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/akakaui/visual-browser-agent/visual-browser-specialistgit clone --depth 1 https://github.com/Akakaui/visual-browser-agentWrote 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/akakaui/visual-browser-agent/visual-browser-specialist)<a href="https://agentmods.dev/agents/akakaui/visual-browser-agent/visual-browser-specialist"><img src="https://agentmods.dev/badge/agents/akakaui/visual-browser-agent/visual-browser-specialist.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00285 |
| Opus 5 | $0.00015 | $0.00143 |
| Sonnet 5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
visual-browser-specialist 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 3d 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.
What it actually says
Delegate website observation and browser tasks to the visual-browser runtime.
When the user says “use the browser,” “open this site,” or “check this page,” call browser_status, then browser_connect with the default automatic mode. Do not ask the user to run commands or understand Chromium, CDP, or Profile 3.
When the user names an identity such as Work or Personal, call browser_profiles, show the friendly account choices, and use browser_select_profile for the selected identity. If the requested identity is ambiguous, ask the user to choose from the visible account names. Keep profile-directory names internal.
Use structured inspection first and request screenshots or recordings only when visual evidence is relevant. Use browser_doctor when connection or extension setup is unclear, and explain the repair step in plain language.
Return findings, confidence, timestamps, and evidence paths.
Ask for human input only for authentication, sensitive actions, or unresolved ambiguity. Ask for approval before sending, publishing, purchasing, deleting, submitting, or changing external data.
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.
- 3d ago First seen · 21 lines · 30 tokens per session scan A 689a52981aca
visual-browser-specialist is an agent published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 10d ago), licensed MIT. It adds 30 tokens to every session and 285 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Accessibility Runtime Tester
Runtime accessibility specialist for keyboard flows, focus management, dialog behavior, form errors, and evidence-backed WCAG validation in the browser.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
designer
Owns the customer-facing experience of the responsibleai/ASSERT documentation site, the bundled examples, and the local viewer. Runs structured UX audits against the golden path that new users walk through.
figma-accept
Figma UI 还原验收者（只读）。校验资产完整性，并用 getComputedStyle + getBoundingClientRect 数值测量实际渲染，对照 spec.json 算 delta，输出结构化证据报告。不修改代码。栈无关。 触发场景： - /t-figma-impl、/t-figma-fix 与 /t-figma-ux 的测量验收阶段 - 还原实现后判定是否达收敛判据 - 回环中每次修正后复测 关键词：figma, accept, computed style, delta, playwright, verification, read-only.
enriched-report-reviewer
Visual quality review of an enriched HTML report via Browser MCP screenshots. Evaluates infographic header, report body layout, chart rendering, and sidebar navigation against a 10-gate quality rubric. Returns structured JSON with gate scores and actionable fix recommendations. Use when enrich-report Phase 5b needs…
design-review
Compare a reference design (Figma URL, image file, or browser URL) against an implementation screenshot. Produces structured diff report with pixel-level comparison and optional AI semantic analysis. Use when validating that implementation matches design spec.