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 Starchild-ai-agent/official-skills --skill control-browsergit clone --depth 1 https://github.com/Starchild-ai-agent/official-skillsWrote 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/starchild-ai-agent/official-skills/control-browser)<a href="https://agentmods.dev/skills/starchild-ai-agent/official-skills/control-browser"><img src="https://agentmods.dev/badge/skills/starchild-ai-agent/official-skills/control-browser/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/starchild-ai-agent/official-skills/control-browser"><img src="https://agentmods.dev/badge/skills/starchild-ai-agent/official-skills/control-browser.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 | $0.00097 | $0.02444 |
| Opus 5.5 | $0.00039 | $0.00978 |
| Sonnet 5.5 | $0.00019 | $0.00489 |
| Haiku 4.5 | $0.00010 | $0.00244 |
Grade B, and why
control-browser scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
error alone, and NEVER tell the user to run `starchild agent-shell` — the The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docs/all-tabs-cleanup.md 2.7 KB
- docs/api-use-behavior.md 7.5 KB
- docs/bootstrap-troubleshooting.md 3.2 KB
- docs/browser-control-interruption.md 2.8 KB
- docs/browser-safety.md 3.7 KB
- docs/browser-troubleshooting.md 4.9 KB
- docs/chrome-troubleshooting.md 3.0 KB
- docs/confirmations.md 3.2 KB
- docs/file-uploads.md 3.3 KB
- docs/local-web-development.md 2.6 KB
- docs/screenshots.md 2.2 KB
- docs/tab-claiming-chrome.md 7.5 KB
- docs/tab-cleanup-chrome.md 2.6 KB
- docs/visibility.md 3.8 KB
- docs/webmcp.md 2.0 KB
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 Changed · +20 lines scan A → B 8926a6f964be
- 1mo ago First seen · 174 lines · 97 tokens per session scan A 21c95fe42000
control-browser is a skill published in the GitHub repository Starchild-ai-agent/official-skills (29 stars, last pushed 4d ago), with no licence file. It adds 97 tokens to every session and 2,444 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
react-component-testing
Applies the three-tier test taxonomy for React applications: unit tests for hooks and pure logic, component tests for behavior and interactions, and end-to-end tests for user flows. Uses Vitest, React Testing Library, and Playwright while focusing on observable behavior over implementation details.
webapp-testing
Test local web applications using browser automation - verify frontend functionality, debug UI behavior, capture screenshots, view console logs, run E2E scenarios, and check accessibility.
ui-design-patterns
Common interface patterns, navigation patterns, form patterns, data display patterns, feedback patterns, and accessibility considerations.
shadcn-skills
Installation, components, blocks, forms, theming, and MCP guidance for shadcn/ui in modern Next.js projects using pnpm.
shadcn-skills
Installation, components, blocks, forms, theming, and MCP guidance for shadcn/ui in modern Next.js projects using pnpm.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…