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 agentmods add skills/live-codes/livecodes/self-hostingnpx skills add live-codes/livecodes --skill self-hostinggit clone --depth 1 https://github.com/live-codes/livecodesWhat 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 | $0.00054 | $0.01283 |
| Opus 5 | $0.00027 | $0.00642 |
| Sonnet 5 | $0.00011 | $0.00257 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
livecodes/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 2d 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 — 231 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.
- 2d ago First seen · 231 lines · 54 tokens per session scan A 0d801970ed76
livecodes/self-hosting is a skill published in the GitHub repository live-codes/livecodes (1,490 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 1,283 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 2026-08-30.
Other skills, from other repositories
lizard
Entry point for deploying and managing apps on Lizard via the lizard CLI (npm @lizard-build/cli). This is a thin bootstrap: it loads the full, version-matched usage guide from the CLI itself, installing the CLI only when needed. Covers the whole app lifecycle (login, init, link, add, up, redeploy, logs, status, scale…
prettier-docs
Prettier 3.9.5 — opinionated code formatter. CLI, API, config, plugins, editor integration, CI.
flockion_cloud_patterns
Picks the smallest cloud design pattern that solves a named problem, and refuses to add one without a named constraint. Covers the full Azure Well-Architected catalog (43 patterns: Circuit Breaker, Retry, Bulkhead, CQRS, Event Sourcing, Saga, Sidecar, Ambassador, Gateway Routing/Aggregation/ Offloading, Quarantine…
flockion_engineering_infra
Forces the simplest, shortest, safest infrastructure that actually works. Lazy senior-DevOps pragmatism for IaC, CI/CD, containers, and cloud automation: Bicep, Terraform, GitHub Actions, Docker, Kubernetes, shell. Use managed platform features before custom infra, official actions before bespoke pipelines, least…
scripting-reference
Python for Rhino and Grasshopper (RhinoCommon, rhinoscriptsyntax, ghpythonlib), C# for Grasshopper components, Python for Revit (pyRevit, RevitPythonShell), JavaScript for web 3D (Three.js), and code patterns for AEC computational design.
code-runner
安全代码执行（Python/JavaScript/Bash脚本运行、超时控制、输出捕获）.