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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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.
[](https://agentmods.dev/agents/wahidyankf/ose-public/swe-usability-tester)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- today Changed d9202cdda39c
- 2d ago First seen · 103 lines · 46 tokens per session scan A 36f66fa17e82
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.
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.
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…
pn-webxr-developer
Specialist: WebXR and browser-based AR/VR with Three.js, A-Frame, or Babylon.js. Invoke directly for immersive web experiences.
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"…
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.