skills.rest
levnikolaevich
levnikolaevichCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ln-22-codebase-auditor

Audits cross-cutting code health across security, delivery, maintainability, dependencies, and concurrency.

556|83|Updated Oct 24, 2025
Search Tags:#static analysis#security review#dependency audit#code health#Concurrency#Code quality#Code Audit
One-click install
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-22-codebase-auditor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ln-22-codebase-auditor
Source: https://github.com/levnikolaevich/claude-code-skills/tree/main/plugins/codebase-audit-suite/skills/ln-22-codebase-auditor
Command: npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-22-codebase-auditor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Codebases accumulate hidden risks across security boundaries, delivery pipelines, dependency health, and concurrency paths that no single linter or detector reliably surfaces. This Skill performs a broad, read-only production-code health audit that turns pattern matches into evidence-backed findings with prioritized remediation.

Core Features & Use Cases

  • Cross-cutting health audit: Covers security boundaries, delivery gates, maintainability, dependencies, dead code, diagnosability, concurrency, and lifecycle in one structured checklist.
  • Evidence-gated findings: Every candidate must pass reachability, materiality, and acceptable-alternative gates before being classified as P0-P3, filtering out style nitpicks and theoretical issues.
  • Verdict-driven report: Produces a PASS, CONCERNS, FAIL, or BLOCKED verdict with a health summary table, findings with verified practice references, and dependency-ordered remediation.
  • Use Case: Before a major release, run the audit to confirm no committed secrets, skipped CI gates, vulnerable reachable dependencies, or race conditions exist, and receive a prioritized remediation plan.

Quick Start

Ask the agent to audit this repository's code health across security, delivery, maintainability, and concurrency, and return a verdict with prioritized findings.

Frequently Asked Questions about ln-22-codebase-auditor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit a codebase for security and maintainability issues?▼

Run a structured audit that establishes a build and test baseline, traces untrusted input into injection sinks, checks authentication and authorization boundaries, and reviews duplication, complexity, and dead code. Each finding needs confirmed reachability and a concrete failure or maintenance impact before being reported.

What does a code health audit cover beyond linting?▼

Beyond linting, a code health audit covers delivery gates like skipped CI checks and non-reproducible builds, dependency vulnerabilities verified against installed versions, concurrency hazards such as race windows and lock ordering, and lifecycle concerns like graceful shutdown and resource cleanup.

How are audit findings prioritized by severity?▼

Findings are classified as P0 through P3 based on exploitability, data or availability impact, delivery blockage, recurrence, and remediation urgency. Only findings with distinct root causes and concrete impact at the repository's evidenced scale are scored.

When should I use a general codebase audit instead of a specialist review?▼

Use a general codebase audit when no single concern dominates and you need broad coverage of security, delivery, and maintainability. Choose specialist audits for documentation trust, test portfolio quality, whole-architecture boundaries, or persistence-specific issues.

Does a codebase audit modify or fix the code it reviews?▼

No, the audit is strictly read-only. It runs only repository-defined or safe diagnostic commands, never rewrites files, deploys, migrates data, or rotates secrets, and reports findings with recommended remediations instead of applying them.

Related Skills

Explore More Software Engineering Skills→
tachiiri-orgtachiiri-org

onboarding

Classify a repository's role and runtime, load guidance, and prepare a Git baseline.

Official
Intermediate
SynkraAISynkraAI
3.1k

aiox-apply-qa-fixes

Applies QA gate findings to a story and hands back for re-review.

Official
Intermediate
B0yZ4kr14B0yZ4kr14

docguard-review

Run docguard-cli diagnose, score, and guard to generate severity-ranked markdown documentation reports.

Community
Advanced
anajuliabitanajuliabit
6

workflow-security-audit

Audit GitHub workflow definitions and composite actions for security regressions.

Community
Advanced