Audit Models — Security skill for Claude Code
Audit subagent model assignments for quality or budget optimization.
How to install Audit Models
Installs to ~/.claude/commands/rolandtolnay-mindsystem-audit-models.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/rolandtolnay/mindsystem/HEAD/.claude/commands/audit-models.md -o ~/.claude/commands/rolandtolnay-mindsystem-audit-models.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Models does
description: Audit subagent model assignments for quality or budget optimization argument-hint: ""
Audit all Mindsystem subagent model assignments against current model capability benchmarks. Recommend optimal model for each agent based on the audit mode:- quality — Maximize output quality. Only downgrade where output is effectively identical.
- budget — Minimize cost. Keep larger models only where the quality gap impacts downstream results. </objec
Alternatives in Security
- Security Threat Model — Generate repo-specific threat models identifying trust boundaries 14.6k ★
- Pal — Multi-model AI integration — chat, debugging, code review, planning, security audit 11.3k ★
- Audit Agent Sessions — Analyze all agent sessions from the last 3 days across Claude, Codex, and Gemini 238 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Skill Suite
Claude Code skills for running models cost-effectively: security gates (secret scanner, commit-gate), model-qu
Jgs Magic Sysmlv1 MCP
Bring Claude Code and any MCP agent to your live SysML v1 models in CATIA Magic: 130+ tools to query, audit, a
Model Audit
Audit model usage across the team to identify cost optimization opportunities.
Token Optimizer Skill
Token cost optimization skill for Claude Code — model routing (Opus/Sonnet/Haiku), extended thinking tuning, p
Xiaoyaoclaw SEO Skill
SEO analysis & optimization skill for any website: audit technical SEO, on-page, content quality, schema and A
Agent Audit
Audit a clarc agent file for quality across 8 dimensions — instruction clarity, model appropriateness, tool co
Related Agents
Budget
AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits
Data Builder
Builds and audits datasets for tiny models — synthetic generation, teacher labelling, held-out splits, and lab
Fleet Implement Cheap
Bulk or low-stakes implementation on budget or free models: mechanical edits, boilerplate, and large repetitiv