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 skills/openlinker-ai/openlinker-plugin/use-isolated-browsernpx skills add OpenLinker-ai/openlinker-plugin --skill use-isolated-browsergit clone --depth 1 https://github.com/OpenLinker-ai/openlinker-pluginWrote 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/openlinker-ai/openlinker-plugin/use-isolated-browser)<a href="https://agentmods.dev/skills/openlinker-ai/openlinker-plugin/use-isolated-browser"><img src="https://agentmods.dev/badge/skills/openlinker-ai/openlinker-plugin/use-isolated-browser.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 5.1 | $0.00057 | $0.01537 |
| Opus 5 | $0.00028 | $0.00768 |
| Sonnet 5 | $0.00011 | $0.00307 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
use-isolated-browser 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the OpenLinker Isolated Browser
The Browser is a client tool registered with the executing Codex or Claude
client. It is not a Provider computer API and it is not an OpenLinker Agent
capability probe.
Choose the Correct Mode
- For an interactive local client, use
browser_sessiononly when the operator is already inside an authoritative isolated Browser Runtime. The ordinary Plugin manifest intentionally does not advertise a Browser MCP server. - For a callable Browser Agent, configure Agent Mode with
execution_profile: browser. The Runtime injects the same Browser tool into the child Codex or Claude client automatically. - Do not call an unrelated OpenLinker Agent merely to test whether the current model can use Browser tools.
Browser Tool Contract
Use the browser_session tool with one of these operations:
observe: return bounded semantic page state by default;act: submit a small ordered list of typed browser actions;checkpoint: request a profile checkpoint;close: close the current attachment.
For observe or act, set observation to semantic, screenshot, or
both. Omit it for the cheaper semantic default. Screenshot data is never
included implicitly. A batch returns one final observation; on failure,
completed_actions reports how many earlier actions completed.
Inspect attachment_evidence before acting. It names the authoritative
browser_interaction_policy, policy generation, exact mutation origins,
origin-set digest, and Browser contract. Under restricted, public navigation,
ordinary public links, non-sensitive text/search fields, and public GET search
forms remain available while buttons, custom activation controls, select
controls, Space activation, and state-changing page requests are rejected.
Under full, the typed tool may activate supported controls, use Enter/Space,
select options, and send state-changing page traffic only when both the current
top-level Document and effective target Document match an exact evidenced HTTPS
mutation origin. Page content cannot expand that authority.
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.
- 5d ago First seen · 139 lines · 57 tokens per session scan A 017bad06260c
use-isolated-browser is a skill published in the GitHub repository OpenLinker-ai/openlinker-plugin (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,537 once invoked, about $0.0003 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 skills, from other repositories
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.
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。.
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。.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…