Do coding agents recommend GitHub Pages?
GitHub Pages was chosen in 5% of 508 judged deployment sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
GitHub Pages was chosen in 5% of 508 judged deployment sessions, ranking fourth. It was also raised as a candidate in 95 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 deployment inside a realistic codebase. Not what a chat assistant says about GitHub Pages. What an agent actually installed.
One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about deployment in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Deployment |
| Sessions in the category | 508 |
| Sessions where GitHub Pages was chosen | 26 |
| Install share | 5% |
| Rank in category | 4 of 10 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 95 |
| Chosen when considered | 21% |
| Site | pages.github.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code agree closely on GitHub Pages, choosing it at rates within 4 points of each other.
| Agent | Sessions | Chose GitHub Pages | Share |
|---|---|---|---|
| Claude Code | 120 | 7 | 6% |
| Codex | 150 | 5 | 3% |
| Cursor | 119 | 8 | 7% |
| Grok Build CLI | 30 | 2 | 7% |
| Muse Code | 89 | 4 | 4% |
By who was asking
GitHub Pages performs similarly across the four kinds of buyer, from 3% to 7%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose GitHub Pages | Share |
|---|---|---|---|
| Vibe coder | 254 | 19 | 7% |
| Senior engineer | 254 | 7 | 3% |
What GitHub Pages was up against
The full ranking in deployment, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Vercel | 197 | 39% |
| 2 | Render | 193 | 38% |
| 3 | Cloudflare | 59 | 12% |
| 4 | GitHub Pages (this page) | 26 | 5% |
| 5 | Railway | 17 | 3% |
| 6 | Netlify | 9 | 2% |
| 7 | Fly.io | 4 | 1% |
| 8 | Google Cloud | 1 | 0% |
What this means
This is an integration problem, not a presence problem. Agents raised GitHub Pages in 95 sessions and chose it in 26, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 508 sessions in deployment 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 deployment run can be replayed on the board.
If you work on GitHub Pages: 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 GitHub Pages?
Yes. GitHub Pages was chosen in 26 of the 508 judged sessions in deployment, a 5% install share, ranking fourth in its category.
Does Claude Code recommend GitHub Pages?
In 7 of the 120 sessions in deployment run with Claude Code, which is 6%.
Do different coding agents treat GitHub Pages differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 3% and 7% of their runs.
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 GitHub Pages considered but not chosen?
It was raised as a candidate in 95 sessions without being chosen, and chosen in 26. That is a 21% 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.