Cross Persona Audit — Security agent for Claude Code
Audits the 5 kern persona definitions for structural divergence.
How to install Cross Persona Audit
Installs to ~/.claude/agents/raymondware-kern-cross-persona-audit.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/raymondware/kern/HEAD/agents/cross-persona-audit.md -o ~/.claude/agents/raymondware-kern-cross-persona-audit.md Restart Claude Code, or start a new session, for it to be picked up.
What Cross Persona Audit does
name: cross-persona-audit model: claude-sonnet-4-6 description: Audits the 5 kern persona definitions for structural divergence. Detects dimensions where two or more personas would produce visually similar output, flags overlap, and produces a pairwise divergence matrix. Run when persona files are modified or when a new persona is added.
Cross-Persona Audit
You are a structural divergence auditor for the kern skill's 5 design personas. Your job is to read the 5 persona reference file
Alternatives in Security
- Token Auditor — Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d 79.4k ★
- Aspm Correlator — Application Security Posture Management persona 548 ★
- Electron Ipc Engineer — Use this agent for any change that touches Electron IPC — adding/removing channels, modifying main.ts ↔ preloa 204 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Dual Channel Drift Auditor
Cold pairwise audit of a declared @dual-pair anchor group. Given ONLY an anchor (never the PR diff or narrativ
Audit Cluster
Maps topic clusters, detects keyword cannibalization via SERP overlap, validates hub-spoke internal linking, i
Audit Sxo
Performs SERP backward analysis, page-type mismatch detection, user story derivation, persona scoring, and gap
Type Auditor
Short-lived agent that consolidates duplicate type definitions found across parallel stories. Spawned by wave-
AI Security Reviewer
Use this agent when reviewing AI-related code (prompts, agent loops, RAG systems, tool definitions, output han
Kavach LLM
KAVACH LLM/AI security specialist. Audits prompt injection (direct + indirect/RAG), jailbreak/persona/system-p
Related Skills
Muse:Benchmark
Muse persona benchmark — measures distinctiveness, voice discipline, schema compliance, and mode fit across al
Agent Audit
Audit a clarc agent file for quality across 8 dimensions — instruction clarity, model appropriateness, tool co
Persona Gen
Generate detailed user personas for your product