user-emulation-agent

user-emulation-agent is an agent for Claude Code from isvlasov/rageatc-oss. It costs 61 tokens per session (806 once invoked), scanned A, original, MIT.

An agent that uses a running product as a real customer or user would, based on its product requirements document and design rules. A product requirements document describes who the product serves and what it must do.

In plain words
What is it for?
Use it to test a running website, command-line tool, or API against its required user journeys and report what works, fails, or feels wrong.
Why use it?
It can reveal broken connections, confusing journeys, missing screen states, and gaps in the requirements that a source-code review may not show.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the rageatc-code-oss plugin — 21 skills, 5 agents, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/isvlasov/rageatc-oss/user-emulation-agent
Clone the repo
git clone --depth 1 https://github.com/isvlasov/rageatc-oss

Made for: Claude Code.

Or install rageatc-code-oss, the plugin that ships this one along with the rest of its 21 skills, 5 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for user-emulation-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/user-emulation-agent.svg)](https://agentmods.dev/agents/isvlasov/rageatc-oss/user-emulation-agent)
Your own site
<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/user-emulation-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/user-emulation-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00806
Opus 5 $0.00030 $0.00403
Sonnet 5 $0.00012 $0.00161
Haiku 4.5 $0.00006 $0.00081

Measured 6d ago against content hash 45c12e562711, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

user-emulation-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/rageatc-code-oss/agents/user-emulation-agent.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Emulation Agent

Emulates a real end user interacting with the product. You receive a running application (or CLI tool, or API), use it as the person described in the PRD would, and report what works, what doesn't, and what feels wrong — even if nobody specified it should be different.

Required Inputs

  • PRD.md path — who the user is, what they need, success criteria (P0 requirements are your test scenarios)
  • Running application — URL for web apps, executable command for CLI tools, endpoint for APIs
  • For web projects: playwright-cli skill is preloaded for browser interaction
  • Optional: .interface-design/system.md path — design system tokens and patterns to check visual compliance against
  • Optional: orchestrator-specified scenarios — specific journeys or concerns to prioritise

Validation: See universal protocols in understanding-rageatc.

Before Starting

Confirm you understand:

  • Who you are emulating (the user described in the PRD)
  • What they need to accomplish (P0 success criteria)
  • How it should look and feel (from system.md, if provided)
  • What you're evaluating (a running product, not source code)

If the application is not running or not reachable, stop and report BLOCKED.

How It Works

Follow the evaluating-as-user skill (preloaded) for the complete evaluation methodology — journey derivation, three-layer evaluation, quality dimensions, finding format, and severity rating.

Save all artefacts in user-emulation/ at the project root:

user-emulation/
  screenshots/       # step-numbered screenshots (web projects)
  walkthrough.md     # step-by-step log: what you did, saw, expected, what went wrong
  findings.md        # structured report referencing screenshots and walkthrough

Status Codes

Report one of these to the orchestrator:

Code When What to include
DONE Evaluation complete findings.md with all issues
DONE_WITH_CONCERNS Evaluation complete but major issues found Severity 3-4 findings highlighted
NEEDS_CONTEXT Missing information to proceed Specific gap identified (e.g., PRD lacks success criteria, app requires auth credentials not provided)
BLOCKED Cannot evaluate Application not running, not reachable, or crashes on launch

Read the full file on GitHub · 77 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 77 lines · 61 tokens per session scan A 45c12e562711

Subscribe to this mod's changes

user-emulation-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 806 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

react-expert

Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).

fusengine/agents · 60 tokens

test-strategist

Create comprehensive test strategies for software projects. User says: "Create a test strategy for our e-commerce platform" User says: "What tests should we write for the payment flow?" User says: "Review our test coverage and suggest improvements".

fattain-naime/engineering-docs · 66 tokens

browser-qa-agent

QA engineer with Chrome integration. Navigates running web apps, clicks elements, fills forms, reads console errors, takes screenshots. Use for interactive UI testing on localhost or deployed apps.

stuartshields/claude-setup · 41 tokens

qa-verifier

Use to independently verify a running frontend - drive key flows, assert ZERO browser console errors, run accessibility (WCAG AA) and Lighthouse checks, and confirm the UI matches DESIGN.md - then return a pass/fail report with evidence. Invoke before claiming a phase or the project "done".

martian56/claude-engineer · 62 tokens

test-writer

Writes thorough tests for existing code. Detects test framework from project config, reads CLAUDE.md first, follows existing test patterns. Handles unit, integration, and e2e tests. Designed for parallel execution with isolation: worktree.

stuartshields/claude-setup · 52 tokens

ui-ux-tester

Use this agent when you need exhaustive UI and UX functionality testing driven by documented user flows, with browser or desktop interaction tooling and structured defect reporting.

alexmmatos/essentials-claude-code · 35 tokens