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 xcrft/mastermind --skill mastermind-browser-verificationgit clone --depth 1 https://github.com/xcrft/mastermindWrote 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/xcrft/mastermind/mastermind-browser-verification)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-browser-verification"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-browser-verification/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/xcrft/mastermind/mastermind-browser-verification"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-browser-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00797 |
| Opus 5.5 | $0.00026 | $0.00319 |
| Sonnet 5.5 | $0.00013 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
mastermind-browser-verification 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind browser verification
An agent that says "I checked it in the browser and it works" has produced no evidence. The claim cannot be re-read, cannot be compared against the next run, and cannot be distinguished from not having looked.
Browser checks are worth running. They just have to leave something behind.
The accessibility tree is the evidence; the screenshot is not
Read the page as an accessibility tree, not as an image. The tree is text: it can be quoted in the report, diffed against the next run, and checked against a criterion like "the disabled control is not focusable" or "the empty state renders". A screenshot proves nothing to anything downstream — it is for a human to look at, and it belongs in the report as an attachment, never as the basis of a claim.
Concretely: assert on roles, names, and states from the tree. "Submit button
present, disabled state set, error text Card expired associated with the
input" is evidence. "Looks right" is not.
Console and network errors are mechanical failures
Read console messages filtered to errors, and network requests for failed responses. A page that throws during render, or 404s on an asset, has failed — that is not a matter of taste and does not need a screenshot to establish.
Record the count and the messages. A clean console is itself an observation worth recording, because next week's run will want something to compare against.
Viewports and colour scheme are a checklist, not a vibe
Resize deliberately and record each result: mobile, tablet, desktop, and the dark scheme if the product has one. "Responsive" as a bare claim means the agent did not resize. Three recorded observations at three widths mean it did.
If a viewport was not checked, it is not checked — see below.
Record what you checked and what you did not
Every browser observation goes into the report with its scope:
### Browser observations
- `read_page` at 375px — nav collapsed to a menu button; primary CTA present and enabled.
- Console — 0 errors, 0 warnings.
- Network — no failed requests.
- Dark scheme — **not checked** (no dark palette in this change).
- Visual fidelity against the frame — **not checked** (needs human review).
What ships with it
1 file 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 · 83 lines · 64 tokens per session scan A 3ccd0c10b7e5
mastermind-browser-verification is a skill published in the GitHub repository xcrft/mastermind (13 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 797 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 2026-08-30.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…