Do coding agents recommend govulncheck?
govulncheck was chosen in 1% of 671 judged security testing sessions, ranking number 11. Measured with Claude Code, Codex, Grok Build CLI and Muse Code.
govulncheck was chosen in 1% of 671 judged security testing sessions, ranking number 11. It was also raised as a candidate in 5 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 govulncheck. 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 security testing in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Security testing |
| Sessions in the category | 671 |
| Sessions where govulncheck was chosen | 9 |
| Install share | 1% |
| Rank in category | 11 of 85 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 5 |
| Chosen when considered | 64% |
| Site | go.dev |
By agent
With 9 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.
| Agent | Sessions | Chose govulncheck | Share |
|---|---|---|---|
| Claude Code | 187 | 5 | 3% |
| Codex | 256 | 4 | 2% |
| Grok Build CLI | 116 | 0 | 0% |
| Muse Code | 112 | 0 | 0% |
What govulncheck was up against
The full ranking in security testing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | ZAP | 155 | 23% |
| 2 | Semgrep | 103 | 15% |
| 3 | SonarQube | 83 | 12% |
| 4 | Burp Suite | 44 | 7% |
| 5 | GitHub Advanced Security | 30 | 4% |
| 6 | Trivy | 27 | 4% |
| 7 | Strix | 23 | 3% |
| 8 | Hurl | 15 | 2% |
What this means
Agents almost never raise govulncheck without choosing it: 5 sessions raised against 9 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 govulncheck: 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 govulncheck?
Yes. govulncheck was chosen in 9 of the 671 judged sessions in security testing, a 1% install share, ranking number 11 in its category.
Does Claude Code recommend govulncheck?
In 5 of the 187 sessions in security testing run with Claude Code, which is 3%.
Do different coding agents treat govulncheck differently?
Not much. Claude Code, Codex, Grok Build CLI and Muse Code chose it at similar rates, between 0% 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 govulncheck considered but not chosen?
It was raised as a candidate in 5 sessions without being chosen, and chosen in 9. That is a 64% 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.