skill-body

skill-body is a skill for Claude Code, Codex from citrolabs/ego-lite. It costs 0 tokens per session (5,497 once invoked), scanned A, original, MIT.

A reference guide for running browser automation scripts with ego-browser. It explains how to inspect pages, open web addresses, and look up the signatures and less common options of browser APIs.

In plain words
What is it for?
Use it to automate and inspect web pages, take page snapshots, navigate with scripts, and check how APIs such as page.click work.
Why use it?
It removes guesswork about the browser commands and shell syntax needed to run them. It also points to installation instructions when the browser connection does not work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to automate and inspect web pages, take page snapshots, navigate with scripts, and check how APIs such as page.click work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/citrolabs/ego-lite/skill-body
About the project

ego lite is a browser built for people and AI agents to use at the same time, letting agents work with the user's existing tabs, logins, cookies, extensions, and bookmarks. It supports browser automation tasks for agents such as Codex and Claude Code, with agents working in separate Spaces while the user keeps control of their tabs. The catalogue entry provides the ego-browser skill for operating it.

citrolabs/ego-lite · 17,509 stars · on GitHub · lite.ego.app

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 citrolabs/ego-lite --skill skill-body
Clone the repo
git clone --depth 1 https://github.com/citrolabs/ego-lite

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 skill-body

README.md
[![agentmods](https://agentmods.dev/badge/skills/citrolabs/ego-lite/skill-body/github.svg)](https://agentmods.dev/skills/citrolabs/ego-lite/skill-body)
Your own site
<a href="https://agentmods.dev/skills/citrolabs/ego-lite/skill-body"><img src="https://agentmods.dev/badge/skills/citrolabs/ego-lite/skill-body/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 skill-body

Your own site · 80×15
<a href="https://agentmods.dev/skills/citrolabs/ego-lite/skill-body"><img src="https://agentmods.dev/badge/skills/citrolabs/ego-lite/skill-body.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,497 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 $0.00000 $0.05497
Opus 5.5 $0.00000 $0.02199
Sonnet 5.5 $0.00000 $0.01099
Haiku 4.5 $0.00000 $0.00550

Measured today against content hash 580aca2a16cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-body 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 today.

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, options)`, `cdp(method, params, options)`
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

package/ego-browser/skill-body/SKILL.md · 552 lines

How it starts

The opening of the file, as written. The whole thing — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ego-browser

Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.

Run browser scripts

Pass the script to ego-browser nodejs. The form depends on the shell that runs the command: heredoc is Bash/Zsh syntax and does not exist in PowerShell or cmd.

Bash, Zsh, Git Bash

ego-browser nodejs <<'EOF'
const task = await taskSpace("inspect example page");
const page = task.page("p1");
await page.goto("https://example.com");

console.log({ taskSpaceId: task.spaceId, page: page.label });
console.log(await page.snapshot());
EOF

When a sandbox blocks heredoc input, use -e instead. Use single quotes around the code and double quotes for JavaScript strings; single quotes within the code require shell quoting.

ego-browser nodejs -e '
const task = await taskSpace("inspect example page");
await task.page("p1").goto("https://example.com");
console.log(task.spaceId);
'

PowerShell

PowerShell has no heredoc, and Windows PowerShell 5.1 drops the double quotes inside an argument when it calls a native program, which splits the script into several arguments. Do not pass a script that contains double quotes or spans several lines to -e. Write it to a UTF-8 .mjs file instead and evaluate an ASCII-only one-line entry point, which needs no double quotes of its own:

ego-browser nodejs -e "await import('file:///C:/Users/<name>/ego/task.mjs')"

The imported module runs with the same helpers and console as an inline script, so the whole task belongs in the .mjs file. Use forward slashes in the file:/// URL. Non-ASCII content such as Chinese text must stay inside the file: never put it in a -e argument.

Do not pipe the file in with Get-Content. Windows PowerShell 5.1 reads a UTF-8 file as ANSI and sends ASCII to native programs, which corrupts non-ASCII text and truncates strings. PowerShell has no < input redirection either.

Read the full file on GitHub · 552 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. today First seen · 552 lines · 0 tokens per session scan A 580aca2a16cc

Subscribe to this mod's changes

skill-body is a skill published in the GitHub repository citrolabs/ego-lite (17,509 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,497 tokens. 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 2026-10-17.

Related

Other skills, from other repositories

actionbook-web-test

Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…

actionbook/actionbook · 71 tokens

active-research

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch operations, stealth browsing, and intelligent page analysis. Use when user asks to research, analyze, investigate…

actionbook/actionbook · 72 tokens

actionbook-scraper

Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.

actionbook/actionbook · 28 tokens

extract

Extract structured data from websites and produce an executable Playwright script plus extracted data. Use when the user wants to scrape, extract, pull, collect, or harvest data from any website — product listings, tables, search results, feeds, profiles, or any repeating content.

actionbook/actionbook · 56 tokens

actionbook

Activate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors.

actionbook/actionbook · 50 tokens

agent-browser

Automates browser interactions for form filling and web page interaction. Used by the request-website command to submit website indexing requests.

actionbook/actionbook · 28 tokens