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 byt3bl33d3r/figaro --skill patchright-cligit clone --depth 1 https://github.com/byt3bl33d3r/figaroWrote 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/byt3bl33d3r/figaro/patchright-cli)<a href="https://agentmods.dev/skills/byt3bl33d3r/figaro/patchright-cli"><img src="https://agentmods.dev/badge/skills/byt3bl33d3r/figaro/patchright-cli/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/byt3bl33d3r/figaro/patchright-cli"><img src="https://agentmods.dev/badge/skills/byt3bl33d3r/figaro/patchright-cli.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 | $0.00052 | $0.01760 |
| Opus 5.5 | $0.00021 | $0.00704 |
| Sonnet 5.5 | $0.00010 | $0.00352 |
| Haiku 4.5 | $0.00005 | $0.00176 |
Grade A, and why
patchright-cli 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 2mo 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.
This is a copy
83% identical to playwright-cli — 316 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with patchright-cli
Quick start
# open new browser
patchright-cli open
# navigate to a page
patchright-cli goto https://playwright.dev
# interact with the page using refs from the snapshot
patchright-cli click e15
patchright-cli type "page.click"
patchright-cli press Enter
# take a screenshot (rarely used, as snapshot is more common)
patchright-cli screenshot
# close the browser
patchright-cli close
Commands
Core
patchright-cli open
# open and navigate right away
patchright-cli open https://example.com/
patchright-cli goto https://playwright.dev
patchright-cli type "search query"
patchright-cli click e3
patchright-cli dblclick e7
patchright-cli fill e5 "[email protected]"
patchright-cli drag e2 e8
patchright-cli hover e4
patchright-cli select e9 "option-value"
patchright-cli upload ./document.pdf
patchright-cli check e12
patchright-cli uncheck e12
patchright-cli snapshot
patchright-cli snapshot --filename=after-click.yaml
patchright-cli eval "document.title"
patchright-cli eval "el => el.textContent" e5
patchright-cli dialog-accept
patchright-cli dialog-accept "confirmation text"
patchright-cli dialog-dismiss
patchright-cli resize 1920 1080
patchright-cli close
Navigation
patchright-cli go-back
patchright-cli go-forward
patchright-cli reload
Keyboard
patchright-cli press Enter
patchright-cli press ArrowDown
patchright-cli keydown Shift
patchright-cli keyup Shift
Mouse
patchright-cli mousemove 150 300
patchright-cli mousedown
patchright-cli mousedown right
patchright-cli mouseup
patchright-cli mouseup right
patchright-cli mousewheel 0 100
Save as
patchright-cli screenshot
patchright-cli screenshot e5
patchright-cli screenshot --filename=page.png
patchright-cli pdf --filename=page.pdf
Tabs
patchright-cli tab-list
patchright-cli tab-new
patchright-cli tab-new https://example.com/page
patchright-cli tab-close
patchright-cli tab-close 2
patchright-cli tab-select 0
What ships with it
7 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.
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.
- 2mo ago First seen · 279 lines · 52 tokens per session scan A e809d6663c3f
patchright-cli is a skill published in the GitHub repository byt3bl33d3r/figaro (154 stars, last pushed 7mo ago), licensed MIT. It adds 52 tokens to every session and 1,760 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to playwright-cli, differing in 316 lines, and is treated as a copy.
Other skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
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.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser-skill
Use a real web browser - read pages through their accessibility tree, click and type by reference, call the tools a site offers (WebMCP), and hand the page to the owner for logins, CAPTCHAs and final confirmations.