Actionable intelligence for Claude Code
Recon measures how much Claude Code each person really uses: what it would cost at API prices, and how much of their subscription quota they get through. You see who needs a premium seat, who'd be fine on standard, and who'd cost less on an API budget. The data never leaves your infrastructure.
| Est. cost | 5-hour quota | |||
|---|---|---|---|---|
| Person | a month | average | highest | Rating |
| priyaPremium | $412.60 | 71% | 100% | |
| samStandard | $188.05 | 38% | 64% | |
| leePremium | $46.10 | 9% | 17% | |
| kimStandard | $7.85 | 2% | 6% | |
Premium seats cost several times a standard one. Without usage figures you can't tell who's getting the value.
Someone who opens Claude Code twice a week may cost far less on pay-as-you-go API usage than on a subscription.
People who hit their 5-hour or weekly limit mid-task lose time. You only hear about it when they ask for more.
Decisions it answers
Standard seat or API budget?
Compare each person's monthly cost at API prices with the price of their seat. When it's consistently lower, an API token budget is the cheaper way to give them Claude Code.
Evidence: estimated cost per person, by month, and an amber rating under £20 a month
Is the premium seat paying for itself?
See how much of their quota Premium seat holders actually use, window after window. If the average and the highest stay well within a standard seat's limits, move them down.
Evidence: each account's seat, its average and highest quota per completed window, and a red rating when a Premium seat stays under 20%
Who needs more?
People whose 5-hour and weekly windows regularly peak at their limit are being slowed down. They're your case for an upgrade, with the figures to back it.
Evidence: quota peaks, live and over time
Which models earn their cost?
Split usage by model to see where the most capable model is used, and where a smaller, cheaper one would do the same job.
Evidence: cost and tokens by person and model
Recon gives you the figures and flags the seats to look at; the call is yours. It doesn't need to know your seat prices, and it never sees what people use Claude for.
What you see
A red, amber or green rating for each Claude account: Premium seats barely used, and light users who may cost less on API tokens. Hover over a rating to see why.
Estimated cost, input, output and cache tokens, and active time per person, across all their devices, with each Claude account's seat: Premium, Standard or Personal.
The same figures split by model, so you can see where Opus is worth it and where a smaller model would do.
Each person's live 5-hour and 7-day quota, plus the average and highest of their completed windows: how much of a seat they really use.
Which laptops are sending, which agent version they run, and whether your stack is healthy. Revoke a device and it stops at once.
Admins and viewers see everyone. Members see only their own figures. Filter by your verified domains, or by accounts outside them.
Every report request, setting change and sign-in is recorded in a tamper-evident log you can read.
How it works
A small agent on each laptop reads Claude Code's own usage metrics and status line, and sends 5-minute totals per model. Nothing per turn.
Runs on your infrastructure, on Docker or Kubernetes. Devices send to it over your network, and it keeps the figures in its own database.
Your stack connects out to Recon over an encrypted tunnel. Reports stream through the portal to your browser and aren't kept anywhere along the way.
Setup: a stack per organisation. On each laptop, a signed installer for macOS or Windows from the portal, an enrolment key, then one command connects Claude Code. On a Docker stack, turn on auto-update and agents keep themselves current.
Security and privacy
We're onboarding a small number of organisations. You get the full product, direct access to the team, and a say in what comes next.
FAQ
It gives you the evidence: each person's cost at API prices, and how much of their quota they use window after window. Recon shows which seat each account holds and rates each one red, amber or green, so the accounts to look at stand out. It doesn't know your seat prices, so the decision stays with you.
No. The agent keeps only totals: estimated cost, token counts, active time and quota, per model, per 5 minutes. Prompts, responses, file paths and session IDs never leave the laptop.
It's Claude Code's own estimate of what the usage would cost at API prices. On a subscription that tells you the value people get and which models drive it. Recon labels it as an estimate everywhere.
Every Claude account used on an enrolled laptop, personal ones included; reports show an account outside your verified domains by its domain only. Usage figures come from any Claude Code account. Subscription quota needs a subscription account: API-key accounts don't report quota, and Recon shows it as unknown rather than zero.
A small Linux VM (2 vCPU, 4 GiB, around 1,000 devices) with Docker, or a Kubernetes namespace. The stack needs outbound access to Recon only, and devices need to reach it on your network or VPN.
Only if you turn operator access on, and you can turn it off at any time. Your stack enforces the setting, and every access is audited.
Revoke their devices from the portal and their stack refuses them at once. Their sign-in can be deactivated the same way, and you can pseudonymise them: their name and email become a random pseudonym everywhere, and their figures stay in your reports.