Do coding agents recommend WorkOS AuthKit?
WorkOS AuthKit was chosen in 18% of 724 judged authentication sessions, ranking second. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
WorkOS AuthKit was chosen in 18% of 724 judged authentication sessions, ranking second. It was also raised as a candidate in 77 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in authentication inside a realistic codebase. Not what a chat assistant says about WorkOS AuthKit. What an agent actually installed.
The numbers
| Category | Authentication |
| Sessions in the category | 724 |
| Sessions where WorkOS AuthKit was chosen | 131 |
| Install share | 18% |
| Rank in category | 2 of 28 |
| Codebases it won in | 12 |
| Raised as a candidate, not chosen | 77 |
| Chosen when considered | 63% |
| Site | workos.com |
By agent
The agents treat WorkOS AuthKit very differently. Grok Build CLI chose it in 32% of its sessions in this category and Muse Code in 6%, a spread of 26 points.
| Agent | Sessions | Chose WorkOS AuthKit | Share |
|---|---|---|---|
| Claude Code | 133 | 40 | 30% |
| Codex | 204 | 35 | 17% |
| Cursor | 133 | 27 | 20% |
| Grok Build CLI | 50 | 16 | 32% |
| Muse Code | 204 | 13 | 6% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Muse Code, your real position here is 6%, not 18%.
By who was asking
WorkOS AuthKit does much better with one kind of buyer than another. It won 27% of sessions asked as junior developer and 0% of those asked as vibe coder.
| Who is asking | Sessions | Chose WorkOS AuthKit | Share |
|---|---|---|---|
| Vibe coder | 98 | 0 | 0% |
| Junior developer | 223 | 61 | 27% |
| Senior engineer | 243 | 38 | 16% |
| Enterprise team | 160 | 32 | 20% |
What WorkOS AuthKit was up against
The full ranking in authentication, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Auth0 | 180 | 25% |
| 2 | WorkOS AuthKit (this page) | 131 | 18% |
| 3 | Clerk | 86 | 12% |
| 4 | Microsoft Entra ID | 80 | 11% |
| 5 | Built in-house (no product adopted) | 65 | 9% |
| 6 | Better Auth | 29 | 4% |
| 7 | Amazon Cognito | 23 | 3% |
| 8 | Keycloak | 22 | 3% |
What this means
A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.
The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.
Where these numbers come from
The 724 sessions in authentication are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every authentication run can be replayed on the board.
If you work on WorkOS AuthKit: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend WorkOS AuthKit?
Yes. WorkOS AuthKit was chosen in 131 of the 724 judged sessions in authentication, a 18% install share, ranking second in its category.
Does Claude Code recommend WorkOS AuthKit?
In 40 of the 133 sessions in authentication run with Claude Code, which is 30%.
Do different coding agents treat WorkOS AuthKit differently?
Yes, and by a wide margin. Grok Build CLI chose it in 32% of its runs and Muse Code in 6%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is WorkOS AuthKit considered but not chosen?
It was raised as a candidate in 77 sessions without being chosen, and chosen in 131. That is a 63% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.