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 instructions/nikolas-sapa/ns-ui/agents-mdgit clone --depth 1 https://github.com/nikolas-sapa/ns-uiWrote 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/instructions/nikolas-sapa/ns-ui/agents-md)<a href="https://agentmods.dev/instructions/nikolas-sapa/ns-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/nikolas-sapa/ns-ui/agents-md.svg" alt="Measured on agentmods" 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 | $0.06237 | $0.06237 |
| Opus 5 | $0.03119 | $0.03119 |
| Sonnet 5 | $0.01247 | $0.01247 |
| Haiku 4.5 | $0.00624 | $0.00624 |
Grade A, and why
ns-ui AGENTS.md 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 5d 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working inside this repo
Reference for an agent editing ns-ui itself. Two other documents may be the one you want:
- Consuming a component in some other project →
https://design.helpmarq.com/llms.txt, or the README. There's also an MCP server (mcp/) and a CLI (cli/) — both optional, neither required to install a component; seehttps://design.helpmarq.com/connectfor per-client config and current publish status. - Setup, the add-a-component walkthrough, the token rule, and how to open a PR →
CONTRIBUTING.md. That is the shared ground for humans and agents, and it is shorter.
What follows is the detail CONTRIBUTING.md deliberately leaves out: the autoplay, useWhen and
gate descriptor schemas, how prop signatures are extracted for llms.txt, and the constraints in
the preview driver that are easy to regress. Read the section you need, not the whole file.
Structure
Each component is a self-contained folder: registry/{core,loud}/<name>/ with:
component.tsx— the actual component."use client", zero or minimal deps, tokens not hex.demo.tsx— the preview render used by/components/<name>and the/preview/<name>screenshot-verifier fixture.meta.json— the single source of truth:name,title,description,collection,tags,instruction(a rich paragraph describing behavior — read byscripts/build-llms.ts),dependencies, the optional site-onlyautoplaydescriptor (see below) that makes the landing-page card demonstrate itself, and the optional site-onlyuseWhenoverride (see below) for llms.txt's "use when" line.screenshots/— generated bynpm run verify, not hand-authored.
core = Geist-dark restraint. loud = deliberately flashy showcase. Collection
is decided at creation time and drives folder placement, not a runtime flag.
Current counts drift by the day — read them from README.md (generated from
registry.json on every build) rather than trusting a number here.
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.
- 5d ago First seen · 353 lines · 6,237 tokens per session scan A eca34000e8a4
ns-ui AGENTS.md is an instructions file published in the GitHub repository nikolas-sapa/ns-ui (17 stars, last pushed yesterday), licensed MIT. It adds 6,237 tokens to every session, about $0.0312 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 instructions, from other repositories
animal-island-ui AGENTS.md
AGENTS.md instructions for guokaigdg/animal-island-ui, covering agents.md — working in this repository, read first, by task, verification, content that must be kept in sync and ground rules.
animal-island-ui CLAUDE.md
Claude Code instructions for guokaigdg/animal-island-ui, a project described as: Animal Crossing-style React UI component library, inspired by Nintendo's game visuals Vue version available. Animal 风格的 React 组件库 灵感来源于任天堂《集合啦！动物森友会》 Vue 版同步发布.
material-ui AGENTS.md
AGENTS.md instructions for mui/material-ui, covering agents.md, package manager, common commands, development and building.
material-ui CLAUDE.md
Claude Code instructions for mui/material-ui: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
ark CLAUDE.md
Claude Code instructions for chakra-ui/ark, covering ark ui - claude development guide, documentation structure, quick start, common commands and install dependencies.
ui-components AGENTS.md
AGENTS.md instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).