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 stickerdaniel/browserjack --skill browsergit clone --depth 1 https://github.com/stickerdaniel/browserjackWrote 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/stickerdaniel/browserjack/browser)<a href="https://agentmods.dev/skills/stickerdaniel/browserjack/browser"><img src="https://agentmods.dev/badge/skills/stickerdaniel/browserjack/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/stickerdaniel/browserjack/browser"><img src="https://agentmods.dev/badge/skills/stickerdaniel/browserjack/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 | $0.00018 | $0.00267 |
| Opus 5.5 | $0.00007 | $0.00107 |
| Sonnet 5.5 | $0.00004 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
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 18d 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
Use the plugin-provided js MCP tool for browser tasks. The MCP initialization instructions contain the exact verified browser-client URL for the installed ChatGPT.app. Import that URL before using agent.browsers.
For the standard /Applications/ChatGPT.app installation:
if (globalThis.agent?.browsers == null) {
const browserClient =
await import("file:///Applications/ChatGPT.app/Contents/Resources/plugins/openai-bundled/plugins/chrome/scripts/browser-client.mjs");
const runtime = await browserClient.setupBrowserRuntime({ globals: globalThis });
if (runtime != null) globalThis.agent = runtime;
}
var availableBackends = await agent.browsers.list();
When the initialization instructions provide a different URL, use that exact URL instead.
Use OpenAI's browser abstractions rather than implementing CDP, navigation, screenshots, or file uploads yourself. Respect OpenAI's site and upload confirmations. Never bypass browser safety policy through raw CDP or alternative browser interfaces.
Do not print cookies, tokens, form values, private page content, or browser-profile data. Get explicit user approval immediately before an irreversible or externally visible action.
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.
- 18d ago Changed · +3 lines 1564c5209ff8
- 1mo ago First seen · 22 lines · 18 tokens per session scan A 22a44b68200e
browser is a skill published in the GitHub repository stickerdaniel/browserjack (2 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 267 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 2026-08-31.
Other skills, from other repositories
macos-harness
Read and operate the apps on this Mac from the shell. Use it when a task needs an app's UI and no API, CLI or purpose-built tool can do it.
set-lineup
This skill should be used when the user asks to "set my lineup", "start him for me", "swap him into my flex", "update my lineup on Yahoo", "fix my lineup before kickoff", "apply my lineup changes", or wants a lineup change actually applied on their fantasy platform. Drives the user's own logged-in browser session to…
propose-trade
This skill should be used when the user asks to "send the trade", "submit the trade offer", "propose the trade on Yahoo", "send him the offer", "make the trade official", "put the offer in", or wants an agreed trade actually transmitted on their fantasy platform. Drives the user's own logged-in browser session to…
submit-waiver-claim
This skill should be used when the user asks to "put in the claim", "submit my waiver claim", "claim him off waivers", "add him and drop X", "file the waiver for me", "place that bid on Yahoo", or wants a specific add/drop transaction executed on their fantasy platform. Drives the user's own logged-in browser session…
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.