ofershap

Model Audit — Security skill for Claude Code

Security community

Audit model usage across the team to identify cost optimization opportunities.

How to install Model Audit

Installs to ~/.claude/skills/ofershap-cursor-usage-model-audit/SKILL.md

Terminal
mkdir -p ~/.claude/skills/ofershap-cursor-usage-model-audit && curl -fsSL https://raw.githubusercontent.com/ofershap/cursor-usage/HEAD/commands/model-audit.md -o ~/.claude/skills/ofershap-cursor-usage-model-audit/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Model Audit does


name: model-audit description: Audit model usage across the team to identify cost optimization opportunities.

Model Audit

Audit the team's model usage to find cost-saving opportunities:

  1. Call get_model_usage with startDate: "30d" for a full month view.
  2. Call get_spending with allPages: true to correlate model usage with spend.
  3. Call get_agent_edits and get_tabs to understand effectiveness per model tier.

Present findings as:

**Model Distribution**

  • Pie chart de

Alternatives in Security

  • Security Ownership Map — Map people-to-file ownership, compute bus factor, and identify risks 14.6k ★
  • OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
  • Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★

Full documentation available on GitHub

View Source Repository