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 joinwell52-AI/CodeFlowMu-open --skill browser-usegit clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-openWrote 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/joinwell52-ai/codeflowmu-open/browser-use)<a href="https://agentmods.dev/skills/joinwell52-ai/codeflowmu-open/browser-use"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/browser-use/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/joinwell52-ai/codeflowmu-open/browser-use"><img src="https://agentmods.dev/badge/skills/joinwell52-ai/codeflowmu-open/browser-use.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 | $0.00093 | $0.00781 |
| Opus 5.5 | $0.00037 | $0.00312 |
| Sonnet 5.5 | $0.00019 | $0.00156 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
browser-use 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Use
Operate approved Web applications through visible, headful Chrome or Edge sessions. Behave like a bounded digital employee, not a crawler.
Workflow
- Call
browser.list_targetsand follow the configured browser and structuredloginProfilesemantics. - Call
browser.open_target; reuse the returned tab when possible. - Call
browser.snapshotorbrowser.findto obtain an exact selector. Never guess or persist brittle coordinates, CSS paths, or XPath. - Use
browser.click,browser.fill, orbrowser.selectfor visible controls. Usebrowser.fill_credentialsfor saved passwords; never request or echo the stored password. - Use
browser.uploadonly for files the user explicitly authorized. It attaches files through the page input without operating a Windows dialog. - Verify each meaningful action with a fresh snapshot, a visible selector, the URL, or a success state.
- Call
browser.cancelwhen the user asks to pause. Claim pause only afterbrowser.statusconfirms it. Resume only on explicit instruction.
For a new or changed login page, call browser.record_login_start, let the user complete one normal login, then call browser.record_login_finish. The generated semantic profile is a draft for user review; password and verification-code values are never recorded.
For a recorded login, call browser.login with target_id; tab_id is optional and the tool atomically opens/reuses/reconnects the correct tab, fills credentials, and selects the recorded company/tenant. Reuse the returned tab_id for browser.submit_login. Do not call open_target again between verification and submission. Report success only when browser.verify_login returns authenticated: true.
Routing
- Web DOM, forms, login, upload, and page navigation: Browser Use.
- Native EXE windows and Windows UI Automation: Windows Use.
- A combined workflow may use both. Switch only when the active interaction surface changes.
Digital-employee boundaries
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.
- 2mo ago First seen · 50 lines · 93 tokens per session scan A 06c5fae09f0f
browser-use is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 781 once invoked, about $0.0004 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
dsh-record-browser-gif
A workflow for recording a real browser application as a GIF demonstration. It operates the running app, captures the interaction, encodes the frames, and checks the resulting file.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
web-app-qa
Test a web app the way a real user would: click through the main flows, try odd inputs, watch for errors, and keep screenshots as proof. You get a bug report ranked by how serious each problem is.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
dsh-engineering
An engineering guide for implementing features, fixing bugs, and maintaining a project's AI engineering rules. It uses the project's existing code, callers, checks, documentation, and conventions rather than applying a generic template.