ln-630-test-auditor

$27

• audit test-suite value through independent worker angles: product behavior, E2E journeys, portfolio value, critical coverage, trustworthiness, manual evidence, structure, and oracle strength

• coordinate ln-631 through ln-638

• require current testing best-practice research

Runtime Contract

Runtime family:

• evaluation-runtime

Identifier:

• test-audit

Phase order:

• PHASE_0_CONFIG

• PHASE_1_DISCOVERY

• PHASE_2_RESEARCH

• PHASE_3_DELEGATE

• PHASE_4_AGGREGATE

• PHASE_5_REPORT

• PHASE_6_SELF_CHECK

Worker Set

• ln-631-test-business-logic-auditor

• ln-632-test-e2e-priority-auditor

• ln-633-test-value-auditor

• ln-634-test-coverage-auditor

• ln-635-test-isolation-auditor

• ln-636-manual-test-auditor

• ln-637-test-structure-auditor

• ln-638-test-oracle-effectiveness-auditor

Worker Invocation (MANDATORY)

Host Skill Invocation: Skill(skill: "...", args: "...") is mandatory delegation.

• Claude: call the Skill tool exactly as shown.

• Codex: if no Skill tool exists, locate the named skill in available skills, read its SKILL.md, treat args as $ARGUMENTS, execute that skill workflow, then return here with its result/artifact.

• Do not inline worker logic or mark the worker complete without executing the target skill.

Use the Skill tool for delegated workers. Do not inline worker logic inside the coordinator.

TodoWrite format (mandatory):

• Resolve audit scope and build manifest

• Load test infrastructure and coverage

• Run best-practice research

• Delegate to domain audit workers

• Aggregate worker findings

• Generate final audit report and remediation plan

• Verify cleanup and self-check

Representative invocations:

Skill(skill: "ln-631-test-business-logic-auditor", args: "{scope}")

Skill(skill: "ln-632-test-e2e-priority-auditor", args: "{scope}")

Skill(skill: "ln-633-test-value-auditor", args: "{scope}")

Skill(skill: "ln-634-test-coverage-auditor", args: "{scope}")

Skill(skill: "ln-635-test-isolation-auditor", args: "{scope}")

Skill(skill: "ln-636-manual-test-auditor", args: "{scope}")

Skill(skill: "ln-637-test-structure-auditor", args: "{scope}")

Skill(skill: "ln-638-test-oracle-effectiveness-auditor", args: "{scope}")

Workflow

• Start evaluation-runtime.

• Discover automated and manual test surfaces.

• Perform mandatory research.

• Delegate audit workers.

• Aggregate findings into one risk-based test audit by reading every worker report_path, normalizing actions from references/test_audit_worker_boundaries.md, deduplicating issues, resolving worker conflicts, and validating actionable problems against references/evaluation_research_contract.md.

• Write .hex-skills/runtime-artifacts/runs/{run_id}/audit-report/ln-630--final-report.md with remediation plan per references/audit_final_report_contract.md.

• Include final pruning groups: delete low-value tests, merge duplicates, rewrite to product behavior, add missing risk-based tests, and keep high-value regression/business-risk tests.

• Remove temporary worker markdown reports and record cleanup evidence.

• Write the evaluation-coordinator summary with report_path set to the final report.

Definition of Done

• Evaluation runtime started

• Test surfaces discovered

• Mandatory research completed

• All planned worker summaries recorded

• Worker conflicts resolved with test_audit_worker_boundaries.md

• Final report and remediation plan written

• Temporary worker markdown reports removed

• evaluation-coordinator summary written

• Runtime completed

Meta-Analysis

Optional reference: load references/meta_analysis_protocol.md only when the user asks for post-run meta-analysis or protocol-formatted run reflection.

When requested after the coordinator run, analyze the session per protocol section 7 and include the protocol-formatted output with the final test audit result.

References

• Workers: ../ln-631-test-business-logic-auditor/SKILL.md, ../ln-632-test-e2e-priority-auditor/SKILL.md, ../ln-633-test-value-auditor/SKILL.md, ../ln-634-test-coverage-auditor/SKILL.md, ../ln-635-test-isolation-auditor/SKILL.md, ../ln-636-manual-test-auditor/SKILL.md, ../ln-637-test-structure-auditor/SKILL.md, ../ln-638-test-oracle-effectiveness-auditor/SKILL.md

Version: 4.0.0

Last Updated: 2025-12-23