model-audit

A command that reviews which AI models a team uses and how that relates to cost and coding results. It compares model distribution, spending, and measures such as accepted edits and tab completions.

In plain words
What is it for?
Finding costly model usage, comparing premium, standard, and budget models, estimating savings from changes, and suggesting spending limits.
Why use it?
Teams may use expensive models for work that less costly models could handle. This audit links model choices to usage and results so possible savings can be identified.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/ofershap/cursor-usage/model-audit
Clone the repo
git clone --depth 1 https://github.com/ofershap/cursor-usage
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 226 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00226
Opus 5 $0.00008 $0.00113
Sonnet 5 $0.00003 $0.00045
Haiku 4.5 $0.00002 $0.00023

Measured yesterday against content hash b2107bb01346, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

commands/model-audit.md · 35 lines

What it actually says

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 description: what % of messages go to each model
  • Premium vs standard vs budget model split

Cost Impact

  • Estimated cost per model (messages × approximate cost per request)
  • Which models are driving the most spend

Optimization Opportunities

  • Users heavily using premium models for tasks that standard models handle well
  • Specific recommendations: "User X could save ~$Y/month by switching from [model] to [model] for [task type]"

Action Items

  • Ranked list of changes by estimated savings
  • Suggested spend limits if appropriate
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 35 lines · 16 tokens per session scan A b2107bb01346

Subscribe to this mod's changes

model-audit is a command published in the GitHub repository ofershap/cursor-usage (8 stars, last pushed 6mo ago), licensed MIT. It adds 16 tokens to every session and 226 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.