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 KunanonJ/ai-skills-hub --skill aside-browsergit clone --depth 1 https://github.com/KunanonJ/ai-skills-hubWrote 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/kunanonj/ai-skills-hub/aside-browser)<a href="https://agentmods.dev/skills/kunanonj/ai-skills-hub/aside-browser"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/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.
<a href="https://agentmods.dev/skills/kunanonj/ai-skills-hub/aside-browser"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/aside-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 | $0.00058 | $0.02146 |
| Opus 5 | $0.00029 | $0.01073 |
| Sonnet 5 | $0.00012 | $0.00429 |
| Haiku 4.5 | $0.00006 | $0.00215 |
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 7d 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. Copies of this mod
1 near-identical copy found in the catalogue:
- browser — 98% identical, 18 lines differ
How it starts
The opening of the file, as written. The whole thing — 166 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 execspawns 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 replstarts 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-likePage.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 aspage.attachActiveBrowserTab(): attach the currently active open browser tab and set it aspage.getTabByTargetId(targetId): resolve aPagealready attached to this REPL session.openTab(url): open a tab, wait until interactive, and updatepageandtabs.closeTab(tab): close a tab and updatepageandtabs.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.
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.
- 7d ago First seen · 166 lines · 58 tokens per session scan A f0ba0064287a
aside-browser is a skill published in the GitHub repository KunanonJ/ai-skills-hub (5 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,146 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 2026-09-03.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
sdd-research
Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.
skill-improver
Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.