Browser Manager

A small browser-window manager for opening, listing, checking, and closing stand-alone browser windows.

In plain words
What is it for?
Use it to open a website, see which browser windows are available, check their state, or close one or all of them.
Why use it?
It keeps website visits in separate browser surfaces and lets an agent identify the correct window before interacting with it.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/binary16labs/prime-silo/browser-manager
Any agent
npx skills add binary16labs/prime-silo --skill browser-manager
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo

Made for: Claude Code, Codex.

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00292
Opus 5 $0.00005 $0.00146
Sonnet 5 $0.00002 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash b6e1f7e426bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Browser Manager 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 2d 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.

Origin

This is a copy

100% identical to Browser Manager — 11 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.

app/L0/_all/mod/_core/skillset/ext/skills/browser-manager/SKILL.md · 49 lines

What it actually says

Use this skill for browser window management on the onscreen agent

transient

  • currently open web browsers in _____transient lists browser id|url|title for stand-alone and inline browser surfaces

main helpers

  • space.browser.open(urlOrOptions?)
  • space.browser.create(urlOrOptions?) = same as open(...)
  • space.browser.close(id)
  • space.browser.closeAll()
  • space.browser.list(), ids(), count(), has(id), state(id)

rules

  • visiting another website means open or navigate a stand-alone browser window, never leave the current runtime page
  • use numeric browser ids like 1
  • prefer the transient browser list or space.browser.list() over guessing ids
  • when at least one browser surface is open, the full auto-loaded browser-control skill covers navigation, page reads, refs, clicks, typing, and history actions

examples Opening a browser window now _javascript return await space.browser.open("https://example.com")

Closing browser 1 now _javascript return space.browser.close(1)

Closing all browser windows now _javascript return { closed: space.browser.closeAll() }

Changes

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.

  1. 2d ago First seen · 49 lines · 10 tokens per session scan A b6e1f7e426bd

Subscribe to this mod's changes

Browser Manager is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 9d ago), licensed MIT. It adds 10 tokens to every session and 292 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Browser Manager, differing in 11 lines, and is treated as a copy.

Related

Other skills, from other repositories

xh

Use when the agent or user needs to make an HTTP request from the shell - GET a URL, POST JSON to an API, check a webhook with auth, test a REST endpoint, fetch and inspect headers, or upload a file.

moabualruz/fulcrum · 49 tokens

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

dingtalk_channel_connect

使用可视浏览器自动完成 QwenPaw 的钉钉频道接入。适用于用户提到钉钉、DingTalk、开发者后台、Client ID、Client Secret、机器人、Stream 模式、绑定或配置 channel 的场景;支持遇到登录页时暂停,等待用户登录后继续。.

agentscope-ai/QwenPaw · 78 tokens

browser_cdp

Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.

agentscope-ai/QwenPaw · 70 tokens

browser_cdp

当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 cdpport,或让多个 agent / 工具共享同一个浏览器时,使用本 skill。browser 默认不开放调试端口;仅当用户明确希望其他本地工具附加时才显式传入 cdpport。.

agentscope-ai/QwenPaw · 85 tokens

browser_visible

当用户需要控制 browser 的浏览器启动方式时,使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口(需让其他本地工具附加时显式传 cdpport);headed 控制是否显示窗口,privatemode 保留用于兼容、不再改变默认行为,browserargs 传入额外的 Chromium 启动参数,executablepath 指定自定义浏览器可执行文件路径。.

agentscope-ai/QwenPaw · 108 tokens