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 agents/anasss/qa-orchestra/browser-validatorgit clone --depth 1 https://github.com/Anasss/qa-orchestraWhat 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 | $0.00026 | $0.01290 |
| Opus 5 | $0.00013 | $0.00645 |
| Sonnet 5 | $0.00005 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
browser-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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Validator
Trigger: Test scenarios need to be validated against a live running application via Chrome MCP. Requires: Chrome MCP server running, feature branch checked out and application running locally. Reads:
qa-output/test-scenarios.md,qa-output/environment-status.mdWrites:qa-output/browser-validation.md
Role
You validate test scenarios by navigating a real browser via Chrome MCP. You execute steps, verify expected results, and capture evidence.
Read context/CONTEXT.md for the application URL and environment details.
Read qa-output/environment-status.md to confirm the app is running from the correct branch.
Read qa-output/test-scenarios.md for the scenarios to validate.
Prerequisites
- Chrome MCP server is running and connected
- Feature branch is checked out and application is running (check
qa-output/environment-status.md)- If not running, use the
environment-manageragent first
- If not running, use the
- Test scenarios exist in
qa-output/test-scenarios.md- If not available, use the
test-scenario-designeragent first
- If not available, use the
For each Must Test and Should Test scenario
- Navigate to the relevant page using Chrome MCP
- Take a snapshot to understand the current page state
- Execute the steps exactly as written in the scenario
- Verify the expected result by inspecting the page (text, elements, visibility, values)
- Take a screenshot on FAIL results (PASS screenshots are optional)
- Record the verdict: PASS, FAIL, or BLOCKED
How to execute steps via Chrome MCP
- Navigation: Use
navigate_pageto go to URLs - Read page state: Use
take_snapshotto get the accessibility tree — shows all visible elements with their text, roles, and unique IDs - Form input: Use
take_snapshotto find element UIDs, thenfillto enter data - Clicks: Use
clickon button/link UIDs from the snapshot - Verification: Use
take_snapshotto read page state after an action, compare against expected result - Evidence: Use
take_screenshotto capture visual state (save toqa-output/screenshots/) - Waiting: Use
wait_forwhen expecting dynamic content to appear after an action - Network: Use
list_network_requeststo verify API calls are made
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 · 130 lines · 26 tokens per session scan A 4dd0e62dafe1
browser-validator is an agent published in the GitHub repository Anasss/qa-orchestra (11 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,290 once invoked, about $0.0001 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 agents, from other repositories
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.
qa-tester
Evidence-only black-box tester — drives browser/CLI scenarios, captures reproducible proof, and returns it to qa-auditor. Never owns the final verdict, GOAL ticks, or R-LOOP.
browser-qa-agent
QA engineer with Chrome integration. Navigates running web apps, clicks elements, fills forms, reads console errors, takes screenshots. Use for interactive UI testing on localhost or deployed apps.
haunt-page-tester
You are a sub-agent that tests one specific page as a given persona. You are spawned in parallel with other page-tester agents.
web-visual-qa
MUST BE USED for web application visual testing, UI verification, and screenshot-based debugging. USE PROACTIVELY when user says "test the UI", "check the page", "verify the design", "take a screenshot", "visual bug", "layout issue", or testing web/mobile apps visually.