Borrowing it
Nothing to install: this file belongs to Kevin-Liu-01/Sigil-UI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kevin-Liu-01/Sigil-UI/main/AGENTS.mdgit clone --depth 1 https://github.com/Kevin-Liu-01/Sigil-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/kevin-liu-01/sigil-ui/agents-md)<a href="https://agentmods.dev/instructions/kevin-liu-01/sigil-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/kevin-liu-01/sigil-ui/agents-md/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/instructions/kevin-liu-01/sigil-ui/agents-md"><img src="https://agentmods.dev/badge/instructions/kevin-liu-01/sigil-ui/agents-md.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 | $0.05549 | $0.05549 |
| Opus 5 | $0.02774 | $0.02774 |
| Sonnet 5 | $0.01110 | $0.01110 |
| Haiku 4.5 | $0.00555 | $0.00555 |
Grade A, and why
Sigil-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 9d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sigil UI — Agent Instructions
Read this before writing any code in a Sigil project.
The #1 Rule
Edit the token spec. Not the components.
Sigil is a token-driven design system. Every visual property — colors, fonts, spacing, radius, shadows, motion, borders — flows from a central token spec through CSS custom properties into components. When you need to change how something looks, you change the tokens. The components update automatically.
WRONG — manually editing component styling:
open Button.tsx → find bg-indigo-600 → change to bg-emerald-600
open Card.tsx → find rounded-lg → change to rounded-none
open Input.tsx → find border-gray-300 → change to border-gray-500
(repeat for every component, miss some, drift, inconsistency)
RIGHT — editing the central token spec:
change --s-primary → every primary-colored element updates (buttons, links, focus rings, badges, gradients)
change --s-radius-md → every medium-radius element updates (cards, inputs, dropdowns, tooltips)
run "sigil preset anvil" → the ENTIRE visual identity changes in one command
This is the fundamental insight. Agents that understand this build 10x faster because one token edit replaces dozens of component edits.
How It Works
DESIGN.md (human/agent-editable markdown — all 33 categories, 519 tokens)
↓ parseDesignMarkdown() / sigil design compile
SigilTokens (TypeScript object, 519 configurable fields)
↓ compileToCss() / compileToTailwind() / compileToW3CJson()
CSS custom properties (--s-primary, --s-radius-md, --s-duration-fast, ...)
Tailwind v4 @theme block
W3C Design Tokens JSON
↓ consumed by
350+ Components (read var(--s-*), never hardcode values)
Legacy path (still supported): sigil.tokens.md → parseMarkdownTokens() → 8 core groups.
To change the visual output, edit the top of this chain — not the bottom.
Quick Reference: What to Edit for Common Tasks
| Task | What to edit | Do NOT edit |
|---|---|---|
| Change primary color | Token CSS: --s-primary: oklch(...) |
Component files |
| Change fonts | Token CSS: --s-font-display: "NewFont", ... |
Component files |
| Change all border radius | Token CSS: --s-radius-md: 12px |
Component files |
| Change animation speed | Token CSS: --s-duration-fast: 200ms |
Component files |
| Change card hover effect | Preset: cards.hover-effect: "glow" |
Card component file |
| Change button press scale | Preset: buttons.active-scale: "0.95" |
Button component file |
| Change background pattern | Preset: backgrounds.pattern: "dots" |
Layout files |
| Change hero padding/layout | Token CSS: --s-hero-padding-y: 120px |
Hero component files |
| Change CTA layout | Token CSS: --s-cta-layout: "split" |
CTA component files |
| Change footer structure | Token CSS: --s-footer-columns: 3 |
Footer component files |
| Change page density | Preset: pageRhythm.density: "editorial" |
Section/layout files |
| Complete visual overhaul | npx @sigil-ui/cli preset <name> |
Any component files |
| Targeted brand update | Edit sigil.tokens.md or token CSS |
Scattered Tailwind classes |
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.
- 9d ago First seen · 385 lines · 5,549 tokens per session scan A 651a5805a332
Sigil-UI AGENTS.md is an instructions file published in the GitHub repository Kevin-Liu-01/Sigil-UI (9 stars, last pushed 1mo ago), licensed MIT. It adds 5,549 tokens to every session, about $0.0277 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.