Code Lexica logo
Track · Free forever

See your team's AI usage.
Then get more from it.

Track shows what Claude Code, Codex, and Cursor actually deliver for what you pay. True Cost by member, model, repo, and tool, explained in a weekly briefing.

  • Free forever, with a full team dashboard and unlimited members
  • True Cost across Claude Code, Codex, and Cursor, the API-rate value every seat delivers
  • Weekly briefings that explain what changed and why
  • A team leaderboard you can share org-wide, no accounts needed
  • Install the CLI, run cdlx init, and you're tracking in 5 minutes
5-minute setup Unlimited team members No credit card
Weekly AI Usage BriefingJul 6 – Jul 12
Emailed

AI usage rose 13% this week, led by the checkout-service payments push. The team pulled $1,015 of API-rate value from its plans, on pace for 2.4× what the seats cost this month. Worth watching: Claude Code is now 62% of True Cost, up from 48%.

checkout-service True Cost +34% — Opus 4.8 on a large refactor
alex@acme.dev drove 21% of org tokens (mostly Opus)
Cursor usage flat; Claude Code up 18% week-over-week
LLM Usage Dashboardacme.dev · last 30 days
All tools
Tokens (30d)418M
API-rate value$4,350
You paid$1,800
Extracted value+$2,550(2.4×)
Claude CodeCodexCursor
Team Leaderboardacme.dev · last 30 days
Shared org-wide

Together: 418M tokens · $4,350 of API-rate value

You paid $1,800 · extracted +$2,550 (2.4×) beyond it

PS

Priya Sharma

75.2Mtok

9-day streak

+$583(3.9×)
AR

Alex Rivera

87.8Mtok

12-day streak

+$713(4.6×)
SC

Sam Chen

58.5Mtok

5-day streak

+$409(3.0×)
Weekly briefing
Tracks the tools your team already uses
Claude Code
Codex
Cursor
GitHub CopilotSoon
Gemini CLISoon
The utilization problem

Every AI seat is a bet. Most orgs can't see the payoff.

You rolled out Max plans, Cursor seats, Copilot licenses. Then the economics shifted under you: Anthropic moved programmatic usage to full API rates, and Copilot metered agent mode. Meanwhile nobody can answer the basic questions. Who's actually using their seat? Which ones sit idle? Are your heaviest users throttled by limits mid-week?

The stakes compound because agent usage is enormous. Most of those tokens go to waste, and a single complex task on Opus 4.8 can burn double-digit dollars in API tokens for one PR.

The teams that thrive in the next phase won't have the biggest budgets. They'll know exactly what they're using, and they'll get the most from every seat.

~70%

of agent tokens are waste: re-grep'ing, re-reading, exploring dead ends. (Stanford agent-trace research)

$10–$15

API tokens burned per complex SWE-Bench Pro task on Opus 4.8.

25×

effective cost increase for teams running claude -p on subsidized Max plans after the June 2026 shift.

What Track shows you

Your whole team's AI usage, and the value behind it

Everything below ships in the free plan, in full.

Every tool, one dashboard, real value

Usage and True Cost across Claude Code, Codex, and Cursor in a single team-level view, so you can see the API-rate value each seat delivers.

Breakdowns that reconcile

Slice usage by member, model, repo, and tool. Every table reconciles 1:1 with the headline numbers, so the totals always add up.

Briefings that explain the why

Every week, Track reads your usage data and writes you the story: what changed, what drove it, and what to do about it. Delivered by email and in-app.

Rate-limit & error visibility

See usage-limit hits, thresholds, and API errors across your team. When your best people get throttled mid-week, the plan is costing you shipped work.

Team leaderboard

Max out your Max plans — together

Adoption grows when it's visible and celebrated. The leaderboard ranks your team by usage: top-3 podium, daily streaks, and a team-total banner that celebrates what you've extracted together. It only ever cheers the front of the pack; nobody gets shamed for a quiet week.

With plan detection, every row shows extracted value in real dollars, so you can see who's pulling multiples of their seat cost out of their Max plan. The people making AI work become the example, and everyone else can see what good looks like.

Then share one link with the whole org. Anyone with a company email can view the board after a quick email code, without an account or a seat.

Team Leaderboardacme.dev · last 30 days
Shared org-wide

Together: 418M tokens · $4,350 of API-rate value

You paid $1,800 · extracted +$2,550 (2.4×) beyond it

PS

Priya Sharma

75.2Mtok

9-day streak

+$583(3.9×)
AR

Alex Rivera

87.8Mtok

12-day streak

+$713(4.6×)
SC

Sam Chen

58.5Mtok

5-day streak

+$409(3.0×)
4JLJordan Lee50.2M+$322(2.6×)
5?Anonymous46.0M+$278(2.4×)
How it works

Tracking in 5 minutes

Two commands in a terminal. You won't paste an API key or route through a proxy, and nothing changes in anyone's workflow.

1

Install the CLI

One command, every major platform.

brew install codelexica/tap/cdlx
2

Initialize

Sign in and pick the repos or directories to track.

cdlx init
3

Watch the dashboard fill in

Usage appears within minutes. Invite the team, or let domain auto-join do it for you.

Teams on Track

Why teams keep it running

Most tools will tell you how many tokens you're consuming. What's been more valuable for us is understanding why usage changed from one week to the next. The insights make the product really useful.
TD

Tom DeMichele

CEO, DogMedia Solutions

As model pricing and usage continue to change, we wanted a better understanding of our exposure. Track gave us a clearer picture of how AI was being used across teams and where costs were trending.
MB

Matt Blizel

Founder, Atlevo

No catch

How is Track free?

Free dev tools have burned people before, so here's the business model, out loud.

Permanent, not a trial

Track is free forever: the full team dashboard, True Cost, briefings, and unlimited members. No credit card, no usage meter counting down, no surprise paywall on features you already rely on.

Visibility is cheap to serve

Track ingests usage metadata, not your source code. Serving a dashboard and a weekly briefing costs us very little, so we can afford to give it to every team, at any size.

Optimize pays the bills

Our paid product, Optimize, stretches the budget Track measures. We only make money when we make your AI spend go further. The tracker stays free, and everything free today stays free.

OptimizeComing soon

Next: same plans, more shipped.

Optimize plugs a context layer into the agent you already use, so each task takes fewer tokens and the same plan ships more. Your plan lasts deeper into the week, and your workflow doesn't change. The SWE-Bench Pro benchmark publishes soon. Learn how it works.

Make your plans go further

Join the Optimize waitlist. Track members get first access when it ships.

Who it's for

Built for the people paying the agent bill

Engineering Leaders

CTOs, VPs, Directors

  • Walk into renewals knowing which seats paid for themselves
  • Board-ready numbers for AI spend and the value it returned
  • A weekly briefing that explains the why, delivered to your inbox
  • Free for the whole team, unlimited members

Platform Teams

Platform, DevEx, AI Tooling Leads

  • One rollup across Claude Code, Codex, and Cursor, with no OTel stack to run
  • See which seats go unused and which hit their limits
  • Domain auto-join onboards the whole org in minutes
  • CSV export for FinOps, showback, and audits

Developers

Engineers, Tech Leads

  • See your own usage and True Cost — team-level, not surveillance
  • Two commands to set up, and nothing changes in your workflow
  • Know when you're approaching plan limits mid-task
  • Prove your Max plan pays for itself

Know your AI usage. Then get more from it.

Start tracking your team's usage and True Cost free in 5 minutes. When you're ready, Optimize stretches every subscription further.