ln-633-test-value-auditor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ln-633-test-value-auditor (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Paths: File paths (references/,../ln-*) are relative to this skill directory.
Type: L3 Worker
Specialized worker calculating portfolio value and maintenance cost for each test.
KEEP, DELETE, MERGE, or REWRITE decisionsMANDATORY READ: Load references/audit_worker_core_contract.md.
Receives contextStore with: tech_stack, testFilesMetadata, codebase_root, output_dir.
Detection policy: use two-layer detection (candidate scan, then context verification); load references/two_layer_detection.md only when the verification method is ambiguous.
1) Parse Context: Extract tech stack, Impact/Probability matrices, test file list, output_dir from contextStore 2) Calculate Scores (Layer 1): For each test: calculate Value Score = Impact x Probability, then annotate duplicate coverage, known regression guard, and maintenance cost 2b) Context Analysis (Layer 2 -- MANDATORY): Before finalizing DELETE or MERGE decisions, ask:
3) Classify Decisions: KEEP, DELETE, MERGE, or REWRITE 4) Collect Findings: Record each REVIEW/REMOVE decision with severity, location (file:line), effort estimate (S/M/L), recommendation 5) Calculate Score: Count violations by severity, calculate compliance score (X/10) 6) Write Report: Build full markdown report in memory per references/templates/audit_worker_report_template.md, write to {output_dir}/ln-633--global.md in single Write call 7) Return Summary: Return minimal summary to coordinator (see Output Format)
Usefulness Score = Business Impact (1-5) x Failure Probability (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 |
| 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 |
| Score Range | Decision | Action |
|---|---|---|
| >=15 | KEEP | Test is valuable, maintain it |
| 10-14 | REWRITE | Keep only if assertions can prove unique product risk |
| <10 | DELETE | Delete test, not worth maintenance cost. Exception: regression guards for known bugs -> KEEP |
Test: "processPayment calculates discount correctly"
Impact: 5 (Critical -- money calculation)
Probability: 4 (High -- complex algorithm, multiple payment gateways)
Usefulness Score = 5 x 4 = 20
Decision: KEEPTest: "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 x 2 = 4
Decision: DELETE (likely already covered by E2E registration test)Test: "login with valid credentials returns JWT"
Impact: 4 (High -- core flow)
Probability: 3 (Medium -- standard auth flow)
Usefulness Score = 4 x 3 = 12
Decision: REWRITE (if E2E covers the flow, merge/delete duplicate assertions; otherwise focus assertions on auth behavior)Process:
KEEP:
MERGE:
REWRITE:
DELETE:
Common low-value tests:
MANDATORY READ: Load references/audit_scoring.md.
Severity mapping by Value Score:
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-633--global.md with category: "Portfolio Value" and checks: value_score, delete_candidates, merge_candidates, rewrite_candidates. Findings must include canonical action as KEEP, DELETE, MERGE, or REWRITE.
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-633--global.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)Note: Tests with KEEP decisions are summarized as retained evidence, not findings. Findings contain only DELETE, MERGE, and REWRITE decisions.
Apply the already-loaded references/audit_worker_core_contract.md.
Apply the already-loaded references/audit_worker_core_contract.md.
{output_dir}/ln-633--global.md (atomic single Write call)references/audit_output_schema.mdVersion: 3.0.0 Last Updated: 2025-12-23
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.