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 unco999/neon3-ai-authoring-mcp --skill skillgit clone --depth 1 https://github.com/unco999/neon3-ai-authoring-mcpWrote 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/unco999/neon3-ai-authoring-mcp/skill)<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.
<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>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 | $0.00029 | $0.01612 |
| Opus 5 | $0.00015 | $0.00806 |
| Sonnet 5 | $0.00006 | $0.00322 |
| Haiku 4.5 | $0.00003 | $0.00161 |
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.
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-runtimeparses and compiles UI declarations.neon-wgpu-runtimeowns the window, GPU, final layout, hit testing, and pixels.neon-projectdis the only project/asset writer and returns stableAssetRefvalues.- 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
- Read
neon3_nui_referencefor the needed topic. - Query
neon3_capabilitiesand current UI/project snapshots when connected to a live runtime. - Generate a complete NUI Flow source with stable semantic keys.
- Call
neon3_nui_validate. - Review the returned input schema, node outline, budget, bindings, and events.
- Use a revisioned patch for a small edit; regenerate the full source for a structural change.
- Call
neon3_nui_submitonly after validation passes. - Call
neon3_diagnoseand 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
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.
- 11d ago First seen · 201 lines · 29 tokens per session scan A 2d3e38377e02
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.
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.
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.
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.
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…
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".
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.