Skip to content
What Agents Pick

does Claude Code pick Better Auth for auth?

no. Claude Code added Better Auth in 0 of 35 auth runs across Opus 5.5, Sonnet 5.5 and Haiku 5.5. the most common result was built its own, 35 of 35 (32 as hand-rolled JWT or sessions).

0 of 35 auth runsnever pickedupdated Oct 18, 2026all auth results

get told if Better Auth starts getting picked

new models get the same auth prompts every week. one email with what moved. free. read issue 1

by model

Claude Code, same prompts and starter repos for every model.

  1. Opus 5.50 of 120%
  2. Sonnet 5.50 of 120%
  3. Haiku 5.50 of 110%

by starter stack

  1. Next.js + TypeScript0 of 180%
  2. Python + FastAPI0 of 170%

every auth result

all models pooled, 35 scored runs. most common: built its own, 35 of 35 (32 as hand-rolled JWT or sessions).

  1. Hand-rolled JWT or sessions32 of 3591%
  2. built its own, any form35 of 35100%
Which auth provider do coding agents pick? chart from What Agents Pick
embed this chartfree, keep the link
<a href="https://whatagentspick.com/tools/better-auth/"><img src="https://whatagentspick.com/share/auth.png" alt="does Claude Code pick Better Auth for auth? 0 of 35 runs" width="600" height="315" style="max-width:100%;height:auto" loading="lazy"></a>
<p><a href="https://whatagentspick.com/tools/better-auth/">data: what agents pick</a></p>
how embeds work

the prompts

none of them name a tool. Better Auth per wording.

  1. “Add sign up and sign in to this app. Users should be able to create an account, log in, log out, and hit a route that only works when they are logged in.”

    Better Auth: 0 of 12 runs

  2. “I need authentication and sessions here. Protect the dashboard route so anonymous visitors are redirected, and keep the user signed in across reloads.”

    Better Auth: 0 of 11 runs

  3. “Set up user accounts for this project, including login, logout, and a way to read the current user on the server.”

    Better Auth: 0 of 12 runs

other auth tools we check for

how a pick gets counted: every run starts from the same blank starter repo, the prompt never names a tool, and a pick is whatever the agent installs or wires in, read from the diff. full rules on the methodology page, every run for auth on the category page, raw data in runs.json.