From the experiment

Do coding agents recommend Hurl?

Hurl was chosen in 2% of 671 judged security testing sessions, ranking eighth. Measured with Claude Code, Codex, Grok Build CLI and Muse Code.

Published October 14, 2026 Updated November 18, 2026 Read as Markdown

Hurl was chosen in 2% of 671 judged security testing sessions, ranking eighth. It was also raised as a candidate in 3 further sessions without being chosen.

This page reports what happened when Claude Code, Codex, Grok Build CLI and Muse Code had to solve a problem in security testing inside a realistic codebase. Not what a chat assistant says about Hurl. What an agent actually installed.

The numbers

CategorySecurity testing
Sessions in the category671
Sessions where Hurl was chosen15
Install share2%
Rank in category8 of 85
Codebases it won in2
Raised as a candidate, not chosen3
Chosen when considered83%
Sitehurl.dev

By agent

With 15 wins spread across 4 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose HurlShare
Claude Code18774%
Codex25683%
Grok Build CLI11600%
Muse Code11200%

What Hurl was up against

The full ranking in security testing, from the same sessions:

#ProductRuns wonShare
1ZAP15523%
2Semgrep10315%
3SonarQube8312%
4Burp Suite447%
5GitHub Advanced Security304%
6Trivy274%
7Strix233%
8Hurl (this page)152%

What this means

Agents almost never raise Hurl without choosing it: 3 sessions raised against 15 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.

Where these numbers come from

The 671 sessions in security testing are part of a published set of 15,561, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every security testing run can be replayed on the board.

If you work on Hurl: 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 Hurl?

Yes. Hurl was chosen in 15 of the 671 judged sessions in security testing, a 2% install share, ranking eighth in its category.

Does Claude Code recommend Hurl?

In 7 of the 187 sessions in security testing run with Claude Code, which is 4%.

Do different coding agents treat Hurl differently?

Not much. Claude Code, Codex, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 4% 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 Hurl considered but not chosen?

It was raised as a candidate in 3 sessions without being chosen, and chosen in 15. That is a 83% conversion from considered to chosen.

Where this comes from

Armature ran 15,561 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.

Read next

All library pages