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 jnPiyush/AgentX --skill browser-automationgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/browser-automation)<a href="https://agentmods.dev/skills/jnpiyush/agentx/browser-automation"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/browser-automation/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/jnpiyush/agentx/browser-automation"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/browser-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 137 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00085 | $0.02057 |
| Opus 5.5 | $0.00034 | $0.00823 |
| Sonnet 5.5 | $0.00017 | $0.00411 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
browser-automation scanned grade A 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 23d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Guessing when the MCP server is missing.** If `playwright` MCP server is not loaded, report the missing prerequisite and stop. Do not fall back to `curl`, do not pretend the page rendered, do not synthesize results. How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
When to load: An Frontier FDE needs to render a page in a real browser, interact with it, capture a screenshot, run an accessibility audit, or read JavaScript-rendered content. Most commonly: UX Designer validating prototypes, Consulting Research reading SPAs, Engineer doing quick end-to-end smoke checks.
DEFAULT test surface for UI-bearing changes: Per the always-on rule in
.github/instructions/project-conventions.instructions.md, the agent browser is the DEFAULT testing surface whenever a change renders UI or HTML. The expected pass: render the running build, capture a snapshot/screenshot per primary route, run an axe-core a11y scan, and drive at least one scripted interaction per primary user task. Fall back to non-browser testing only when no UI surface exists or the Playwright MCP server is unavailable -- and report the missing prerequisite rather than silently skipping.
When NOT to load
- Static HTTP fetches (use the agent's normal fetch tool).
- Bulk crawling, scraping behind auth, or anything outside the Frontier security profile's URL allowlist (see Anti-Patterns).
- Desktop GUI automation -- use the upstream
computer-use-and-browser-agentsskill instead. - Long-lived background scrapers -- Frontier FDEs are task-scoped, not service-shaped.
Prerequisites
The Playwright MCP server is not bundled with Frontier. Install it once per workspace:
# 1. Install Playwright MCP (Node-based MCP server, runs via npx)
# Verify Node 20+ is on PATH first:
node --version
# 2. Add to .vscode/mcp.json under "servers":
# {
# "servers": {
# "playwright": {
# "command": "npx",
# "args": ["-y", "@playwright/mcp@latest"]
# }
# }
# }
# 3. Reload the MCP server list in your host (VS Code: "MCP: List Servers" -> Restart).
If the MCP server is not present, an agent that loads this skill MUST report the missing prerequisite and stop, not guess. See "Anti-Patterns" #4.
A follow-up DevOps issue tracks wiring this into the Frontier .vscode/mcp.json template as an opt-in switch. Until then, install per workspace.
What ships with it
1 file 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.
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.
- 23d ago Changed · -1 lines f4d5c48a3656
- 1mo ago Changed 400e51940935
- 1mo ago First seen · 138 lines · 85 tokens per session scan A e6a4eafb35fe
browser-automation is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,057 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…