cursor-cost-optimization

A Cursor Enterprise usage-analysis guide for reducing AI spending through team usage data and model-selection advice. Cursor is an AI coding editor, and Enterprise teams are organizations using its managed plan.

In plain words
What is it for?
Reviewing team and model usage, finding high-spend patterns, and choosing lower-cost model tiers for code completion, inline edits, and other tasks.
Why use it?
It helps identify whether spending comes mainly from model choice, request volume, or a small group of users, so teams can target the main source of cost.

Skill for Claude CodeCodex

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 skills/ofershap/cursor-usage-plugin/cursor-cost-optimization
Any agent
npx skills add ofershap/cursor-usage-plugin --skill cursor-cost-optimization
Clone the repo
git clone --depth 1 https://github.com/ofershap/cursor-usage-plugin

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00036 $0.01088
Opus 5 $0.00018 $0.00544
Sonnet 5 $0.00007 $0.00218
Haiku 4.5 $0.00004 $0.00109

Measured yesterday against content hash 2ebdedc6c132, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-cost-optimization 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

This is a copy

100% identical to cursor-cost-optimization — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/cursor-cost-optimization/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Cost Optimization

You have access to Cursor Enterprise usage data through the cursor-usage MCP server. This skill teaches you how to identify cost-saving opportunities and recommend actionable changes.

Cost Optimization Framework

Step 1: Understand the Spend Profile

Call get_team_overview to get the baseline, then:

  1. Identify the spend distribution — Is spend concentrated in a few users or spread evenly?

    • If top 10% of users account for >50% of spend → focus on those users
    • If spend is evenly distributed → focus on model selection policies
  2. Identify the cost driver — Is it model choice, volume, or both?

    • Call get_model_usage to see which models dominate
    • Premium models (Opus, GPT-5) at 10-50x the cost of standard models (Sonnet, GPT-4o)
    • A team of 50 where 5 people use Opus can spend more than the other 45 combined

Step 2: Model Selection Optimization

The single highest-impact cost lever is model selection.

Task Type Recommended Model Tier Why
Code completion / tabs Budget (Flash) High volume, low complexity, latency-sensitive
Inline edits (Cmd+K) Standard (Sonnet, GPT-4o) Good balance of quality and cost
Chat conversations Standard Most questions don't need frontier models
Agent mode (complex tasks) Premium (Opus) only when needed Reserve for genuinely complex multi-step work
Code review Standard Pattern matching, not creative generation

Key insight: Most developers default to the "best" model out of habit, not necessity. 80%+ of requests can be handled by standard-tier models with no noticeable quality difference.

Step 3: Spend Limits

Use set_spend_limit to set guardrails:

Read the full file on GitHub · 87 lines

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 · 87 lines · 36 tokens per session scan A 2ebdedc6c132

Subscribe to this mod's changes

cursor-cost-optimization is a skill published in the GitHub repository ofershap/cursor-usage-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,088 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursor-cost-optimization, differing in 0 lines, and is treated as a copy.