON summary per 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-634--{identifier}.md (global) or {output_dir}/ln-634--{identifier}.md (domain-aware) with category: "Coverage Gaps" and checks: money_flow_coverage, security_flow_coverage, data_integrity_coverage, core_journey_coverage.
Return summary per 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-634--{identifier}.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)
Apply the already-loaded references/audit_worker_core_contract.md.
domain_mode="domain-aware", scan ONLY scan_path production code (not entire codebase)domain field in each finding when domain-awareApply the already-loaded references/audit_worker_core_contract.md.
{output_dir}/ln-634--{identifier}.md or ln-634--{identifier}.md (atomic single Write call)references/audit_output_schema.mdVersion: 3.0.0 Last Updated: 2025-12-23