aside-browser

aside-browser is a skill for Claude Code, Codex from joonlab/joonlab-claudecode-setting-for-share. It costs 58 tokens per session (2,806 once invoked), scanned A, original, MIT.

A browser tool for automating websites and apps, including services where the user is already signed in. It offers both an autonomous task runner and direct, Playwright-compatible browser controls.

In plain words
What is it for?
Use it for website testing, clicking and filling forms, working in services such as Slack or LinkedIn, capturing screenshots, checking network activity, and downloading files.
Why use it?
It removes the need to manually repeat browser actions or pass around login details. Direct controls also help inspect exact page state, verify results, take screenshots, and download files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for website testing, clicking and filling forms, working in services such as Slack or LinkedIn, capturing screenshots, checking network activity, and downloading files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joonlab/joonlab-claudecode-setting-for-share/aside-browser
Install

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.

Any agent
npx skills add joonlab/joonlab-claudecode-setting-for-share --skill aside-browser
Clone the repo
git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-share

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for aside-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/aside-browser/github.svg)](https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/aside-browser)
Your own site
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/aside-browser"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/aside-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.

agentmods 80×15 button for aside-browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/aside-browser"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/aside-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.02806
Opus 5 $0.00029 $0.01403
Sonnet 5 $0.00012 $0.00561
Haiku 4.5 $0.00006 $0.00281

Measured 8d ago against content hash 6eb8d3bfeca3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aside-browser 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 8d 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.

- `fetch(url)`: cookie-bearing HTTP; use only for safe same-origin or trusted direct-download GET/HEAD requests.
claude/skills/aside-browser/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aside Browser

Aside is an AI browser. Inside Aside is an inteligent agent designed to handle complex tasks across user's logged-in accounts, cookies, websites and SaaS tools the user uses, and browsing histories. Aside has CLI interface that exposes its agent's prompt execution surface (aside exec) and browser automation tools (aside repl).

There are two ways of controlling Aside:

  • aside exec spawns Aside's agent session. think of it like spawning subagent. Use when you need to work across user's logged-in accounts, apps (e.g. Slack, X, LinkedIn, etc.), memory, and browsing history.
  • aside repl starts JS REPL session that provides Playwright-compatible, low-level browser interaction tools. Use when you need to inspect screenshot / DOM / evidence directly, perform deterministic UI steps, verify exact state, capture screenshots, or download files.

Choose the Surface

  • Whole-task delegation to Aside's autonomous browser agent: aside exec.
  • Direct evidence, downloads, screenshots, exact verification, or sensitive logged-in work: aside repl.

Before using the CLI, inspect current usage instead of relying on memorized options:

aside --help
aside exec --help
aside repl --help

both aside exec and aside repl opens new ephemeral session that keeps context and state. use interactive PTY for aside CLI commands: the session will be deleted as the CLI process exists.

exec usages

Think using Aside agent as aside exec like using browser-special subagent. After entering the command, the CLI will show Aside agent's thinking and tool call status. poll it and watch it. give user status update around every 60 seconds. the user can't see what's going in Aside CLI background, so you have to restate and give update to user.

REPL Usages

The REPL is a persistent ES2023+ JavaScript environment within one live REPL session. Top-level const and let bindings persist, so use fresh variable names.

Available globals:

  • page: current Playwright-like Page.
  • tabs: open pages in this REPL session.
  • listBrowserTabs(): list currently open Aside Browser tabs without attaching to them.
  • attachBrowserTab(targetId): attach an open browser tab to this REPL session and set it as page.
  • attachActiveBrowserTab(): attach the currently active open browser tab and set it as page.
  • getTabByTargetId(targetId): resolve a Page already attached to this REPL session.
  • openTab(url): open a tab, wait until interactive, and update page and tabs.
  • closeTab(tab): close a tab and update page and tabs.
  • snapshot(page, options?): primary page-reading API; returns { tree, diff }.
  • annotatedScreenshot(page), page.screenshot(): visual verification.
  • page.pdf(options?): print the current page to PDF; save user-visible PDFs under ./artifacts/, e.g. await page.pdf({ path: './artifacts/page.pdf', format: 'A4' }).
  • fetch(url): cookie-bearing HTTP; use only for safe same-origin or trusted direct-download GET/HEAD requests.
  • fs, path, Buffer, sleep, display, pwd.

Read the full file on GitHub · 173 lines

Changes

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.

  1. 8d ago First seen · 173 lines · 58 tokens per session scan A 6eb8d3bfeca3

Subscribe to this mod's changes

aside-browser is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 2,806 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

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.

pinchtab/pinchtab · 52 tokens

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.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens