swe-usability-tester

swe-usability-tester is an agent for Claude Code from wahidyankf/ose-public. It costs 46 tokens per session (1,525 once invoked), scanned A, original, MIT.

A usability testing agent that tries a running website or command-line tool as a first-time user would. It judges frozen tasks against named usability principles and changes nothing.

In plain words
What is it for?
It helps assess web tasks across viewport sizes and languages, or command-line help, errors, exit codes, and output as a newcomer experiences them.
Why use it?
It can reveal problems that are easy to miss when the reviewer already knows the product, its layout, or its expected workflow.

Agent for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit It helps assess web tasks across viewport sizes and languages, or command-line help, errors, exit codes, and output as a newcomer experiences them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wahidyankf/ose-public/swe-usability-tester
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.

Clone the repo
git clone --depth 1 https://github.com/wahidyankf/ose-public

Made for: Claude Code.

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 swe-usability-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-usability-tester/github.svg)](https://agentmods.dev/agents/wahidyankf/ose-public/swe-usability-tester)
Your own site
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/swe-usability-tester"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-usability-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for swe-usability-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/swe-usability-tester"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-usability-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,525 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00046 $0.01525
Opus 5.5 $0.00018 $0.00610
Sonnet 5.5 $0.00009 $0.00305
Haiku 4.5 $0.00005 $0.00153

Measured today against content hash d9202cdda39c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swe-usability-tester 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 today.

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.

.agents/agents/swe-usability-tester.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWE Usability Tester

Judges whether a newcomer can use a running product. The product's intended behaviour is deliberately kept from it, because a tester who knows where everything is cannot see what a first use misses. It edits nothing it judges; repository-write serves its findings record and captures alone.

Normal Workload

Across the frozen tasks, it sweeps the surface against a heuristic set, walks each task step by step, runs the usability probes, and rates each violation of a named principle. Judging observed behaviour against a published rubric takes high-context judgement about what a first-time user meets, so this is plan work.

Surface

The caller names one surface per pass. With none named, it asks rather than guessing.

Surface Used through Judged
web a real browser at the served origin each task at every viewport class and locale in scope
cli the installed command in a scratch directory help text, error messages, exit codes, and output streams, as a first-time user meets them

Under cli, each finding cites the principle a newcomer's experience breaks and, where it applies, the rule of the Command-Line Interface contract, as Building Command-Line Interfaces teaches. The contract describes every tool, not this product, so reading it keeps the pass blind.

Blind by Construction

Its brief holds only the surface, its address or command, the viewport classes and locales for web, and the frozen task list, as Exploratory and Usability Review requires. repository-read serves its own definition, its declared skills, the governance documents they link to, and the record it writes, never a specification, source file, design asset, or another lens's findings. When anything else reached it, the record labels the lens spec-aware.

Read the full file on GitHub · 103 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. today Changed d9202cdda39c
  2. 2d ago First seen · 103 lines · 46 tokens per session scan A 36f66fa17e82

Subscribe to this mod's changes

swe-usability-tester is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,525 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.

Related

Other agents, from other repositories

design-review

Comprehensive UI/UX design review with automated browser testing via Playwright CLI. Use when reviewing front-end PRs, validating responsive design, testing accessibility compliance (WCAG 2.1 AA), or verifying visual consistency across viewports.

joaquimscosta/arkhe-claude-plugins · 51 tokens

enriched-report-reviewer

Visual quality review of an enriched HTML report via Browser MCP screenshots. Evaluates infographic header, report body layout, chart rendering, and sidebar navigation against a 10-gate quality rubric. Returns structured JSON with gate scores and actionable fix recommendations. Use when enrich-report Phase 5b needs…

cogni-work/insight-wave · 75 tokens

pn-webxr-developer

Specialist: WebXR and browser-based AR/VR with Three.js, A-Frame, or Babylon.js. Invoke directly for immersive web experiences.

perniemann/pnCore · 36 tokens

ux-tester

Use for UX testing — evaluating user experience through the browser like a real user. Given a feature, flow, or page to test, walks it in a real browser and reports what's confusing, broken, or missing. Doesn't read code or diffs — only sees what the user sees. Triggers: "ux test", "test the ux", "is this confusing"…

heyJordanParker/dotfiles · 90 tokens

seo-visual

Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.

lionkiii/claude-seo-skills · 25 tokens

seo-visual

Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.

buithang3058/Agentic-SEO · 25 tokens