Zest

AI CODING ANALYTICS

Claude Code usage dashboard
for your whole team.

Run /usage in Claude Code to see your session cost and how much of your plan's limits is used. Claude Code analytics for Team and Enterprise owners are at claude.ai/analytics/claude-code; Zest adds each engineer's sessions, models and tokens next to the pull requests they merged.

Start free
npx @winding-labs/zest

Free for 3 seats · No credit card · One command signs in every agent on your machine

Sample data

Stack in the Zest app: how well your setup is wired, and what raises the score

YOUR OWN NUMBERS

See your own Claude Code month

Pick the .claude folder in your home folder and this page reads the session logs Claude Code keeps there: your sessions, active days, projects, tokens, models and skills from the last 30 days. It reads them in this browser tab, with no terminal.

The folder is hidden. On a Mac, go to your home folder in the window that opens and press Cmd Shift . to show it. On Windows, paste %USERPROFILE%\.claude into the window's address bar.

This reads a folder on your computer, so open the page on a laptop to see your month. You can sign up now and connect Claude Code from your computer later.

Your Claude Code, last 30 days

Sessions
Days with Claude Code
Projects
Tokens

Models

    Skills

      Busiest projects

        This is one laptop, and Claude Code deletes these logs after 30 days by default. Zest records the same numbers every day for everyone on your team, with what the sessions cost and the pull requests they led to.

        Start free

        Read in this browser tab. Nothing leaves your computer.

        USED BY ENGINEERING TEAMS AT

        Flyps Charm Wildfires Geoforge MisaLabs

        How to check your Claude Code usage

        Run /usage inside Claude Code, one of its built-in commands. In the browser, Settings, then Usage on claude.ai shows the same limits. Individual Pro, Max and Ultra plans get no Claude Code usage dashboard from Anthropic; that is for Team, Enterprise and Console.

        /cost and /stats are aliases that open the same /usage screen, which has three parts:

        • Session: tokens per model, API time and lines changed, with a dollar figure Claude Code estimates at list price. On a subscription, that figure is not your bill.
        • Plan usage on Pro, Max, Ultra, Team and Enterprise: how much of your limits is used, and which skills, subagents, plugins and MCP servers used it.
        • Stats for the last 24 hours or 7 days (press d or w), read from this machine's history. Usage on other devices or on claude.ai is not in them.

        How to see team usage on a Claude Team plan

        Claude Team analytics are open to Owners and Primary Owners: click your initials in the lower left of claude.ai, then Analytics, which also has pages for Chat, Cowork and Claude Design. Under Claude Code, each member's accepted lines, plus their pull requests once Anthropic's GitHub app is connected, are listed with a CSV export; the usage numbers cover the current calendar month and reset at the start of each month.

        That page's Usage tab shows the organization's top skills, MCP servers and tools, and its Value tab shows cost per commit, pull request and session and the top spenders, with every formula editable.

        For tokens and estimated spend per person, open Settings, then Analytics, and export the spend report under "How much is Claude costing?". Each row is one person's use of one model, up to the last 90 days. Its dollars cover usage credits only, because use inside a seat's allowance isn't metered in dollars. The Team plan has no analytics API; only Enterprise does. The Claude Code Analytics API in the table covers Console organizations, not usage on a Claude subscription.

        Claude Team analytics goes through the other Analytics pages and what each one shows per member.

        Where Claude Code usage shows per engineer, from Anthropic's docs and Help Center, read November 10, 2026.
        ViewWho opens itPer engineerMerged pull requests
        /usageAnyone, on this machineYour own onlyNo
        Analytics, then Claude CodeTeam and Enterprise owners, Enterprise adminsAccepted lines, a top-10 leaderboard and a CSV of every userYes, with Anthropic's GitHub app (public beta)
        Spend reportTeam and Enterprise ownersTokens and usage-credit spend per modelNo
        Claude Code Analytics APIConsole adminsDaily records per userCounts only
        OpenTelemetryAn admin who runs a collectorThrough user.emailCounts only
        ZestEach engineer installs a pluginEvery sessionEach session next to the pull request it led to

        The Claude Code analytics dashboard for Team and Enterprise

        Owners of a Team or Enterprise plan, and Enterprise admins, open claude.ai/analytics/claude-code. It shows daily active users and sessions, lines of code accepted, the suggestion accept rate, and a top-10 leaderboard you can export for every user as a CSV.

        Install Anthropic's GitHub app and it adds the pull requests and lines shipped with Claude Code's help, a public beta that Anthropic calls a deliberate underestimate. It labels those pull requests claude-code-assisted, so you can search for them on GitHub too. For each engineer's tokens and cost, the docs point to OpenTelemetry or the spend report. API customers get a smaller dashboard at platform.claude.com/claude-code, with each user's spend and lines over a date range you pick, 30 days by default.

        The Claude Code Analytics API

        Claude Console organizations can pull per-user numbers with an Admin API key. One call returns one UTC day, up to 1,000 records a page, with a page cursor for the next. A user or API key can have several records a day, one for each terminal, account type and remote or local session, so add them up for the day's total of sessions, lines added and removed, commits and pull requests by Claude Code, accepted and rejected edits, and tokens and estimated cost per model. The cost is in US cents. Data lags by up to an hour, and Anthropic's API reference lists every field. On Enterprise, claude.ai usage comes from the Claude Enterprise Analytics API instead, with its own key.

        curl "https://api.anthropic.com/v1/organizations/usage_report/claude_code?starting_at=2026-10-04&limit=20" \
          -H "anthropic-version: 2026-10-21" \
          -H "x-api-key: $ANTHROPIC_ADMIN_KEY"

        Claude Code monitoring with OpenTelemetry (OTel)

        For your own dashboards, Claude Code exports OpenTelemetry metrics and events to a collector you run. An admin can set the same variables for every engineer in the env block of the managed settings file. We ran the setup end to end and wrote up a tested collector config, the queries and two traps in Claude Code monitoring with OpenTelemetry.

        The metrics include claude_code.session.count, claude_code.token.usage, claude_code.cost.usage, claude_code.lines_of_code.count, claude_code.commit.count and claude_code.pull_request.count. Each carries session.id and, when known, user.email, so you can group by engineer. Set OTEL_RESOURCE_ATTRIBUTES to label every metric with a team or cost center, and OTEL_METRICS_INCLUDE_REPOSITORY=true (Claude Code v2.1.269 or later) to split usage per repository. Anthropic notes that the cost metrics are approximations.

        export CLAUDE_CODE_ENABLE_TELEMETRY=1
        export OTEL_METRICS_EXPORTER=otlp       # or prometheus, console
        export OTEL_LOGS_EXPORTER=otlp          # events: prompts, tool results, API requests
        export OTEL_EXPORTER_OTLP_PROTOCOL=grpc
        export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
        export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer your-token"
        claude

        Usage trackers: ccusage, /usage and a team view

        ccusage, an open-source CLI, turns the session logs on one machine into usage reports; it and the live limit meters are compared on Claude usage trackers. The built-in /insights command writes an HTML report on what you worked on and where sessions went wrong. Like /usage, both see one machine, and Claude Code session history is deleted after 30 days unless you raise cleanupPeriodDays.

        Local counts can disagree. On the Claude Code version we ran, the cache behind /stats counted 1.9 to 2.7 times the tokens of a deduplicated recount of the same transcripts (September 5 to 12, 2026), because each response's usage is logged once per content block. The status line's own cost estimate came within 8% of our recount. That cache is ~/.claude/stats-cache.json, and local dashboards read it too: the Claude Usage Analytics extension for VS Code lists it as the source of its token and model statistics. Recount before you quote a local dashboard's totals.

        And one laptop isn't the team: in the 30 days to October 3, our heaviest user's laptop opened 596 of the 878 pull requests we merged (68%). The rest came from three other engineers, Codex and other machines.

        bunx ccusage claude daily   # Claude Code tokens and cost by day
        bunx ccusage blocks         # usage per 5-hour window

        How Zest tracks Claude Code usage

        Each engineer installs the Zest plugin, which takes about a minute (setup). Three hooks record session start, session end and every tool call, and each session lands on the team dashboard:

        Zest needs no collector and doesn't read OpenTelemetry exports, so the two can run side by side.

        • Per session: models, input, output and cache tokens, and a cost estimated from list prices. Plans and token rates are on Claude Code pricing, and the token cost calculator prices a month of your own tokens.
        • Context and 5-hour and weekly limit use at the end of each session, from the status line data.
        • Skills, subagents and MCP tools per session, rolled up per engineer in the AI Stack view.
        • The branch, commits and pull request a session touched, so the Zest GitHub App can match it to what merged.
        • Secrets and personal data are redacted on the engineer's machine before upload; /zest:ignore turns tracking off for a folder.
        Spend in the Zest app: your agent usage at list prices, by week and by modelSample data

        What Claude Code usage looks like on our own team

        Of the 2,620 pull requests merged in our two repos from July 5 to October 3, 2026, 95% carry an AI agent's signature and about 90% carry Claude Code's.

        866 pull requests merged in our two repos from August 12 to October 4, 2026 carry a session-analytics block, written by the agent that opened them. The blocks show the default model changing twice in four weeks: Fable 5 and Opus 5 in August, then Fable 5.1 from September 1, then Opus 5.5 from September 22, which wrote every pull request in October. Opus 5.5's merged in a median 25 minutes and Opus 5's in 47, over different weeks and different work.

        A signature marks a pull request an agent opened or co-wrote, while Anthropic's contribution metrics match lines in merged pull requests to Claude Code sessions, so the two shares differ. How much code is written by AI puts them next to Google's and Microsoft's figures.

        TRY IT ON YOUR TEAM

        See what your team ships with AI.

        Starter is free (3 seats, no credit card). Pro is $49 a month with 5 seats and Max is $149 a month with 10 seats — priced per workspace, not per engineer, with extra seats at $19 a month. See pricing

        Start free
        npx @winding-labs/zest

        A FEW THINGS TO KNOW

        Questions

        How do I check my Claude Code usage limit?+

        Run /usage in Claude Code. On Pro, Max, Ultra, Team and Enterprise plans it shows how much of your limits is used and what used it; /cost and /stats open the same screen.

        Why is my Claude Code analytics dashboard empty?+

        The dashboard processes data once a day, so allow up to 24 hours after setup. Anyone missing from it should run claude update, because 2.0.28 is the first version that reports there. Contribution metrics also need GitHub Cloud and aren't available with zero data retention, and individual Pro, Max and Ultra plans have no Claude Code analytics at all.

        How do I see Claude Code usage across my team?+

        Install the Zest plugin in each engineer's Claude Code (/plugin marketplace add https://github.com/Winding-Labs/zest-claude, then /plugin install zest, then /reload-plugins, then /zest:login) and connect your GitHub org. Sessions appear on the Zest dashboard per engineer, with their models, tokens, skills and the pull requests they led to.

        Is there a Claude Code usage API?+

        Yes. Claude Console organizations call GET /v1/organizations/usage_report/claude_code with an Admin API key for each user's daily sessions, lines, commits, pull requests, tokens and estimated cost; Enterprise plans use the Claude Enterprise Analytics API.

        Does Zest upload our source code?+

        No code diffs are uploaded. The Claude Code plugin sends the text of the conversation, not tool inputs or outputs, after redacting secrets and personal data on the engineer's machine. Message text is kept for at most 90 days.