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/oneworks-ai/app/external-browser-drivernpx skills add oneworks-ai/app --skill external-browser-drivergit clone --depth 1 https://github.com/oneworks-ai/appWhat 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 | $0.00024 | $0.00442 |
| Opus 5 | $0.00012 | $0.00221 |
| Sonnet 5 | $0.00005 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
external-browser-driver 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.
What it actually says
Browser Control
Browser Control currently controls Google Chrome through the OneWorks extension. Its browser-facing contract is transport-neutral so future extension transports, such as Firefox, can implement the same capability without renaming the product.
- Call
chrome_capabilitiesbefore using a capability family for the first time. Missing permissions are recoverable: ask the user to grant the named group from the Chrome extension popup, then retry. The OneWorks page reports permission state but never grants Chrome permissions itself. - Discover targets with
chrome_windows,chrome_tabs, andchrome_frames. Never guess IDs or rely on an implicit current tab. - Reuse the returned
tab_id,frame_id, anddocument_id. Refresh the target/snapshot afterTARGET_NOT_FOUNDorDOCUMENT_CHANGED. - Prefer
execute_chrome_workflowfor ordered page-local work. Independent tab workflows may be submitted together withexecute_chrome_workflows. - High-risk operations return
CONFIRMATION_REQUIRED; describe the audit summary and wait for the user to approve it in the extension/OneWorks UI before retrying. - Prefer semantic operations. Use
chrome_raw,chrome_cookies.list_with_values,chrome_page.snapshot_sensitive, orchrome_page.type_sensitiveonly when the matching OneWorks advanced-access preference has been applied to the connected browser and capability discovery reports it enabled. Raw is a browser-session-wide superset of cookie/sensitive-field access and executes globally exclusively. Always supply the intendedtab_idand expected origin; the bridge and extension additionally negotiate and enforce an exact full-URL fingerprint without exposing query or fragment values. Review the R4 preview and obtain confirmation for every use. - Never claim access to Chrome Password Manager: Chrome exposes no extension API for reading or exporting saved passwords. Sensitive page operations cover only page fields, DOM, and storage. Do not request host file-system paths, host-process code execution, cross-origin bypasses outside the explicit Raw capability, or silent permission grants.
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.
- 2d ago First seen · 19 lines · 24 tokens per session scan A 0806dbd5a38c
external-browser-driver is a skill published in the GitHub repository oneworks-ai/app (18 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 442 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
lov-fill-web-form
Fill web forms by fetching form fields from a URL, deep-searching the user's local knowledge base for relevant info, and generating a markdown document with all answers pre-filled. Use when the user provides a URL to a web form (conference application, speaker submission, event registration, profile form) and wants…
agent-browser
为 Agent 设计的自动化浏览器 CLI 工具，也能操作 Electron 桌面应用。当需要与网站交互（包括页面导航）时使用.
deva-cloak
Drive CloakBrowser stealth Chromium inside the deva cloak container - a headed, anti-detection browser for scraping, automation, or checking a site the way a real browser sees it. Use when the task needs a browser that bypasses bot detection (Cloudflare, FingerprintJS, reCAPTCHA scoring), or when the user asks to…
browser-testing
定义了使用浏览器开发者工具进行端到端（E2E）测试的工作流，测试用例以 Markdown 文件形式记录。.
twitter-watch
提取一系列 Twitter 推文的互动数据并整合生成报告.
preview-json
Render and preview JSON files in browser with syntax highlighting, collapsible tree view, and search.