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/vaneenige/monochrome-ui/agents-mdgit clone --depth 1 https://github.com/vaneenige/monochrome-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/vaneenige/monochrome-ui/agents-md)<a href="https://agentmods.dev/instructions/vaneenige/monochrome-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/vaneenige/monochrome-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 5.1 | $0.07729 | $0.07729 |
| Opus 5 | $0.03864 | $0.03864 |
| Sonnet 5 | $0.01546 | $0.01546 |
| Haiku 4.5 | $0.00773 | $0.00773 |
Grade A, and why
monochrome-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 today.
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 — 636 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for working on monochrome: an accessible, headless UI component library with no runtime dependencies. Eight components (Accordion, Collapsible, Dialog, Menu, Menubar, Popover, Tabs, Tooltip), plus an optional router and thin React and Vue wrappers. The core is framework-agnostic and works on plain HTML; import it once and every correctly- structured component on the page becomes interactive.
North stars (non-negotiables)
These aren't preferences. Break any of them and it isn't monochrome any more:
- DOM is the source of truth. Every decision reads
aria-expanded,aria-selected,aria-checked,aria-hidden,aria-disabled. There is no internal state object mirroring the DOM anywhere in the library. - Event delegation only. Listeners go on
window. Zero per-element listeners. Each component registers only the events it handles. Combined, the set is still the nine:pointerdown,pointerup,click,pointermove,keydown,scroll,resize,focusin,focusout. - Zero timers. No
setTimeout,requestAnimationFrame,queueMicrotask, debounce, or throttle. Every action is synchronous within its event. - Zero runtime dependencies. Shared helpers (
src/dom.ts) import nothing. Components import only those helpers. The wrappers import only their framework (as peer deps) plus one side-effect import of their own core file, so a single wrapper import ships both markup and behavior. - Baseline 2024 browsers. We rely on the Popover API. No polyfills shipped.
- One file per component. Shared helpers live in
src/dom.ts. Each component issrc/{name}.tsand registers its own window listeners.src/index.tsonly imports every component soimport "monochrome"still lights up the page. Components do not import each other.
Why the core looks weird (and should stay weird)
Six architectural choices that explain the shape of the library. Each looks odd at a glance and each has a specific reason. Don't "fix" them.
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.
- today Changed · +48 lines · +644 tokens per session ce2e146e4f2b
- 2d ago Changed · -6 lines · -126 tokens per session a3bc0e035e7c
- 6d ago First seen · 594 lines · 7,211 tokens per session scan A d47011dae8cf
monochrome-ui AGENTS.md is an instructions file published in the GitHub repository vaneenige/monochrome-ui (132 stars, last pushed yesterday), licensed MIT. It adds 7,729 tokens to every session, about $0.0386 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
motion-lexicon AGENTS.md
AGENTS.md instructions for Ryan-yang125/motion-lexicon, covering agent instructions, operating context, communication, product boundary and technical stack.
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: Kawaii React UI component library 可爱风格 React 组件库.
kernel-ui AGENTS.md
AGENTS.md instructions for kemiljk/kernel-ui, covering working in this repo, release checklist for pull requests, the one rule that matters most: build every component twice, repo layout and conventions to match, not reinvent.
kolibri copilot-instructions.md
Copilot instructions for public-ui/kolibri, covering github copilot instructions for kolibri repository, kolibri overview, essential setup commands, 1. install node.js 22 and 2. enable pnpm.
kolibri AGENTS.md
AGENTS.md instructions for public-ui/kolibri, covering agent instructions, handling hints, 🚨 format-first rule, semantic versioning and project structure.