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 skills add jqaisystems/jqai-ai-skills --skill website-change-verifiergit clone --depth 1 https://github.com/jqaisystems/jqai-ai-skillsWrote 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/skills/jqaisystems/jqai-ai-skills/website-change-verifier)<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/website-change-verifier"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/website-change-verifier/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/skills/jqaisystems/jqai-ai-skills/website-change-verifier"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/website-change-verifier.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 | $0.00071 | $0.00728 |
| Opus 5.5 | $0.00028 | $0.00291 |
| Sonnet 5.5 | $0.00014 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
website-change-verifier 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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Change Verifier
Verify the complete user-visible result of a website change. Default to read-only checks and report the highest completion state supported by evidence.
1. Identify the change and platform
- Confirm the project root, target route, requested outcome, source of truth, and expected visibility.
- Inspect project instructions, manifests, entrypoints, routing, and nearby implementation patterns.
- Read references/framework-checks.md for the detected stack.
- Preserve existing public URLs and unrelated behavior unless the request explicitly changes them.
2. Map affected surfaces
Check which parts of this chain apply:
- content or data source
- route or page rendering
- navigation, listings, related content, and internal links
- title, description, canonical, Open Graph, structured data, and accessibility text
- sitemap, robots rules,
llms.txt, feeds, search indexes, or static export - images, video, downloads, and responsive variants
- local server, deployment, cache, and live state
For hidden content, distinguish navigation removal from direct access, sitemap presence, and search visibility.
3. Verify in layers
- Read references/verification-matrix.md and select checks proportional to the change.
- Run syntax, type, lint, test, or production-build checks supported by the project.
- Confirm the correct listener and make a real request to each affected route.
- Use
scripts/verify_routes.pyfor deterministic status and response-text checks. - Inspect rendered desktop and mobile behavior when layout, interaction, forms, or media changed.
- Confirm required text is present and replaced text is absent.
- Check discovery surfaces only when the content is intended to appear there.
Example:
python scripts/verify_routes.py `
--url http://127.0.0.1:8766/example `
--contains "http://127.0.0.1:8766/example::Expected heading" `
--not-contains "http://127.0.0.1:8766/example::Old wording"
What ships with it
4 files 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.
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.
- 1mo ago First seen · 69 lines · 71 tokens per session scan A 2768bdcfea54
website-change-verifier is a skill published in the GitHub repository jqaisystems/jqai-ai-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 728 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
playwright-qa
QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review…
browser-agent
Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Playwright) with ISTQB test matrix generation, automated testcase execution, console/network error tracing, and defect reporting.
browser-task-and-automation-and-delegation
A required procedure for browser actions carried out through a separate browser specialist. Browser actions include opening pages, filling forms, taking snapshots, performance checks, automated tests, and data collection.
setup-playwright
Use when adding, extending, or repairing a repo-owned Playwright test harness across Node Playwright Test, Playwright Pytest, or .NET/Java test frameworks. Also use when explicitly persisting @playwright/cli developer tooling, or adding or regenerating Playwright Test Agent definitions for a compatible Node Playwright…
playwright-testing
Use for explicitly requested live browser investigation with playwright-cli, or for writing, debugging, reviewing, or hardening Playwright tests in an existing working harness across Node, Python, .NET, or Java. Covers flake triage, locator refinement, visual and responsive checks, test structure, fixtures, auth-state…