neon3-ai-authoring

neon3-ai-authoring is a skill for Claude Code, Codex from unco999/neon3-ai-authoring-mcp. It costs 29 tokens per session (1,612 once invoked), scanned A, original, MIT.

An authoring guide for building Neon3 user interfaces and Python or Node applications through Neon3's public communication protocol. It explains the boundaries between UI declarations, the runtime, project files, and domain data.

In plain words
What is it for?
Creating or changing Neon3 interfaces, checking available runtime capabilities, validating submitted data, handling diagnostics, and connecting UI actions to project or domain services.
Why use it?
It prevents code from relying on capabilities that the UI language does not have, such as reading files, using the network, or running application logic inside the interface.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Creating or changing Neon3 interfaces, checking available runtime capabilities, validating submitted data, handling diagnostics, and connecting UI actions to project or domain services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unco999/neon3-ai-authoring-mcp/skill
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.

Any agent
npx skills add unco999/neon3-ai-authoring-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/unco999/neon3-ai-authoring-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for neon3-ai-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/unco999/neon3-ai-authoring-mcp/skill/github.svg)](https://agentmods.dev/skills/unco999/neon3-ai-authoring-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/unco999/neon3-ai-authoring-mcp/skill"><img src="https://agentmods.dev/badge/skills/unco999/neon3-ai-authoring-mcp/skill/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.

agentmods 80×15 button for neon3-ai-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/unco999/neon3-ai-authoring-mcp/skill"><img src="https://agentmods.dev/badge/skills/unco999/neon3-ai-authoring-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00029 $0.01612
Opus 5 $0.00015 $0.00806
Sonnet 5 $0.00006 $0.00322
Haiku 4.5 $0.00003 $0.00161

Measured 11d ago against content hash 2d3e38377e02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

neon3-ai-authoring 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 11d 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.

skill/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neon3 AI Authoring Skill

You are an authoring client for Neon3. Treat the runtime and domain services as the source of truth. Before creating or changing UI, read the relevant neon3_nui_reference topic and query neon3_capabilities when a live session exists.

Non-negotiable boundaries

  • NUI Flow is declarative data, not JavaScript, Rust, Python, Lua, or a callback language.
  • NUI Flow cannot read files, access the network, execute code, calculate domain rules, create GPU resources, or write projects.
  • neon-ui-runtime parses and compiles UI declarations.
  • neon-wgpu-runtime owns the window, GPU, final layout, hit testing, and pixels.
  • neon-projectd is the only project/asset writer and returns stable AssetRef values.
  • Domain facts arrive through typed input frames. Do not infer them from local UI state.
  • Interaction crosses the boundary as a declared semantic intent, never as coordinates, renderer hit IDs, or GPU handles.
  • Always validate before submit. On rejection, fix the source using the returned diagnostic code and source span.

Required workflow

  1. Read neon3_nui_reference for the needed topic.
  2. Query neon3_capabilities and current UI/project snapshots when connected to a live runtime.
  3. Generate a complete NUI Flow source with stable semantic keys.
  4. Call neon3_nui_validate.
  5. Review the returned input schema, node outline, budget, bindings, and events.
  6. Use a revisioned patch for a small edit; regenerate the full source for a structural change.
  7. Call neon3_nui_submit only after validation passes.
  8. Call neon3_diagnose and compare program, input, fragment, and composition revisions.

NUI Flow V1 mental model

An NUI document has one root declaration plus top-level declarations:

version 1
surface surface.example revision 1
budget nodes=128 bindings=64 instances=64 text=64 glyphs=4096 events=32 clips=24
input title text default text:empty
input enabled bool default true
surface root column w 800 h 500 gap 8 pad 12
  text heading value $title
  button save value "Save" enabled $enabled event document.save

Read the full file on GitHub · 201 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. 11d ago First seen · 201 lines · 29 tokens per session scan A 2d3e38377e02

Subscribe to this mod's changes

neon3-ai-authoring is a skill published in the GitHub repository unco999/neon3-ai-authoring-mcp (1 stars, last pushed 17d ago), licensed MIT. It adds 29 tokens to every session and 1,612 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

nextjs-pages-router

Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.

trpc/trpc · 67 tokens

with-tanstack-query

Compose Angular Query with signal-owned Table filtering, sorting, and pagination state using reactive query options, manual row-model boundaries, direct query data, server counts, and valid injection context.

TanStack/table · 42 tokens

auth-web-cloudbase

CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.

TencentCloudBase/CloudBase-AI-Toolkit · 38 tokens

service-digital-engagement-channel-configure

Configures and deploys enhanced chat Messaging Channels for Messaging for In-App and Web (MIAW). Use when the user needs to create, deploy, and activate a messaging channel configured with Omni-Channel Flow, Omni-Channel Queue, User, or Agentforce Service Agent routing. Generates MessagingChannel metadata, deploys it…

forcedotcom/sf-skills · 173 tokens

om-system-extension

Extend installed Open Mercato modules through UMES enrichers, interceptors, mutation guards, widgets, menus, entity extensions, events, component/page replacements, and overrides. Use for "extend core", "add field/column/action", "hide page", "intercept API", "UMES", or "rozszerz moduł".

open-mercato/open-mercato · 73 tokens

cloudbase-sites

Use when the user wants to vibe-code a full-stack web app inside DeepSeek Harness — scaffold from CloudBase templates, local Vite preview, PostgreSQL tables, and one-click static hosting deploy with a real domain.

TencentCloudBase/CloudBase-AI-Toolkit · 48 tokens