Pantheon Audit — Security skill for Claude Code
Audit: heuristic scan (zero LLM) + Themis review.
How to install Pantheon Audit
Installs to ~/.claude/skills/ils15-pantheon-legacy-pantheon-audit/SKILL.md
mkdir -p ~/.claude/skills/ils15-pantheon-legacy-pantheon-audit && curl -fsSL https://raw.githubusercontent.com/ils15/pantheon-legacy/HEAD/commands/pantheon-audit.md -o ~/.claude/skills/ils15-pantheon-legacy-pantheon-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Pantheon Audit does
description: "Audit: heuristic scan (zero LLM) + Themis review. Usage: /pantheon-audit [--light|--full|--plan]" agent: "themis"
/pantheon-audit — Quality & Security Audit
**What:** Layer 1 heuristic scan (zero tokens, <2s). If BLOCKING, returns score. If APPROVED, Themis deep review.
**Usage:**
/pantheon-audit— Full audit (Layer 1 → 2 → 3)/pantheon-audit --light— Layer 1 only (quick scan)/pantheon-audit --full— Force full review/pantheon-audit --plan— Verificat
Alternatives in Security
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
- Beamer Skill — A Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations 163 ★
- Rolecraft — The security-first skill manager for AI agents — every install runs a security scan 75 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Review UX Audit
Full UX audit of a frontend codebase. Produces persona cards, journey maps, heuristic sweep, anti-pattern find
Speckit Workflow V2
Full Spec Kit flow with quality gates: constitution→specify→clarify→plan→contract→checklist→tasks→analyze→impl
Security 0day
Scan the current branch's diff (vs main) for 0-day-style vulnerabilities. Light, fast, PR-focused.
Fd Verify
FlowDeck pipeline stage. Verify the implementation by running tests, checking regression on the plan's affecte
LaptopAI Agent
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local
Skills Janitor
Audit, deduplicate, check, fix, and track usage of your Claude Code skills. 9 slash commands, zero dependencie
Related Agents
Themis.Agent
Quality & security gate — heuristic scan (Layer 1, zero LLM) + deep
Figma Analytics
Use to audit the Figma library side of the design system: override hotspots (instances drifted from their main
Light Review FakeTest
Audit a Delphi DUnitX or classic-DUnit test suite for FAKE or WEAK tests — tests that pass without verifying t