From the experiment

Do coding agents recommend Escape?

Escape was chosen in 2% of 531 judged security testing sessions, ranking ninth. Measured with Claude Code, Codex, Grok Build CLI and Muse Code.

Published October 14, 2026 Updated November 13, 2026 Read as Markdown

Escape was chosen in 2% of 531 judged security testing sessions, ranking ninth. It was also raised as a candidate in 22 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 Escape. What an agent actually installed.

The numbers

CategorySecurity testing
Sessions in the category531
Sessions where Escape was chosen10
Install share2%
Rank in category9 of 68
Codebases it won in4
Raised as a candidate, not chosen22
Chosen when considered31%
Siteescape.tech

By agent

With 10 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 EscapeShare
Claude Code18742%
Codex11611%
Grok Build CLI11633%
Muse Code11222%

What Escape was up against

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

#ProductRuns wonShare
1ZAP12624%
2Semgrep8616%
3SonarQube7013%
4Burp Suite346%
5GitHub Advanced Security285%
6Strix234%
7Trivy173%
8StackHawk132%

What this means

Escape was raised in 22 sessions and chosen in 10. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

Where these numbers come from

The 531 sessions in security testing are part of a published set of 15,379, 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 Escape: 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 Escape?

Yes. Escape was chosen in 10 of the 531 judged sessions in security testing, a 2% install share, ranking ninth in its category.

Does Claude Code recommend Escape?

In 4 of the 187 sessions in security testing run with Claude Code, which is 2%.

Do different coding agents treat Escape differently?

Not much. Claude Code, Codex, Grok Build CLI and Muse Code chose it at similar rates, between 1% and 3% 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 Escape considered but not chosen?

It was raised as a candidate in 22 sessions without being chosen, and chosen in 10. That is a 31% conversion from considered to chosen.

Where this comes from

Armature ran 15,379 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