/

/

Cursor and Claude Code spend per developer

Cursor and Claude Code spend per developer

Cursor and Claude Code spend per developer

Track AI coding tool spend per user and per model, from Cursor and the Anthropic Claude Code connector, next to the rest of your cloud.

Runs in

Claude · Slack

First optimization recommendation

The next day

ROI

Pays for itself with the first recommendation you act on

Costory app dashboard 'Claude models usage': waterfall chart of cost change by Claude model over 12 months, a cost distribution donut and a cost details table, in the demo workspace

Playbook

What the agent does

From what Costory notices to what you decide. Costory suggests the next step in conversation, and you decide whether to go ahead.

Costory notices

Monthly, or when a team's AI coding spend jumps.

Context used

Billing data only

Billing data only

Remembered

The user-to-team mapping is defined in your Context layer.

The user-to-team mapping is defined in your Context layer.

Costory investigates

01

Connect Cursor

Admin API key or Terraform; per-user spend via user email, and per-model usage.

02

Connect Claude Code

Anthropic Admin API key; per-actor attribution by user email or API key name.

03

Group by team

Map users to teams.

04

Review monthly

A report per engineering team.

Where you see it

Claude

You decide

Engineering managers decide on plans, models or budgets.

Why it matters

AI coding tools went from a few seats to a real budget line. Engineering leaders need to see who uses what, and which models drive cost.

Who it’s for

Engineering managers, CTOs, finance

Where it runs

Claude · Slack

What you get

What lands in front of your team

Spend per developer

Spend per developer and per model.

Team rollups

Budgets per engineering team.

Next to cloud

AI tools in the same cost model.

Sources and assistants

What it connects

The billing data, context and assistants this playbook uses. Each links to its setup page.

The billing data, context and assistants this playbook uses. Each links to its setup page.

Example prompts

Or drive it yourself

The agent runs this on its own once set up. These prompts open in Claude, pre-filled, to set it up, review it or dig into a result.

The agent runs this on its own once set up. These prompts open in Claude, pre-filled, to set it up, review it or dig into a result.

Review

Show last month's Cursor and Claude Code spend per developer and per model, grouped by team.

Spot

Which teams' AI coding spend grew fastest this quarter, and which models drove it?

FAQ

Questions about this playbook

Can we see spend per developer?

Yes. Cursor spend is attributed by user email, and the Anthropic Claude Code connector attributes usage by user email or API key name.

Is claude.ai Enterprise supported too?

Yes, through the separate Anthropic Claude AI connector, which imports per-user cost with an Analytics API key.

Which agents and assistants work with Costory?

Claude, Claude Code, Cursor, VS Code with GitHub Copilot and Dust connect to the hosted Costory MCP server with OAuth.

Does Costory change anything in our cloud accounts?

No. Costory reads billing exports and the metrics you connect, and has no write access to your cloud. Actions it takes create Costory objects only: alerts, reports, dashboards and events. Your team stays in control of every change.

Step-by-step guide in the Costory docs

Put this playbook on call

Included in every plan, from €250/month. 30-day free trial: connect in under 30 minutes, get your first optimization recommendation the next day.

First optimization recommendation

The next day

ROI

Pays for itself with the first recommendation you act on

Setup

About 30 minutes

Data residency

EU

Access

Read-only on your cloud