live-codes/livecodes is a browser-based code playground for writing and running code in more than 90 languages, frameworks, and processors. It is used to experiment with code, import modules, embed interactive editors in websites, and host playgrounds on a static file server without a backend. The catalogue add-ons support working with LiveCodes.
Borrowing it
Nothing to install: this file belongs to live-codes/livecodes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/live-codes/livecodes/develop/.agents/skills/livecodes/self-hosting/SKILL.mdgit clone --depth 1 https://github.com/live-codes/livecodesWrote 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/live-codes/livecodes/self-hosting)<a href="https://agentmods.dev/skills/live-codes/livecodes/self-hosting"><img src="https://agentmods.dev/badge/skills/live-codes/livecodes/self-hosting/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/live-codes/livecodes/self-hosting"><img src="https://agentmods.dev/badge/skills/live-codes/livecodes/self-hosting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium MCP Rug Pull · line 107 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 117 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 178 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00052 | $0.01286 |
| Opus 5.5 | $0.00021 | $0.00514 |
| Sonnet 5.5 | $0.00010 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
self-hosting 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 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.
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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill requires sdk-embedding. Read it first for foundational concepts.
LiveCodes — Self-Host LiveCodes
LiveCodes runs entirely client-side. Host it on any static file server or CDN.
Deployment Options
Download Release
- Download from GitHub releases
- Extract the
buildfolder - Serve from any static host
# Files to serve
build/
├── index.html
├── livecodes/
│ ├── assets/
│ └── ...
└── docs/ (optional)
Build from Source
git clone https://github.com/live-codes/livecodes.git
cd livecodes
npm install
npm run build # Build to build/ directory
npm run serve # Local preview at http://localhost:8080
npm run deploy # Build + deploy to GitHub Pages
GitHub Pages (Built-in)
# Setup
npm install
npm run deploy # Deploys to gh-pages branch
Configure CNAME file for custom domain if needed.
Docker
docker-compose up -d
Docker setup includes:
- HTTPS with auto-certificates
- Share service (short URLs)
- Broadcast server
- Open Graph meta tags
- Custom 404 page
# docker-compose.yml
# See: docs/docs/advanced/docker.mdx for customization
Other Static Hosts
- Cloudflare Pages: Connect repo,
npm run build, servebuild/ - Netlify: Connect repo,
npm run build, servebuild/ - Firebase Hosting:
firebase init hosting, deploybuild/
Configure SDK for Self-Hosted App
import { createPlayground } from 'livecodes';
createPlayground('#container', {
appUrl: 'https://playground.example.com',
template: 'react',
});
The appUrl tells the SDK where to load the playground iframe from.
Custom Build
Subdirectory Hosting
By default, LiveCodes expects to be at the root of a domain. For subdirectories:
# Host at https://example.com/playground/
npx cross-env BASE_URL="/playground/" npm run build
This sets <base href="/playground/"> and adjusts all asset paths.
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 Changed · +1 lines · -2 tokens per session b0cd893922f6
- 2mo ago First seen · 231 lines · 54 tokens per session scan A 0d801970ed76
self-hosting is a skill published in the GitHub repository live-codes/livecodes (1,525 stars, last pushed 13d ago), licensed MIT. It adds 52 tokens to every session and 1,286 once invoked, about $0.0002 per session on Opus 5.5. 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.
self-hosting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| self-hostinglive-codes/livecodes | Skill | 1.5k | 13d ago | MIT | A | 52 | Claude Code, Codex |
| incident-response-skillagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 24 | Claude Code, Codex |
| contrib-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 65 | Claude Code, Codex |
| github-review-iterationprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 60 | Claude Code |
| review-implement-phaseprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 38 | Claude Code |
| angular-developerangular/angular | Skill | 101k | yesterday | MIT | A | 93 | Claude Code, Codex |
| no-bare-castsprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |