livecodes/headless-mode

A guide for using LiveCodes, an in-browser coding playground, without displaying its user interface. It shows how to load code, compile it, read the result, and respond to changes through its software interface.

In plain words
What is it for?
Use it to build Markdown compilers, code formatters, or other tools that need compiled output from LiveCodes without a visible playground.
Why use it?
It lets tools compile and process code in the background when showing an interactive editor is unnecessary.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/live-codes/livecodes/headless-mode
Any agent
npx skills add live-codes/livecodes --skill headless-mode
Clone the repo
git clone --depth 1 https://github.com/live-codes/livecodes

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.01041
Opus 5 $0.00019 $0.00521
Sonnet 5 $0.00008 $0.00208
Haiku 4.5 $0.00004 $0.00104

Measured yesterday against content hash 86028db7f1c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

livecodes/headless-mode 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 yesterday.

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.

.agents/skills/livecodes/headless-mode/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill builds on sdk-embedding and sdk-methods. Read them first for foundational concepts.

LiveCodes — Headless Mode

Headless mode runs LiveCodes without any visible UI. Use SDK methods to compile code, get output, and react to events.

Setup

import { createPlayground } from 'livecodes';

// Create headless playground - container is optional
const playground = await createPlayground({
  headless: true,
  config: {
    markup: { language: 'markdown', content: '# Hello World' },
  },
});

// Use SDK methods
const code = await playground.getCode();
console.log(code.markup.compiled); // "<h1>Hello World</h1>"
console.log(code.result); // Result page HTML

Core Patterns

Markdown compiler

import { createPlayground } from 'livecodes';

let playground;

async function compileMarkdown(markdown) {
  if (!playground) {
    playground = await createPlayground({
      headless: true,
      config: { autoupdate: false },
    });
  }

  await playground.setConfig({
    markup: { language: 'markdown', content: markdown },
  });

  const code = await playground.getCode();
  return code.markup.compiled;
}

// Usage
const html = await compileMarkdown('# Hello\n\nWorld');
console.log(html); // "<h1>Hello</h1>\n<p>World</p>"

React/JSX compiler

import { createPlayground } from 'livecodes';

let playground;

async function compileJSX(jsxCode) {
  if (!playground) {
    playground = await createPlayground({
      headless: true,
      config: { autoupdate: false },
    });
  }

  await playground.setConfig({
    script: { language: 'react', content: jsxCode },
  });

  const code = await playground.getCode();
  return code.script.compiled;
}

const compiled = await compileJSX(`
  function App() {
    return <h1>Hello</h1>;
  }
`);

Python interpreter

import { createPlayground } from 'livecodes';

let playground;

async function runPython(code) {
  if (!playground) {
    playground = await createPlayground({
      headless: true,
      config: { autoupdate: true },
    });
  }

  // Set up console listener before running
  const outputs = [];
  playground.watch('console', ({ method, args }) => {
    outputs.push({ method, args });
  });

  await playground.setConfig({
    script: { language: 'python', content: code },
  });

  // Python runs automatically with autoupdate: true
  // Or: await playground.run();

  return outputs;
}

// Usage
const outputs = await runPython('print("Hello from Python!")');
// [{ method: 'log', args: ['Hello from Python!'] }]

Read the full file on GitHub · 190 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. yesterday First seen · 190 lines · 38 tokens per session scan A 86028db7f1c2

Subscribe to this mod's changes

livecodes/headless-mode is a skill published in the GitHub repository live-codes/livecodes (1,488 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 1,041 once invoked, about $0.0002 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 2026-08-30.