with one click
ln-620-codebase-auditor
// Use when auditing the codebase through the evaluation platform with mandatory research, coordinated domain audit workers, and structured summaries.
// Use when auditing the codebase through the evaluation platform with mandatory research, coordinated domain audit workers, and structured summaries.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | ln-620-codebase-auditor |
| description | Use when auditing the codebase through the evaluation platform with mandatory research, coordinated domain audit workers, and structured summaries. |
| license | MIT |
Paths: File paths (
references/,../ln-*) are relative to this skill directory.
Type: L2 Coordinator Category: 6XX Audit
MANDATORY READ: Load references/evaluation_coordinator_runtime_contract.md, references/evaluation_summary_contract.md, references/evaluation_research_contract.md
MANDATORY READ: Load references/research_tool_fallback.md
ln-621 through ln-629Runtime family:
evaluation-runtimeIdentifier:
codebase-auditPhase order:
PHASE_0_CONFIGPHASE_1_DISCOVERYPHASE_2_RESEARCHPHASE_3_DELEGATEPHASE_4_AGGREGATEPHASE_5_REPORTPHASE_6_SELF_CHECKln-621-security-auditorln-622-build-auditorln-623-code-principles-auditorln-624-code-quality-auditorln-625-dependencies-auditorln-626-dead-code-auditorln-627-observability-auditorln-628-concurrency-auditorln-629-lifecycle-auditorHost Skill Invocation: Skill(skill: "...", args: "...") is mandatory delegation.
SKILL.md, treat args as $ARGUMENTS, execute that skill workflow, then return here with its result/artifact.Use the Skill tool for delegated workers. Do not inline worker logic inside the coordinator.
TodoWrite format (mandatory):
Resolve audit scope and build manifestLoad codebase structure and stackRun best-practice researchDelegate to domain audit workersAggregate worker findingsGenerate audit reportVerify cleanup and self-checkRepresentative invocations:
Skill(skill: "ln-621-security-auditor", args: "{scope}")
Skill(skill: "ln-622-build-auditor", args: "{scope}")
Skill(skill: "ln-623-code-principles-auditor", args: "{scope}")
Skill(skill: "ln-624-code-quality-auditor", args: "{scope}")
Skill(skill: "ln-625-dependencies-auditor", args: "{scope}")
Skill(skill: "ln-626-dead-code-auditor", args: "{scope}")
Skill(skill: "ln-627-observability-auditor", args: "{scope}")
Skill(skill: "ln-628-concurrency-auditor", args: "{scope}")
Skill(skill: "ln-629-lifecycle-auditor", args: "{scope}")
Start evaluation-runtime with required_research=true.
Detect project type, stack, and applicability of audit workers.
Mandatory research sources:
Delegate applicable audit workers. Child workers must use evaluation-worker-runtime and emit evaluation-compatible summaries.
Merge security, correctness, architecture, and maintainability findings.
Write final codebase audit output and coordinator summary.
Required checks:
Write summary_kind=evaluation-coordinator.
evaluation-coordinator summary writtenOptional 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.
../ln-621-security-auditor/SKILL.md, ../ln-622-build-auditor/SKILL.md, ../ln-623-code-principles-auditor/SKILL.md, ../ln-624-code-quality-auditor/SKILL.md, ../ln-625-dependencies-auditor/SKILL.md, ../ln-626-dead-code-auditor/SKILL.md, ../ln-627-observability-auditor/SKILL.md, ../ln-628-concurrency-auditor/SKILL.md, ../ln-629-lifecycle-auditor/SKILL.mdVersion: 5.0.0 Last Updated: 2025-12-23