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 zwl467135974/lumina --skill browser-controlgit clone --depth 1 https://github.com/zwl467135974/luminaWrote 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/zwl467135974/lumina/browser-control)<a href="https://agentmods.dev/skills/zwl467135974/lumina/browser-control"><img src="https://agentmods.dev/badge/skills/zwl467135974/lumina/browser-control/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/zwl467135974/lumina/browser-control"><img src="https://agentmods.dev/badge/skills/zwl467135974/lumina/browser-control.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 | $0.00050 | $0.00810 |
| Opus 5.5 | $0.00020 | $0.00324 |
| Sonnet 5.5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
browser-control 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.
What it actually says
浏览器控制(Playwright)
通过 MCP 接入的官方 @playwright/mcp 工具面驱动真实浏览器。工具命名规则为
mcp__{server}__{tool},下文以 server 名 playwright 为例(实际前缀以当前
环境的 MCP 配置为准)。
核心工作流:快照 → 定位 → 操作 → 留证
- 打开页面:
mcp__playwright__browser_navigate(url)。等待加载完成后 先取结构化快照,不要急于截图。 - 读取结构:
mcp__playwright__browser_snapshot。返回页面的可访问性 树,每个可交互元素带ref编号——这是后续操作的定位依据。 - 定位操作:
browser_click(element, ref)、browser_type(element, ref, text)、browser_fill_form(fields)、browser_select_option(element, ref, values)、browser_press_key(key)。必须使用快照中的 ref 定位,不要凭记忆猜 CSS 选择器;页面变化后重新取快照再操作。 - 视觉留证:
browser_take_screenshot仅在需要视觉证据(布局、颜色、 渲染问题)时使用;结构化信息一律以快照为准,省 token 且更精确。
页面状态与多标签
- 弹出对话框(alert/confirm/prompt):先
browser_handle_dialog(accept), 不要让对话框阻塞后续操作。 - 新窗口/弹出页:操作后用
browser_tabs(action: "list")观察全部标签页,browser_tabs(action: "select", index: n)切换。 - 等待动态内容:
browser_wait_for(text=..., time=...),不要连续无脑重试。
排障顺序
页面不符合预期时按序排查:
- 重新
browser_snapshot确认当前真实状态(可能已被重定向); browser_console_messages(level: "error")看前端报错;browser_network_requests确认关键请求是否成功(4xx/5xx/超时);- 仍无头绪再截图人工判读。
纪律
- 快照优先:能用快照解决的绝不用截图,能用文本绝不用视觉。
- ref 时效:任何 click/type 之后页面可能变化,长流程中定期重新快照。
- 数据落库:采集到的结构化数据写入任务结果或文件,不要只留在对话里。
- 退出:任务结束调用
browser_close释放浏览器进程。
边界
- 浏览器运行在 Lumina 服务端所在主机,访问目标受部署层网络策略约束;
内网/环回地址可能被
--blocked-origins拦截,属预期行为。 - 文件系统访问默认限定工作区根目录,
file://导航被禁用。
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 · 55 lines · 50 tokens per session scan A 56cd6b07949a
browser-control is a skill published in the GitHub repository zwl467135974/lumina (91 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 810 once invoked, about $0.0002 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 2026-09-23.
browser-control compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| browser-controlzwl467135974/lumina | Skill | 91 | 1mo ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 12d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | 3d ago | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 911 | 3d ago | MIT | A | 40 | Claude Code |