ui-test

A testing procedure that imitates a person using Claude.ai or ChatGPT through a visible chat window and the TinyAssets connector.

In plain words
What is it for?
Use it to enter requests in the actual chatbot interface, inspect the rendered replies, and record problems with the end-user experience.
Why use it?
It tests what a real user can understand and do, including whether the chatbot responds correctly without exposing internal tool details.

Skill for Claude CodeCodex

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 skills/jonnyton/tinyassets/ui-test
Any agent
npx skills add Jonnyton/TinyAssets --skill ui-test
Clone the repo
git clone --depth 1 https://github.com/Jonnyton/TinyAssets

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00092 $0.09116
Opus 5 $0.00046 $0.04558
Sonnet 5 $0.00018 $0.01823
Haiku 4.5 $0.00009 $0.00912

Measured 2d ago against content hash db8118b7ba37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-test scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. **Corroborate through a second channel.** An unauthenticated `curl` against the same live endpoint
.agents/skills/ui-test/SKILL.md · 503 lines

How it starts

The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ui-test

You simulate a real person chatting with Claude.ai or ChatGPT on their phone or laptop, using the TinyAssets MCP connector at https://tinyassets.io/mcp (the canonical URL installed by users). You do not call the MCP directly. You do not parse DOM metadata that a human user cannot see. You type into the chat box. You read the rendered response. You log what happened.

The human host is watching the browser tab. Your job is to look like a naive, curious user — one who does not know tool names, action parameters, or anything about the system's internals. If the chatbot doesn't understand you, that's a finding, not a problem to route around.

Driver routes

  • Codex / OpenAI-family route: use any harness-supported browser control path that keeps the same live chatbot tab visible to the host: Codex in-app Browser, the Chrome extension/plugin, CDP or a CLI browser driver, or an equivalent visible route. Open or continue https://claude.ai/ by default; ChatGPT Developer Mode is also valid when its TinyAssets connector is installed. If one driver is unavailable, try another host-visible driver before declaring a blocker.
  • Claude Code route: use the visible Chrome profile through scripts/claude_chat.py. This remains the default route for Claude team user-sim. Host-login Claude.ai access is not the proof requirement; Claude.ai is valid when a real browser session can use the TinyAssets connector.
  • Anthropic / Cowork ChatGPT route: when an Anthropic-family driver has browser or computer control, use ChatGPT when Developer Mode is enabled and the TinyAssets connector is added/visible in that same session. Do not verify in an isolated browser profile unless the host explicitly says that profile is the user-installed connector state. Claude Code on Windows can drive this route via scripts/chatgpt_chat.py (sibling of claude_chat.py, same CDP at localhost:9222, reuses the Chrome profile).

Proof standard

The verification target is a rendered chatbot conversation using the live installed connector. Claude.ai, ChatGPT Developer Mode, and future chatbot clients are all acceptable when the host can watch the same live tab, the tester can see the connector in the browser, type a normal user prompt, and observe the chatbot's rendered answer or tool-use result. The browser-control transport is an implementation detail, not part of the proof contract. Browser automation, screenshots, DOM snapshots, direct tests, and public canaries can help navigate or gather supporting evidence; they do not replace final rendered chatbot proof.

Read the full file on GitHub · 503 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 503 lines · 92 tokens per session scan A db8118b7ba37

Subscribe to this mod's changes

ui-test is a skill published in the GitHub repository Jonnyton/TinyAssets (1 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 9,116 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.