cursor-usage-analysis

A guide for correctly interpreting Cursor Enterprise usage data, including team spending, usage patterns, and model adoption. Cursor is a coding editor with built-in AI features.

In plain words
What is it for?
Use it to review team AI costs, compare usage over time, investigate individual users, and understand Cursor usage metrics.
Why use it?
Raw usage numbers can be misleading, especially when plan-included spending, extra charges, and premium-model requests are counted separately.

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

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,535 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 $0.00051 $0.01535
Opus 5 $0.00026 $0.00767
Sonnet 5 $0.00010 $0.00307
Haiku 4.5 $0.00005 $0.00153

Measured yesterday against content hash 958b8a3f2034, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-usage-analysis 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-usage-analysis — 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-usage-analysis/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Usage Analysis

You have access to Cursor Enterprise API data through the cursor-usage MCP server. This skill teaches you how to interpret that data correctly — the API returns raw numbers, but understanding what they mean requires context that isn't in the docs.

Before You Start

  1. Use the get_team_overview tool first to orient yourself — it gives you the big picture in one call.
  2. For user-specific questions, use get_user_deep_dive with their email.
  3. For time-range analysis, all analytics tools accept startDate and endDate.

Critical Data Interpretation Rules

Spending

  • spendCents is the total spend including the subscription-included amount. To get overage (extra cost beyond the plan), subtract includedSpendCents.
  • A user with spendCents: 5000 and includedSpendCents: 4000 has $10 in overage, not $50 in total extra cost.
  • fastPremiumRequests counts requests to premium/expensive models (Opus, GPT-5, etc.) that consume the fast request quota faster.
  • Spend limits (hardLimitOverrideDollars) only cap overage spend, not included spend. A limit of $0 means "no overage allowed," not "no usage allowed."

Lines of Code Metrics

  • totalLinesAdded includes ALL lines: agent-suggested, tab-completed, and manually typed. It is NOT a measure of AI productivity.
  • acceptedLinesAdded is the real AI productivity metric — lines the user explicitly accepted from AI suggestions.
  • The acceptance rate (acceptedLinesAdded / totalLinesAdded) is misleading because the denominator includes manual edits. Use totalAccepts / totalApplies for the true AI acceptance rate.
  • Agent mode lines are counted in totalLinesAdded but may not appear in acceptedLinesAdded because agent mode auto-applies changes.

Request Types

  • composerRequests: Inline edit requests (Cmd+K / Ctrl+K)
  • chatRequests: Chat panel conversations
  • agentRequests: Agent mode (autonomous multi-step tasks)
  • usageBasedReqs: Requests that count against the usage-based billing tier (overage)
  • cmdkUsages: Legacy name for composer/inline edit usage
  • bugbotUsages: Automated bug detection runs

Read the full file on GitHub · 120 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 120 lines · 51 tokens per session scan A 958b8a3f2034

Subscribe to this mod's changes

cursor-usage-analysis is a skill published in the GitHub repository ofershap/cursor-usage-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 1,535 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursor-usage-analysis, differing in 0 lines, and is treated as a copy.