Moli is a Rust-based headless browser that gives AI agents a complete browser runtime for retrieving pages, extracting content, searching the web, and automating browser tasks. It is for agents and developers who need JavaScript, DOM, CSS, networking, storage, rendering, screenshots, or browser automation through CLI, CDP, or WebDriver protocols. The catalogue contains skills and instructions for using Moli.
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 lexmount/moli --skill moli-cdp-servergit clone --depth 1 https://github.com/lexmount/moliWrote 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/lexmount/moli/moli-cdp-server)<a href="https://agentmods.dev/skills/lexmount/moli/moli-cdp-server"><img src="https://agentmods.dev/badge/skills/lexmount/moli/moli-cdp-server/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/lexmount/moli/moli-cdp-server"><img src="https://agentmods.dev/badge/skills/lexmount/moli/moli-cdp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 20 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- low Supply Chain · line 19 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00074 | $0.00709 |
| Opus 5.5 | $0.00030 | $0.00284 |
| Sonnet 5.5 | $0.00015 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
moli-cdp-server 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 1mo 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.
curl --proto '=https' --tlsv1.2 -fsSL \ 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.
Run Moli's CDP Server
Run one Moli CDP server and connect the requested CDP client to its endpoint. Preserve the client's existing API where Moli supports it.
Workflow
-
Resolve
molifromPATH. If it is unavailable, install the latest prebuilt release for the current platform:Linux or macOS:
curl --proto '=https' --tlsv1.2 -fsSL \ https://github.com/lexmount/moli/releases/latest/download/moli-installer.sh | shOn Windows, use PowerShell:
powershell -ExecutionPolicy ByPass -c "irm https://github.com/lexmount/moli/releases/latest/download/moli-installer.ps1 | iex"Resolve the installed binary again and run
moli --version. The default location is~/.local/bin/molion Linux/macOS and%LOCALAPPDATA%\Moli\bin\moli.exeon Windows when it is not yet onPATH. -
Start
moli serveon the default loopback endpointhttp://127.0.0.1:9222. -
Add
--layoutwhen the workflow needs real element geometry, coordinate input, screenshots, PDFs, or screencasts. Add--resourceonly when all optional visual/media resources are required. -
Probe
/json/versionbefore connecting the client. -
Connect with the client's remote/attach API; do not launch a second bundled browser.
-
Close CDP clients cleanly, then stop the Moli server if this workflow owns it.
Playwright over CDP
import { chromium } from "playwright";
const browser = await chromium.connectOverCDP("http://127.0.0.1:9222");
const context = browser.contexts()[0];
const page = context.pages()[0] ?? await context.newPage();
await page.goto("https://example.com");
console.log(await page.locator("body").innerText());
await browser.close();
Integration rules
- Bind to
127.0.0.1by default. Expose another host only when the user explicitly needs remote access and has addressed network access controls. - Treat Moli as a remote endpoint. Avoid Chrome launch flags and assumptions that require a local Chromium executable.
- Expect selected CDP coverage, not complete Chrome protocol parity. Preserve explicit unsupported errors.
- Use a unique port for parallel isolated runs.
- Persist state intentionally with
--profile-dir; otherwise keep runs disposable. - Pass proxy, cookie, resource, user-agent, and private-network policy to the Moli server, not to a nonexistent child browser process.
What ships with it
2 files 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.
- 1mo ago First seen · 74 lines · 74 tokens per session scan A 062405167e89
moli-cdp-server is a skill published in the GitHub repository lexmount/moli (19,673 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 709 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
playwright-rs-usage
Procedural reference for using playwright-rs in Rust browser-automation code — object model (Browser/Context/Page/Locator), the locator!() macro, builder pattern for options, auto-wait semantics, adding the crate and installing its browsers, and how to capture / inspect traces for failure diagnosis. Use when writing…
rawtrace-debug-browser
Use RawTrace for continuous evidence capture when browser failures depend on transient DOM, network timing, WebSocket ordering, or authentication transitions. Requires an existing authorized Chromium CDP browser. Do not use for static edits, ordinary code reading, or simple web facts.
threads-composer-debug
Threads CDP Browser Hijacking — Playwright selector mode, no CDP flooding.
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
stagehand-facade
Browse, navigate, inspect, screenshot, and automate websites with the exact fx tools mcpstagehandrun, mcpstagehandsnapshot, and mcpstagehandscreenshot.