Claude Code

Antenna automatically tracks AI coding metrics from Claude Code. Get insight into adoption, activity, and the impact of Claude Code on your team’s productivity.

Connection Methods

We support Claude.ai Enterprise, Claude.ai Team subscriptions, Claude Developer Platform (API) accounts, and self-hosted deployments. You can connect one or more of the following:

• Claude.ai Enterprise – For organizations on a Claude.ai Enterprise plan. Connect using an Analytics API key.
• Claude.ai Team – Team members log in with their Claude.ai subscriptions, including Pro, Max, and Team.
• Claude Developer Platform – Claude Code is managed through an organization with shared API billing on platform.claude.com. Usage analytics are tracked via Claude Code’s Analytics API .
• Self-Hosted Claude Code – Claude Code is hosted on AWS Bedrock. Usage data is read from Model Invocation Logging in S3.

Method 1: Claude.ai Enterprise

For organizations on a Claude.ai Enterprise plan, connect using an Analytics API key to pull usage data directly from Anthropic’s Analytics API.

Method 2: Claude.ai Team

We use OpenTelemetry  to track usage from Claude.ai subscriptions (Pro, Max, and Team).

{
  "env": {
    "CLAUDE_CODE_ENABLE_TELEMETRY": "1",
    "OTEL_METRICS_EXPORTER": "otlp",
    "OTEL_EXPORTER_OTLP_PROTOCOL": "http/json",
    "OTEL_EXPORTER_OTLP_METRICS_ENDPOINT": "https://app.antenna.dev/api/v1/otel/claude/metrics",
    "OTEL_EXPORTER_OTLP_HEADERS": "Authorization=Bearer your_token",
    "OTEL_METRIC_EXPORT_INTERVAL": "3600000"
  }
}

When developers log into Claude with their subscription via their Terminal they will see a notification: “Managed settings require approval”. Users must accept these settings to use Claude. This will update the ~/.claude/settings.json file in each user’s home directory.

Other important notes:

• You must be an Owner to update managed settings.
• If you have your own OpenTelemetry collector or have already set up a .claude/settings.json in the repo with OpenTelemetry configured, managed settings will supersede it. Keep this in mind if you or your team have an existing repo-level OpenTelemetry configuration.
• This setting only tracks Claude CLI usage. It tracks terminal usage, but not activity in Claude Code editor extensions or the desktop app.
• For more detail on how to configure your settings file, see Claude Code settings .

Method 3: Claude Developer Platform

To connect your Claude Developer Platform (API) account:

This integration uses the Admin API. You must use an Admin API key (keys start with sk-ant-admin...), which is different from standard Claude API keys. Standard API keys cannot access the usage report or organization users endpoints. Only organization members with the admin role can create Admin API keys.

Method 4: Self-Hosted Claude Code

If Claude Code runs on AWS Bedrock, Antenna can read usage data directly from Model Invocation Logging  in S3. This requires no changes to your Claude Code deployment — Antenna assumes an IAM role in your account and reads the invocation logs from your S3 bucket.

Prerequisites

• An AWS account running Claude Code on Amazon Bedrock
• Model Invocation Logging  enabled and configured to write to an S3 bucket
• IAM permissions to create policies and roles

Setup

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetObject",
        "s3:ListBucket"
      ],
      "Resource": [
        "arn:aws:s3:::YOUR_BUCKET_NAME",
        "arn:aws:s3:::YOUR_BUCKET_NAME/*"
      ]
    }
  ]
}

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Principal": {
        "AWS": "arn:aws:iam::134217665810:role/software-app-prod"
      },
      "Action": "sts:AssumeRole",
      "Condition": {
        "StringEquals": {
          "sts:ExternalId": "YOUR_EXTERNAL_ID"
        }
      }
    }
  ]
}

How it works

Bedrock Model Invocation Logging writes a gzipped JSON file to S3 for each invocation. These files are organized by date under a path like:

s3://YOUR_BUCKET/AWSLogs/ACCOUNT_ID/BedrockModelInvocationLogs/REGION/YYYY/MM/DD/

Each file contains one JSON object per line (NDJSON format) with fields including:

• timestamp — when the invocation occurred
• identity.arn — the identity ARN of the caller (used for user identification)
• modelId — the Bedrock model used
• input.inputTokenCount and output.outputTokenCount — token usage

Antenna reads these files daily, aggregates token usage per user, and surfaces the data in your AI dashboards. Users are identified by their identity ARN — if your developers assume IAM roles with unique session names (e.g. arn:aws:sts::123456789012:assumed-role/DeveloperRole/jane.smith), Antenna will automatically create a user for each unique session name.

Alternative: S3 Replication (Push)

If your organization prefers not to grant Antenna cross-account IAM role access, you can use S3 Cross-Account Replication instead. In this model, your S3 bucket automatically pushes data into a dedicated Antenna-managed bucket. Antenna never accesses your account, and you never access Antenna’s account — replication is handled entirely by AWS’s S3 service internally.

What you need

• Admin access to your AWS account
• The Destination Bucket ARN and AWS Account ID provided by Antenna

Replication setup

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Principal": {
        "Service": "s3.amazonaws.com"
      },
      "Action": "sts:AssumeRole"
    }
  ]
}

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetReplicationConfiguration",
        "s3:ListBucket"
      ],
      "Resource": "arn:aws:s3:::YOUR_SOURCE_BUCKET"
    },
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetObjectVersionForReplication",
        "s3:GetObjectVersionAcl",
        "s3:GetObjectVersionTagging"
      ],
      "Resource": "arn:aws:s3:::YOUR_SOURCE_BUCKET/*"
    },
    {
      "Effect": "Allow",
      "Action": [
        "s3:ReplicateObject",
        "s3:ReplicateDelete",
        "s3:ReplicateTags"
      ],
      "Resource": "ANTENNA_DESTINATION_BUCKET_ARN/*"
    }
  ]
}

Data collected

Claude.ai Enterprise

We pull organization-level usage analytics from the Anthropic Analytics API.

Claude.ai Team / Pro / Max (OpenTelemetry)

We receive metrics every hour, such as lines added, commits, pull requests, tokens, and related usage. For full details on what Claude Code sends, see Monitoring usage  in Claude Code’s OpenTelemetry documentation.

We do not collect logs (for example, prompts). Only aggregated metrics are sent.

Self-Hosted Claude Code (AWS Bedrock — Model Invocation Logging)

For Bedrock deployments, Antenna reads Model Invocation Logging data from your S3 bucket. Each invocation log contains:

• Timestamp, model ID, and API operation
• Input and output token counts
• Identity ARN (used to identify individual users)
• Cache token usage (creation and read)

Antenna does not read the request or response body content. Only the metadata fields listed above are processed. All data stays in your AWS account — Antenna reads it via a cross-account IAM role with read-only S3 access.

Claude Developer Platform

We pull from two Anthropic API endpoints:

We use the organization users response to match Claude users to Git users. For full parameter and response details, see Claude Code Analytics API  and Administration API .