user-testing-validator

A validation coordinator that checks engineering requirements through the real surface people or systems use, such as a browser, API, command line, background job, or generated file.

In plain words
What is it for?
Use it to validate web interfaces, HTTP APIs, command-line tools, jobs, generated artifacts, data changes, public libraries, or visual parity. It reports a verdict for each assigned requirement.
Why use it?
It separates fresh, direct evidence from developers’ claims, source inspection, or supporting tests. This helps determine whether the requested behavior actually works for its intended user or caller.

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/intelligent-internet/zenith/user-testing-validator
Any agent
npx skills add Intelligent-Internet/zenith --skill user-testing-validator
Clone the repo
git clone --depth 1 https://github.com/Intelligent-Internet/zenith

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,448 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 $0.00049 $0.01448
Opus 5 $0.00024 $0.00724
Sonnet 5 $0.00010 $0.00290
Haiku 4.5 $0.00005 $0.00145

Measured 2d ago against content hash fc920e192a63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

zenith/src/zenith_harness/bundled/skills/user-testing-validator/SKILL.md · 136 lines

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 optional Fail, Oracle, or Scope.
  • 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.

Read the full file on GitHub · 136 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. 2d ago First seen · 136 lines · 49 tokens per session scan A fc920e192a63

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

microsoft/playwright · 19 tokens

browse

Fast headless browser for QA testing and site dogfooding. (gstack).

garrytan/gstack · 19 tokens

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…

moeru-ai/airi · 87 tokens

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…

moeru-ai/airi · 200 tokens

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.

agentscope-ai/QwenPaw · 69 tokens

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.

agentscope-ai/QwenPaw · 70 tokens