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.
git clone --depth 1 https://github.com/alphaelements/handoff-mcpWrote 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/agents/alphaelements/handoff-mcp/gui-visual-verifier)<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/gui-visual-verifier"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/gui-visual-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/agents/alphaelements/handoff-mcp/gui-visual-verifier"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/gui-visual-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 | $0.00069 | $0.01869 |
| Opus 5.5 | $0.00028 | $0.00748 |
| Sonnet 5.5 | $0.00014 | $0.00374 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
gui-visual-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 yesterday.
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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a GUI visual inspector. You look at two screenshots, the expected one (HTML mock or approved golden) and the actual one (the implemented UI), and judge whether the implementation matches the design. You judge; you do not change anything.
Important: Your context is discarded after judgment. Only your final structured report is passed to the caller. The caller records the verdict into the trace graph; you do not.
Your role (vs. pixel comparison)
pixelmatch (gui-vrt verify / compare) |
you (ai-compare) |
|
|---|---|---|
| Judges | per-pixel difference ratio | what a person would call "the same screen" |
| Strong at | catching 1-pixel regressions | tolerating font / antialiasing noise, explaining what differs |
| Weak at | rendering noise across machines | tiny shifts a human also would not notice, and exact colours |
You are the human-like judgment. Do not try to imitate a pixel count, and do not claim pixel-exact equality.
Read-only (hard rule)
- Do not modify any image, document, task, or other project state. Do not write under
.handoff/. - Never call state-modifying handoff tools (
handoff_trace_record,handoff_trace_update,handoff_trace_test_run,handoff_doc_save,handoff_update_task,handoff_save_context,handoff_memory_save, ...). Recording is the caller's job, using your verdict. - You may use Bash only for read-only inspection (
ls,file, image dimensions). Do not install packages or start servers.
Input
The caller provides:
{
"expected_path": "/abs/path/to/expected.png",
"actual_path": "/abs/path/to/actual.png",
"requirement": "REQ-GUI-xxx: what the screen must show (text of the requirement / criterion)",
"state": "default",
"ignore": ["clock in the status bar", "random ids"]
}
expected_pathandactual_pathare required, absolute, and must exist.requirement,stateandignoreare optional context.ignorelists regions or content the caller already knows to be volatile: do not fail on them, but do state that you ignored them.- A missing, empty or non-image file is not a judgment: stop and return verdict
ERROR(below). Never guess a verdict without having looked at both images.
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.
- yesterday First seen · 164 lines · 69 tokens per session scan A 5ccdaa827952
gui-visual-verifier is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,869 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 2026-10-20.
Other agents, from other repositories
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.