ln-620-codebase-auditor
Use when auditing the codebase through the evaluation platform with mandatory research, coordinated domain audit workers, and structured summaries.
What this skill does
> **Paths:** File paths (`references/`, `../ln-*`) are relative to this skill directory.
**Type:** L2 Coordinator
**Category:** 6XX Audit
# Codebase Auditor
## Mandatory Read
**MANDATORY READ:** Load `references/evaluation_coordinator_runtime_contract.md`, `references/evaluation_summary_contract.md`, `references/evaluation_research_contract.md`
**MANDATORY READ:** Load `references/audit_final_report_contract.md`
**MANDATORY READ:** Load `references/codebase_audit_worker_boundaries.md`
**MANDATORY READ:** Load `references/research_tool_fallback.md`
Conditional read: load `references/epistemic_protocol.md` only when source confidence or claim uncertainty affects issue validation.
## Purpose
- audit runtime/codebase risks: security, delivery gates, dependency/reuse health, maintainability, dead code, diagnosability, concurrency, lifecycle, and config validation
- coordinate exactly `ln-621` through `ln-629`
- require stack-aware research before scoring
## Runtime Contract
Runtime family:
- `evaluation-runtime`
Identifier:
- `codebase-audit`
Phase order:
1. `PHASE_0_CONFIG`
2. `PHASE_1_DISCOVERY`
3. `PHASE_2_RESEARCH`
4. `PHASE_3_DELEGATE`
5. `PHASE_4_AGGREGATE`
6. `PHASE_5_REPORT`
7. `PHASE_6_SELF_CHECK`
## Worker Set
- `ln-621-security-boundary-auditor`
- `ln-622-build-delivery-gate-auditor`
- `ln-623-duplication-overabstraction-auditor`
- `ln-624-code-maintainability-hotspot-auditor`
- `ln-625-dependency-reuse-auditor`
- `ln-626-dead-code-pruning-auditor`
- `ln-627-diagnosability-auditor`
- `ln-628-concurrency-correctness-auditor`
- `ln-629-runtime-lifecycle-config-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 codebase structure and stack`
- `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:
```text
Skill(skill: "ln-621-security-boundary-auditor", args: "{scope}")
Skill(skill: "ln-622-build-delivery-gate-auditor", args: "{scope}")
Skill(skill: "ln-623-duplication-overabstraction-auditor", args: "{scope}")
Skill(skill: "ln-624-code-maintainability-hotspot-auditor", args: "{scope}")
Skill(skill: "ln-625-dependency-reuse-auditor", args: "{scope}")
Skill(skill: "ln-626-dead-code-pruning-auditor", args: "{scope}")
Skill(skill: "ln-627-diagnosability-auditor", args: "{scope}")
Skill(skill: "ln-628-concurrency-correctness-auditor", args: "{scope}")
Skill(skill: "ln-629-runtime-lifecycle-config-auditor", args: "{scope}")
```
## Workflow
### Phase 0: Config
Start `evaluation-runtime` with `required_research=true`.
### Phase 1: Discovery
Detect project type, stack, and applicability of audit workers.
### Phase 2: Research
Mandatory research sources:
1. official docs or standards
2. MCP Ref
3. Context7 when framework docs matter
4. current web best-practice research
### Phase 3: Delegate
Delegate applicable audit workers. Child workers must use `evaluation-worker-runtime` and emit evaluation-compatible summaries.
### Phase 4: Aggregate
Merge runtime/codebase risk findings using `references/codebase_audit_worker_boundaries.md`. Read every worker `report_path`, normalize actions, deduplicate repeated issues, resolve worker conflicts, and validate each actionable problem against the research source order in `references/evaluation_research_contract.md`.
### Phase 5: Report
Write `.hex-skills/runtime-artifacts/runs/{run_id}/audit-report/ln-620--final-report.md` per `references/audit_final_report_contract.md`. Include the remediation plan, source-backed validation for each confirmed issue, and cleanup note. Remove temporary worker markdown reports after consolidation. The `evaluation-coordinator` summary `report_path` must point to the final report only.
### Phase 6: Self-Check
Required checks:
- [ ] research completed
- [ ] all applicable worker summaries recorded
- [ ] worker conflicts resolved with `codebase_audit_worker_boundaries.md`
- [ ] aggregation completed
- [ ] final remediation report written
- [ ] cleanup verified
- [ ] temporary worker markdown reports removed
- [ ] coordinator summary recorded
## Summary Contract
Write `summary_kind=evaluation-coordinator`.
## Definition of Done
- [ ] Evaluation runtime started
- [ ] Applicable workers selected
- [ ] Research completed
- [ ] All applicable worker summaries recorded
- [ ] Worker set remained exactly `ln-621` through `ln-629`
- [ ] Worker conflicts resolved with `codebase_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 codebase audit result.
## References
- Workers: `../ln-621-security-boundary-auditor/SKILL.md`, `../ln-622-build-delivery-gate-auditor/SKILL.md`, `../ln-623-duplication-overabstraction-auditor/SKILL.md`, `../ln-624-code-maintainability-hotspot-auditor/SKILL.md`, `../ln-625-dependency-reuse-auditor/SKILL.md`, `../ln-626-dead-code-pruning-auditor/SKILL.md`, `../ln-627-diagnosability-auditor/SKILL.md`, `../ln-628-concurrency-correctness-auditor/SKILL.md`, `../ln-629-runtime-lifecycle-config-auditor/SKILL.md`
---
**Version:** 5.0.0
**Last Updated:** 2025-12-23
Related in Security
mac-ops
IncludedComprehensive macOS workstation operations — diagnose kernel panics, identify failing drives, audit launchd startup items, decode wake reasons, triage TCC permission denials, manage APFS snapshots, recover from no-boot. Use for: Mac is slow, slow bootup, won't boot, kernel panic, kernel_task hot, mds_stores CPU, photoanalysisd, cloudd, login loop, gray screen, sleep wake failure, drive failing, IO errors, APFS snapshots eating space, Time Machine local snapshots, Spotlight indexing, launchd, LaunchAgent, LaunchDaemon, login items, TCC permissions, Full Disk Access, Screen Recording denied, Gatekeeper, quarantine, com.apple.quarantine, app is damaged, helper tool, /Library/PrivilegedHelperTools, pmset, wake reasons, dark wake, sysdiagnose, panic.ips, DiagnosticReports, configuration profile, MDM profile, remote diagnostics over SSH.
a11y-audit
IncludedRun accessibility audits on web projects combining automated scanning (axe-core, Lighthouse) with WCAG 2.1 AA compliance mapping, manual check guidance, and structured reporting. Output is configurable: markdown report only, markdown plus machine-readable JSON, or markdown plus issue tracker integration. Use this skill whenever the user mentions "accessibility audit", "a11y audit", "WCAG audit", "accessibility check", "compliance scan", or asks to check a web project for accessibility issues. Also trigger when the user wants to verify WCAG conformance or map findings to a specific standard (CAN-ASC-6.2, EN 301 549, ADA/AODA).
erpclaw
IncludedAI-native ERP system with self-extending OS. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting. 413 actions across 14 domains, 43 expansion modules. Constitutional guardrails, adversarial audit, schema migration. Double-entry GL, immutable audit trail, US GAAP.
assess
IncludedAssesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. Compares against project conventions and prior decisions from memory. Produces structured evaluation reports with actionable improvement suggestions. Use when evaluating code, designs, architectures, or comparing alternative approaches.
spring-boot-security-jwt
IncludedProvides JWT authentication and authorization patterns for Spring Boot 3.5.x covering token generation with JJWT, Bearer/cookie authentication, database/OAuth2 integration, and RBAC/permission-based access control using Spring Security 6.x. Use when implementing authentication or authorization in Spring Boot applications.
code-hardcode-audit
IncludedDetect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.