# Do coding agents recommend HCL AppScan?

> HCL AppScan was chosen in 4% of 181 judged security platforms sessions, ranking fifth. Measured with Claude Code, Codex, Grok Build CLI and Muse Code.

Source: https://armature.tech/library/do-coding-agents-recommend-hcl-appscan
Published: 2026-10-14 · Updated: 2026-11-18
Publisher: Armature, Inc. (https://armature.tech)

---

> HCL AppScan was chosen in 4% of 181 judged security platforms sessions, ranking fifth. It was also raised as a candidate in 11 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 platforms inside a realistic codebase. Not what a chat assistant says about HCL AppScan. What an agent actually chose.

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 platforms in general, and the splits below cannot separate the two. Treat them as a description of that repository.

## The numbers

| | |
| --- | --- |
| Category | Security platforms |
| Sessions in the category | 181 |
| Sessions where HCL AppScan was chosen | 8 |
| Install share | 4% |
| Rank in category | 5 of 27 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 11 |
| Chosen when considered | 42% |
| Site | hcltechsw.com |

## By agent

With 8 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 HCL AppScan | Share |
| --- | --- | --- | --- |
| Claude Code | 51 | 2 | 4% |
| Codex | 72 | 3 | 4% |
| Grok Build CLI | 30 | 3 | 10% |
| Muse Code | 28 | 0 | 0% |

## What HCL AppScan was up against

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

| # | Product | Runs won | Share |
| --- | --- | --- | --- |
| 1 | Checkmarx One | 50 | 28% |
| 2 | GitLab Security | 43 | 24% |
| 3 | Snyk | 22 | 12% |
| 4 | Aikido Security | 19 | 10% |
| 5 | HCL AppScan **(this page)** | 8 | 4% |
| 6 | GitHub Advanced Security + ZAP | 6 | 3% |
| 7 | DefectDojo + Gitleaks + Semgrep + Trivy + ZAP | 5 | 3% |
| 8 | GitHub Advanced Security + Microsoft Defender for Cloud | 3 | 2% |

## What this means

HCL AppScan was raised in 11 sessions and chosen in 8. 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 181 sessions in security platforms 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](/library/how-we-measured-this).

Every security platforms run can be replayed on [the board](/leaderboards/security-platforms).

If you work on HCL AppScan: 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 HCL AppScan?

Yes. HCL AppScan was chosen in 8 of the 181 judged sessions in security platforms, a 4% install share, ranking fifth in its category.

### Does Claude Code recommend HCL AppScan?

In 2 of the 51 sessions in security platforms run with Claude Code, which is 4%.

### Do different coding agents treat HCL AppScan differently?

Not much. Claude Code, Codex and Grok Build CLI chose it at similar rates, between 4% and 10% 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 HCL AppScan considered but not chosen?

It was raised as a candidate in 11 sessions without being chosen, and chosen in 8. That is a 42% conversion from considered to chosen.

## Read next

- [How to get picked for security platforms by coding agents](https://armature.tech/library/security-platforms-coding-agents-playbook) (Markdown: https://armature.tech/library/security-platforms-coding-agents-playbook.md)
- [Do coding agents recommend Checkmarx One?](https://armature.tech/library/do-coding-agents-recommend-checkmarx-one) (Markdown: https://armature.tech/library/do-coding-agents-recommend-checkmarx-one.md)
- [Do coding agents recommend GitLab Security?](https://armature.tech/library/do-coding-agents-recommend-gitlab-security) (Markdown: https://armature.tech/library/do-coding-agents-recommend-gitlab-security.md)
- [Do Claude Code, Codex and Cursor pick the same tools?](https://armature.tech/library/do-claude-code-and-codex-agree) (Markdown: https://armature.tech/library/do-claude-code-and-codex-agree.md)

---

Armature helps software products get discovered and used by coding agents.
Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech
