What is test-user?
test-user is a Claude Code mod by WeaponizedLego that a Haiku test user that clicks through your locally running app and reports UI/UX issues, with a live pane of its tasks, findings and failures. It is listed under Interface and has 1 GitHub stars.
| Type | Claude code mod |
|---|---|
| Author | WeaponizedLego |
| Repository | WeaponizedLego/claude-code-mods |
| Popularity | 1 GitHub stars |
| Category | Interface |
| Security | Low risk (80/100) |
| Rank | #2,389 of 5,272 Claude Code mods; #999 in Interface |
| Last commit | 2026-10-12 |
| Hooks | 8 events |
| Sees | Agent calls, every prompt, mcp__test-user__test_finding calls, mcp__test-user__test_finish calls, mcp__test-user__test_plan calls, mcp__test-user__test_report calls, mcp__test-user__test_task calls, subagent spawns |
| Draws on | Pane |
Is test-user safe to install?
test-user scores 80/100 on the MCPMods security check: Low risk. Things to review: watches every prompt or event. It passed 5 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| No network access | Pass |
| Starts no processes | Pass |
| Writes no files or config | Pass |
| Doesn't read environment variables | Pass |
| Watches every prompt or event | Review |
| Drives Claude (model calls, prompts) | Note |
| Passes claude plugin validate | Pass |
| No license detected | Note |
API calls in its code
| Call | What it means |
|---|---|
$.agent.register | |
$.clock.every | |
$.clock.now | |
$.command.register | |
$.prompt.submit | drives Claude |
$.state.get | |
$.state.set | |
$.tool.register | drives Claude |
$.ui.close | draws interface |
$.ui.open | draws interface |
$.ui.resolve | draws interface |
$.ui.status | draws interface |
$.ui.toast | draws interface |
How do I install test-user?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/WeaponizedLego/claude-code-mods claude plugin validate ./claude-code-mods/test-user
- Install it. Run this in your terminal, then /reload-plugins in an open session.
claude plugin marketplace add WeaponizedLego/claude-code-mods && claude plugin install test-user@claude-code-mods
Or ask Claude to set it up
Paste this into Claude Code and it installs test-user for you:
Install the "test-user" Claude Code mod from https://github.com/WeaponizedLego/claude-code-mods/tree/main/test-user. Run claude plugin validate on it first and show me what it can access before you enable it.
More from WeaponizedLego/claude-code-mods
This repository has 4 Claude Code mods on MCPMods.
- change-card: A short card that explains what an agent changed on this branch: a headline, a few one-line changes, where to look first (Low risk)
- plan-progress: Reads a phased plan into a live progress tree: phases, steps, elapsed time and an estimate of what is left (Low risk)
- usage-band: A band above the prompt showing context fill, tokens, cost and rate limits: stat tiles in the desktop app, a coloured ro (Low risk)