Reflexion — Security skill for Claude Code
Audit and optimize the .claude/ ecosystem — skills, hooks, guides, patterns, agents, and settings — for quality, coherence, and token efficiency.
How to install Reflexion
Installs to ~/.claude/commands/ncoevoet-facet-reflexion.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ncoevoet/facet/HEAD/.claude/commands/reflexion.md -o ~/.claude/commands/ncoevoet-facet-reflexion.md Restart Claude Code, or start a new session, for it to be picked up.
What Reflexion does
description: Audit and optimize the .claude/ ecosystem — skills, hooks, guides, patterns, agents, and settings — for quality, coherence, and token efficiency. Use when reviewing configuration health, fixing dead references, improving skill triggers, or optimizing the instruction budget.
You are a `.claude/` ecosystem auditor. Scan silently (no intermediate output), then present a flat prioritized report.
Phase 0 — Conversation History Analysis
Review the full conversation history i
Alternatives in Security
- Beamer Skill — A Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations 163 ★
- Agentlinter — ESLint for AI Agents — AGENTS.md/CLAUDE.md 채점·진단·자동수정 Position Risk Warning · Token Efficiency · Security Chec 78 ★
- Cross Review — Use when: reviewing high-stakes changes such as security-sensitive code, public API changes, or data migration 62 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
J Config Audit
Security audit of Claude, Codex, Gemini, and shared agent configuration for secrets, over-broad permissions, a
Optimizing Skills Performance
Audit and optimize AI agent skills for token efficiency using progressive disclosure principles
Aisecscan
Static security scanner for Claude Code configuration — settings, permissions, hooks, MCP servers, agents/suba
Agent Config Audit
Audit AI agent configuration files for security risks: risky permissions in .claude settings, secrets and unpi
Cchub
Desktop hub for managing Claude Code MCP servers, health checks, configuration profiles, skills, plugins, hook
Optimize Harness
Audit one or all supported agent harnesses for config efficiency, hook overhead, permission friction, plugin a
Related Agents
Automation Sentinel
Use this agent to monitor, analyze, and optimize the automation ecosystem (agents, commands, hooks). This is a
Context Analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the use
Academic Historian
Expert in historical analysis, periodization, material culture, and historiography — validates historical cohe