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/selekkt/skelet/agents-mdgit clone --depth 1 https://github.com/Selekkt/skeletWrote 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/selekkt/skelet/agents-md)<a href="https://agentmods.dev/instructions/selekkt/skelet/agents-md"><img src="https://agentmods.dev/badge/instructions/selekkt/skelet/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 | $0.00960 | $0.00960 |
| Opus 5 | $0.00480 | $0.00480 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
skelet 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Developing Skelet.css
This repository is the Skelet.css framework source. If you are working here, you are
developing the framework itself. Read this before changing any file in css/.
Building a site with Skelet, not editing the framework? You want the usage reference, not this file:
docs/using/skelet.md.
What Skelet is
A lightweight, classless-first CSS framework for modern browsers. Plain, untranspiled CSS —
no build step, no JavaScript runtime, no npm dependencies. It styles selected native
elements, adds a token-driven component layer, and provides attribute-based grid/flex
primitives (<x-grid>, <x-flex>) instead of a large utility-class API.
Source of truth
When docs, fixtures, and CSS disagree, trust in this order:
css/skelet.css— core framework behavior.css/skelet-overlay.css,css/skelet-tooltips.css— optional add-ons.- A current, focused fixture in
tests/. docs/,skelet.html,README.md— scaffolding that can lag the CSS.
The checked-in CSS is authoritative for framework behavior. npm and jsDelivr mechanically
use package.json#version, so never publish while that version disagrees with the CSS banner
or release tag (see releasing).
Repo map
css/
skelet.css Core framework
skelet-tooltips.css Optional add-on — CSS-only tooltips.
skelet-overlay.css Optional add-on — <dialog> / Popover visual treatment.
app.css Consumer override layer (loaded last). Shipped as a starter.
tests/ Manual browser fixtures — visual, not assertion-based.
docs/
using/skelet.md The "build a site WITH Skelet" API reference (for consumers).
developing/ You are here — how the framework is built and shipped:
architecture.md file map, section order, cascade strategy, distribution
releasing.md versioning, npm publish, CDN, downstream sync
skelet.html Accessible HTML starter (ships to consumers).
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 · 74 lines · 960 tokens per session scan A e51b0eee4a74
skelet AGENTS.md is an instructions file published in the GitHub repository Selekkt/skelet (141 stars, last pushed 6d ago), licensed MIT. It adds 960 tokens to every session, about $0.0048 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
electron CLAUDE.md
Instructions for electron/electron, covering electron development guide, running nodemodules binaries, project overview, directory structure and build tools setup.
electron copilot-instructions.md
Instructions for electron/electron, covering copilot instructions for electron, build system, linting, running a single test and example: npm run test -- -g "ipc".
Instatic CLAUDE.md
Claude Code instructions for CoreBunch/Instatic, covering instatic, local admin smoke tests, repository workflow and pr conventions, what this project is and stack at a glance.
html-video CLAUDE.md
Instructions for nexu-io/html-video, covering html-video 项目工作区, 角色与边界, 产品定位(决策时间线), 关键差异化 vs hyperframes and 目录结构.
textfox AGENTS.md
Instructions for adriankarlen/textfox, covering claude.md, what this is, commands, architecture and css layer.
shadow-plugin AGENTS.md
Instructions for flornkm/shadow-plugin, covering shadow agent instructions, dev environment tips, css (tailwind) class instructions and avoid double borders.