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.
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 citrolabs/ego-lite --skill ego-lite-simplifygit clone --depth 1 https://github.com/citrolabs/ego-liteWrote 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/citrolabs/ego-lite/ego-lite-simplify)<a href="https://agentmods.dev/skills/citrolabs/ego-lite/ego-lite-simplify"><img src="https://agentmods.dev/badge/skills/citrolabs/ego-lite/ego-lite-simplify/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/citrolabs/ego-lite/ego-lite-simplify"><img src="https://agentmods.dev/badge/skills/citrolabs/ego-lite/ego-lite-simplify.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 | $0.00068 | $0.00959 |
| Opus 5 | $0.00034 | $0.00479 |
| Sonnet 5 | $0.00014 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
ego-lite-simplify 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 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.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplify ego-lite
Reduce concepts and maintenance surface, not just line count. Prefer a few well-proven deletions over a long list of guesses.
Establish the contract
- Read
AGENTS.mdand the design document that owns the affected behavior. - Inspect
git statusand preserve unrelated user changes. - Decide whether the request is an audit or an authorized implementation. Do not turn a cleanup into a product decision without making the behavior change explicit.
- Identify the relevant boundary before judging code:
globalThis.egois supplied by the closed-source app;docs/native-bindings-api.mddocuments that external contract.- The runtime has direct CLI and embedded SDK startup paths.
- Public agent APIs must stay aligned across implementation, tests,
help(), andskills/ego-browser/SKILL.md. - Browser state can outlive the short Node.js process.
Find strong candidates
Start with production areas carrying the most state, branching, or public surface. Look for:
- Exports, helpers, events, options, fallbacks, packages, or state fields with no production consumer.
- Tests or documentation that are the only consumers of behavior that is no longer required.
- Multiple representations of the same page, task-space, session, ref, lifecycle, or output state.
- Pass-through layers that add vocabulary but no policy, isolation, or test seam.
- Compatibility code that is unnecessary on an explicitly breaking branch.
- Generality with no current product use, such as unsupported concurrency modes or unused extension points.
- Special cases, rollback paths, or validation that exist only to protect a removable surface.
- Hand-written parsers, queues, retry logic, or utilities that a Node.js built-in or healthy dependency can replace with less total code.
Do not count moving logic into a wrapper as simplification. Estimate the net result: implementation, tests, docs, public names, state transitions, and special cases removed minus new glue and dependencies added.
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.
- today First seen · 74 lines · 68 tokens per session scan A 4ca1d897db80
ego-lite-simplify is a skill published in the GitHub repository citrolabs/ego-lite (15,632 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 959 once invoked, about $0.0003 per session on Opus 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 2026-09-10.
Other skills, from other repositories
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
issue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…
code-assessment
Detect, review, and fix code-quality and correctness issues in an AEM as a Cloud Service project — locally, with no external services or network calls. Use whenever a user wants to check, review, assess, audit, scan, modernize, upgrade, or fix AEM Java, Sling Models, OSGi, or Maven code — for example: "check my Sling…