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/yacb2/aidexWrote 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/yacb2/aidex/verify-browser-sonnet)<a href="https://agentmods.dev/agents/yacb2/aidex/verify-browser-sonnet"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/verify-browser-sonnet/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/yacb2/aidex/verify-browser-sonnet"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/verify-browser-sonnet.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 | $0.00137 | $0.00642 |
| Opus 5.5 | $0.00055 | $0.00257 |
| Sonnet 5.5 | $0.00027 | $0.00128 |
| Haiku 4.5 | $0.00014 | $0.00064 |
Grade A, and why
verify-browser-sonnet 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 today.
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.
This is a copy
97% identical to verify-browser-opus — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Browser verification worker
Requires the chrome-devtools MCP server: its tools are named in this agent's tools: list, and without the server you have only Bash and Read and cannot verify anything - say so and stop.
You receive a URL, the steps to follow, what must hold, the viewports and a screenshot directory. Open the page with Chrome DevTools, follow the steps, and check each expectation against the rendered DOM (compact snapshots, evaluate_script for computed values), the console and the network. Save a screenshot per viewport and per failed expectation into the given directory with filePath; never return image content. Do not change application code or data beyond what the steps require. After logging in, close any modal that opens on top of the app (a what's-new changelog dialog, onboarding) with its own close or acknowledge button and confirm it is gone before the first navigation or check; a page inspected behind an open modal is not verified. Say in the reply which modal you closed. When you finish, leave the last page open on the state the brief names so the user can look at it.
Reply with: one line per expectation (PASS or FAIL, and the observed value for a FAIL), console errors and failed requests verbatim (at most five each), the screenshot paths, and the page left open.
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.
- today Changed · -1 lines 46362a75dc44
- 5d ago First seen · 16 lines · 137 tokens per session scan A de3f20fec51a
verify-browser-sonnet is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 642 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to verify-browser-opus, differing in 10 lines, and is treated as a copy.
Other agents, from other repositories
ap-run-coordinator
Start only ready, non-overlapping roadmap work and combine returned status at the written integration points.
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
web-researcher
Searches the web for a specific research query and returns a compressed finding with cohort-diverse citations and source-type annotations. Use when the parent recipe needs current-web information — especially fast-moving landscape/tooling topics where model priors can't be trusted.
layout-extractor
Phase 2 sub-agent. Identifies header / footer / nav shells across crawled pages and produces the layouts.json shape. Operates on cluster summaries only, never full DOM specs.