Skip to content
Book a callSkip the hiring grind

Day 37 of 52 · about 15 min · Basics · Bonus

See how your team uses Claude Code

Deciding whether Claude Code is worth it takes numbers: who uses it, what it ships and what it costs. The analytics dashboard shows adoption and contribution, and OpenTelemetry sends usage and cost metrics to the monitoring you already run.

You’ll finish with

  • A clear picture of what your plan’s dashboard shows, and who can open it
  • Claude Code’s metrics on a local Prometheus page
  • The managed settings that send a whole team’s metrics to your collector

You’ll need

  • For the dashboard: a Team or Enterprise Admin or Owner role, or a Console role with the UsageView permission
  • Contribution metrics are in public beta on Team and Enterprise and need GitHub connected
  • For OpenTelemetry: Claude Code on any plan and a browser
Start from the practice project as of Day 35 (.zip, 46 KB)

Before you start

Tell us about your setup and the steps change to fit it. Your answers stay in this browser, and you can change them at any time.

Which system are you on?

Commands differ between systems. Pick the one you’ll run Claude Code on.

The steps

One step at a time. When a step’s check matches, tick it and the next one opens.

0 of 4 steps done0%

  1. Step 1 of 4: Open the dashboard for your plan

    Team and Enterprise get adoption and contribution metrics; the Console gets usage and spend.

    Team and Enterprise

    • claude.ai/analytics/claude-code
    • Daily active users, sessions, lines accepted
    • PRs shipped with Claude Code, leaderboard, CSV export

    Claude Console

    • platform.claude.com/claude-code
    • Usage and spend
    • No contribution metrics
    Per-user tokens and cost on Team and Enterprise come from the spend report or OpenTelemetry.

    Check it worked

    The dashboard opens and shows daily active users or usage for your organization.

  2. Step 2 of 4: Turn on contribution metrics

    Connect GitHub so merged pull requests show the work done with Claude Code.

    In order:

    1. Install the Claude GitHub app

      A GitHub admin, at github.com/apps/claude

    2. Enable Claude Code analytics

      An Owner, at claude.ai/admin-settings/claude-code

    3. Turn on GitHub analytics

      Same page, then sign in to GitHub and pick organizations

    4. Wait for data

      Usually within 24 hours, then daily

    Not available with Zero Data Retention. The counts are deliberately conservative.

    Check it worked

    The summary shows PRs with CC, or "Data processing in progress" while it fills.

  3. Step 3 of 4: Try OpenTelemetry on your machine

    Serve Claude Code’s metrics on a local Prometheus page to see what it reports.

    For macOS, Linux and WSL

    Terminal

    Run: export CLAUDE_CODE_ENABLE_TELEMETRY=1

    Run: export OTEL_METRICS_EXPORTER=prometheus

    Run: claude

    What happens: While it runs, open http://localhost:9464/metrics in a browser.

    Set for this terminal only. Close it to stop.

    For Windows

    PowerShell

    Run: $env:CLAUDE_CODE_ENABLE_TELEMETRY = "1"

    Run: $env:OTEL_METRICS_EXPORTER = "prometheus"

    Run: claude

    What happens: While it runs, open http://localhost:9464/metrics in a browser.

    Set for this PowerShell window only. Close it to stop.

    Check it worked

    Send one prompt, then reload the page: it lists Claude Code’s metrics as plain text.

  4. Step 4 of 4: Send the team’s metrics to your collector

    Admins set the same variables in managed settings, pointed at an OTLP collector.
    managed-settings.json
    env.CLAUDE_CODE_ENABLE_TELEMETRY: "1"
    Required to turn telemetry on
    env.OTEL_METRICS_EXPORTER: "otlp"
    Send metrics over OTLP
    env.OTEL_EXPORTER_OTLP_PROTOCOL: "grpc"
    Required: there is no default
    env.OTEL_EXPORTER_OTLP_ENDPOINT: "http://collector.example.com:4317"
    Your collector
    A repository’s .claude/settings.json can’t turn telemetry on.

    Prompt text stays redacted unless you set OTEL_LOG_USER_PROMPTS=1. Tell your team what you collect.

    Check it worked

    Your backend receives claude_code.session.count after a teammate starts a session.

    If it didn’t work

    Nothing arrives

    Start Claude Code with claude --debug-file <path> and look for [3P telemetry] errors in that file.

Finish · 4 of 4 steps to go

You can see adoption, output and cost

Read the trend monthly, and ask your most active users to share what works for them.

What you’ll have checked

  • You know which dashboard your plan has
  • Claude Code’s metrics reach a page or backend you control

Lesson updates by email

Get lesson updates by email

Leave your email and we’ll tell you when we add or update a lesson.

We’ll email you when we add or update a lesson. We use your email only for this. Privacy policy

Claude Code for your team

Want Claude Code set up across your team?

HorizonLux sets up and repairs Claude Code for teams: CLAUDE.md rules, hooks that enforce them and reviewed MCP servers. Book a free call to talk it through.

Book a free call Claude Code agency

Related

Free tool

AI Agent Cost Estimator

How we build

AI software factory

Questions

Questions about Day 37

Does the dashboard count API key usage?

Contribution metrics cover only users in your claude.ai organization, not Console API or third-party usage.

Sources

Checked against the official Claude Code docs on .

Independent resource, not affiliated with Anthropic. HorizonLux wrote this lesson; Claude Code is made by Anthropic.