Agent Native Audit — Security skill for Claude Code
Run comprehensive agent-native architecture review with scored principles.
How to install Agent Native Audit
Installs to ~/.claude/skills/barkleesanders-claude-code-starter-agent-native-audit/SKILL.md
mkdir -p ~/.claude/skills/barkleesanders-claude-code-starter-agent-native-audit && curl -fsSL https://raw.githubusercontent.com/barkleesanders/claude-code-starter/HEAD/commands/agent-native-audit.md -o ~/.claude/skills/barkleesanders-claude-code-starter-agent-native-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Native Audit does
name: agent-native-audit description: Run comprehensive agent-native architecture review with scored principles argument-hint: "[optional: specific principle to audit]"
Agent-Native Architecture Audit
Conduct a comprehensive review of the codebase against agent-native architecture principles, launching parallel sub-agents for each principle and producing a scored report.
Core Principles to Audit
- Action Parity - "Whatever the user can do, the agent can do"
- **Tools as Pr
Alternatives in Security
- FastAPI Review — Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu 243.5k ★
- Brooks Audit — Run a Brooks-Lint architecture audit 1.5k ★
- OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Security Engineer
Expert application security engineer specializing in threat modeling, vulnerability assessment, secure code re
Reviewgate
Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini
AI Engineering Skills
Focused Claude Code / Cursor skills for systematic AI-native engineering: codebase discovery, security review,
Review Code Maintainability
Structural maintainability audit: god objects, hidden coupling, dead code, comment-standard compliance, and dr
Review CSS Architecture
Audit CSS and design-token usage against the console-idiom rubric: ad hoc overrides, magic values, duplicated
Intent Engineering
Enforce intent engineering: a Claude Code plugin with 5 review lenses (predictability, convention, simplicity,
Related Agents
Gsd UI Auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd-
Thrunt UI Auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /thru
Channel Auditor
Produces a scored channel health report across packaging and SEO, performance, content strategy and monetizati