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.
npx agentmods add skills/intelligent-internet/zenith/user-testing-validatornpx skills add Intelligent-Internet/zenith --skill user-testing-validatorgit clone --depth 1 https://github.com/Intelligent-Internet/zenithWhat 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 | $0.00049 | $0.01448 |
| Opus 5 | $0.00024 | $0.00724 |
| Sonnet 5 | $0.00010 | $0.00290 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
user-testing-validator 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 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.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Testing Validator
Use this skill when the validation assignment requires real user, caller, operator, or consumer-surface evidence for engineering assertions.
Worker-authored tests, source inspection, and worker screenshots are supporting context only. Fresh validator-collected evidence is the verdict source.
Inputs
Read:
- Validation assignment, assigned target ids, requested surface/method, and any assignment-level setup or dependency notes.
- Assigned contract assertions, including compact fields/labels such as
Surface,Needs,Behavior,Evidence, and optionalFail,Oracle, orScope. AGENTS.md.- Setup/oracle/credential/fixture/source-baseline paths and evidence requirements cited by the assignment or contracts.
- Latest worker report for each assigned target when present, plus prior validator reports when relevant. Treat reports as claims, not proof; do not let them anchor the verdict.
Surface Selection
Choose the surface that matches the contract:
- Browser/UI: real navigation, interaction, visual/state checks, console errors, relevant network observations.
- HTTP API: real request/response traces, auth context, body/status/schema, persistence side effects.
- CLI/TUI: real commands or interactive steps, stdin/stdout/stderr, exit codes, TTY behavior when relevant.
- Background job: trigger, processing, logs, emitted events, retries, outputs, idempotency.
- Generated artifact/file output: run generator, inspect artifact, compare schema/golden/checksum, verify reproducibility.
- Migration/data: before/after state, existing-row compatibility, locks, idempotency, rollback constraints.
- Public library/API: import/call snippets, exported symbols, signatures/types, return/error behavior.
- Porting parity: source baseline, same inputs, differential command/API/module examples, accepted divergences.
Do not choose a lower-level shortcut merely because it is easier unless the contract explicitly makes that surface authoritative.
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.
- 2d ago First seen · 136 lines · 49 tokens per session scan A fc920e192a63
user-testing-validator is a skill published in the GitHub repository Intelligent-Internet/zenith (283 stars, last pushed 26d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,448 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.