Claude Code Adoption
Overview
Clients buying Claude Code seats want to know whether they are used and
what they produce. anthropic_admin_usage_report_claude_code returns one
record per user (or API key) per UTC day with sessions, lines of code,
commits, PRs, tool acceptance, and per-model token use and estimated
cost. This skill rolls that into an adoption picture.
Anti-triggers
- The client's whole API bill — use
spend-review. Claude Code cost here is an
estimate for Claude Code activity only.
Key Concepts
- One day per call.
starting_at is a single UTC date
(YYYY-MM-DD). A month is one call per day, each paged with page /
next_page (limit up to 1000).
- Actor.
actor.type is user_actor (with email_address) or
api_actor (with api_key_name). Report them separately; an API-key
actor is automation, not a person.
- Core metrics:
num_sessions, lines_of_code.added /
.removed, commits_by_claude_code, pull_requests_by_claude_code.
- Tool actions: accepted and rejected counts per tool (edit, write,
and so on). Acceptance rate = accepted / (accepted + rejected). A low
rate points at onboarding or prompt habits, not at the product.
- Estimated cost is per model in
model_breakdown[].estimated_cost,
in cents.
customer_type is api or subscription; subscription_type is
team or enterprise for subscription orgs. Local and remote (web)
sessions arrive as separate rows (is_remote).
Workflows
Monthly adoption report
anthropic_admin_organization_get - confirm the org.
- For each day of the month,
anthropic_admin_usage_report_claude_code
with that date, paging to the end.
- Sum per
actor.email_address: active days, sessions, lines added,
commits, PRs, acceptance rate, estimated cost (cents to dollars once).
- Rank by active days, not lines of code. Lines reward churn; active
days show habit.
Unused seats
anthropic_admin_users_list with roles: ["claude_code_user"] (Console
orgs) or the full list (Enterprise), paged to the end.
- Build the set of emails with any activity in the last 30 days from the
daily reports.
- Seats with no activity are reclaim candidates. Give the client the
list with each person's
added_at; someone added last week is not idle.
Per-team view
anthropic_admin_analytics_usage with group_by: ["actor"] or
["workspace_id"] and products filtered to Claude Code gives a 31-day
token and request roll-up in one call when day-by-day detail is not
needed. Check the product values the org returns before filtering.
Gotchas
- 30 calls for a month is normal. Run them in order and stop on a 429
(see api-patterns) rather than retrying
hard.
- Today's data is incomplete. Report through yesterday (UTC).
- Present productivity numbers as usage, not performance. Per-person
tables stay with the client's engineering lead; QBR slides carry team
totals.
Related Skills
1---2name: anthropic-admin-claude-code-adoption3description: >4 Claude Code adoption and value reporting for a client's Anthropic5 organization: the per-user daily Claude Code usage report (sessions,6 lines added and removed, commits, pull requests, tool accept/reject7 counts, tokens and estimated cost per model), how to roll days up into a8 month, and how to set it against seat inventory to find unused seats.9 All tools are read-tier.10when_to_use: >-11 When reporting how a client's developers use Claude Code, finding Claude Code seats12 nobody uses, or preparing a Claude Code ROI slide for a QBR.13 Use when: claude code usage, claude code adoption, claude code seats unused, claude code14 roi, claude code productivity, developer ai usage, or claude code report.15metadata:16 source: https://skillmd.com/skills/wyre-ai/anthropic-admin-claude-code-adoption17---1819# Claude Code Adoption2021## Overview2223Clients buying Claude Code seats want to know whether they are used and24what they produce. `anthropic_admin_usage_report_claude_code` returns one25record per user (or API key) per UTC day with sessions, lines of code,26commits, PRs, tool acceptance, and per-model token use and estimated27cost. This skill rolls that into an adoption picture.2829## Anti-triggers3031- **The client's whole API bill** — use32 [spend-review](../spend-review/SKILL.md). Claude Code cost here is an33 estimate for Claude Code activity only.3435## Key Concepts3637- **One day per call.** `starting_at` is a single UTC date38 (`YYYY-MM-DD`). A month is one call per day, each paged with `page` /39 `next_page` (`limit` up to 1000).40- **Actor.** `actor.type` is `user_actor` (with `email_address`) or41 `api_actor` (with `api_key_name`). Report them separately; an API-key42 actor is automation, not a person.43- **Core metrics:** `num_sessions`, `lines_of_code.added` /44 `.removed`, `commits_by_claude_code`, `pull_requests_by_claude_code`.45- **Tool actions:** accepted and rejected counts per tool (edit, write,46 and so on). Acceptance rate = accepted / (accepted + rejected). A low47 rate points at onboarding or prompt habits, not at the product.48- **Estimated cost** is per model in `model_breakdown[].estimated_cost`,49 in **cents**.50- `customer_type` is `api` or `subscription`; `subscription_type` is51 `team` or `enterprise` for subscription orgs. Local and remote (web)52 sessions arrive as separate rows (`is_remote`).5354## Workflows5556### Monthly adoption report57581. `anthropic_admin_organization_get` - confirm the org.592. For each day of the month, `anthropic_admin_usage_report_claude_code`60 with that date, paging to the end.613. Sum per `actor.email_address`: active days, sessions, lines added,62 commits, PRs, acceptance rate, estimated cost (cents to dollars once).634. Rank by active days, not lines of code. Lines reward churn; active64 days show habit.6566### Unused seats67681. `anthropic_admin_users_list` with `roles: ["claude_code_user"]` (Console69 orgs) or the full list (Enterprise), paged to the end.702. Build the set of emails with any activity in the last 30 days from the71 daily reports.723. Seats with no activity are reclaim candidates. Give the client the73 list with each person's `added_at`; someone added last week is not idle.7475### Per-team view7677`anthropic_admin_analytics_usage` with `group_by: ["actor"]` or78`["workspace_id"]` and `products` filtered to Claude Code gives a 31-day79token and request roll-up in one call when day-by-day detail is not80needed. Check the `product` values the org returns before filtering.8182## Gotchas8384- 30 calls for a month is normal. Run them in order and stop on a 42985 (see [api-patterns](../api-patterns/SKILL.md)) rather than retrying86 hard.87- Today's data is incomplete. Report through yesterday (UTC).88- Present productivity numbers as usage, not performance. Per-person89 tables stay with the client's engineering lead; QBR slides carry team90 totals.9192## Related Skills9394- [seat-inventory](../seat-inventory/SKILL.md) - who holds a Claude Code seat95- [spend-review](../spend-review/SKILL.md) - total API spend