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 oneworks-ai/app --skill external-browser-drivergit clone --depth 1 https://github.com/oneworks-ai/appWrote 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/oneworks-ai/app/external-browser-driver)<a href="https://agentmods.dev/skills/oneworks-ai/app/external-browser-driver"><img src="https://agentmods.dev/badge/skills/oneworks-ai/app/external-browser-driver/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/oneworks-ai/app/external-browser-driver"><img src="https://agentmods.dev/badge/skills/oneworks-ai/app/external-browser-driver.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 | $0.00024 | $0.00442 |
| Opus 5.5 | $0.00010 | $0.00177 |
| Sonnet 5.5 | $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 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
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.
- 1mo 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 (20 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 442 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ui-regression
This skill should be used when the user asks to "verify UI changes", "audit UI quality", "test every screen and action", "run regression QA", "check a deployed UI", or "validate an extension release". Test known web and browser-extension workflows on localhost, staging, or production with action coverage, recovery…
tavily-usage
This skill should be used when user asks to "search the web", "fetch content from URL", "extract page content", "use Tavily search", "scrape this website", "get information from this link", or "web search for X".
run-qa
This skill should be used when user asks to "run QA", "verify real playback", "test provider connections", or "check website, extension or Android flows" with tracked journeys.
lov-publish-wechat-channels
A browser-based assistant for checking, uploading, saving, scheduling, and publishing local videos to WeChat Channels, WeChat’s short-video platform. It also verifies the resulting draft or publication status.
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…
preview-json
Render and preview JSON files in browser with syntax highlighting, collapsible tree view, and search.