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/monkeyui-dev/vibe-to-ui/agents-mdgit clone --depth 1 https://github.com/MonkeyUI-dev/vibe-to-uiWhat 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 | $0.02738 | $0.02738 |
| Opus 5 | $0.01369 | $0.01369 |
| Sonnet 5 | $0.00548 | $0.00548 |
| Haiku 4.5 | $0.00274 | $0.00274 |
Grade C, and why
vibe-to-ui AGENTS.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$HOME" How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
This repository (vibe-to-ui) is primarily an Agent Skill package (Markdown
instructions + seed templates), plus a small Node.js zero-dependency CLI for
Design Context lifecycle (bin/vibe-to-ui.js, package.json bin). There is still
no application server, no build step, no automated test suite, and no linter.
Dependencies are not required to use the skill instructions; Node ≥18 is required
only when running the vibe-to-ui context CLI. The startup update script is
intentionally a no-op.
User Design Context vs skill package
Live Design Context profiles belong under the user home path
~/.vibe-to-ui/profiles/<profile>/, not in this
repository. The Inspiration Library belongs under
~/.vibe-to-ui/inspirations/<product>/pages/<page>/ (also user home — not the skill package).
Templates under assets/design-context/ are seeds only. Skill
install, update, or reinstall must never overwrite, delete, or reset
~/.vibe-to-ui/. There is no env override for the root path.
SKILL.md description (progressive disclosure — do not inflate)
name + description are the only fields loaded at agent startup for every
installed skill (Agent Skills progressive disclosure).
They must stay small, stable, and optimized for routing (when to activate),
not for teaching the full product.
Follow the Agent Skills spec and these repo rules when editing frontmatter:
| Rule | Requirement |
|---|---|
| Hard limit | description ≤ 1024 characters (spec max). Non-empty. |
| Soft target | Prefer ≈ 400–700 characters (~100–175 tokens). Do not drift toward the hard ceiling. |
| Job of the field | What the skill does + when to use it, with concrete trigger keywords |
| Not the job | Workflow steps, CLI flags, path layouts, open-ended target examples, intake playbooks, long capability catalogs |
| Activation | Include keywords agents match on user intent (e.g. design system, tokens, motion, mood board, spatial layout, visual assets, Design Context, ~/.vibe-to-ui, screenshot, URL, inspiration) |
| Stability | Do not casually rewrite or expand description while implementing features — put detail in the Markdown body or references/ |
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.
- 2d ago First seen · 206 lines · 2,738 tokens per session scan C 037c4230f3e7
vibe-to-ui AGENTS.md is an instructions file published in the GitHub repository MonkeyUI-dev/vibe-to-ui (27 stars, last pushed 3d ago), licensed MIT. It adds 2,738 tokens to every session, about $0.0137 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
melta-ui AGENTS.md
Instructions for tsubotax/melta-ui, covering melta ui — ai エージェント作業ガイド, アーキテクチャ概要, 最初に読むファイル, 読み込みモード and 作業ルール.
agent-toolkit AGENTS.md
Instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.
decantr CLAUDE.md
Instructions for decantr-ai/decantr, covering claude.md -- decantr, project, packages, apps and terminology.
bluetemberg CLAUDE.md
Instructions for prototypdigital/bluetemberg, a project described as: AI coding standards shipped like a dependency. Version-locked, integrity-verified, signed, and routed by role and stack version. Emits AGENTS.md, Cursor rules, and more.
ultra-max-token-burner AGENTS.md
Instructions for floytra-dev/ultra-max-token-burner: When the user asks to expand, operationalize, professionalize, govern, validate, or make a prompt more manager-visible, use the Ultra Max Token Burner workflow in SKILL.md.
ui-ux-design-pro-skill CLAUDE.md
Instructions for saifyxpro/ui-ux-design-pro-skill, covering project overview, cli commands, full design system generation (markdown output), search across all databases (sub-50ms) and audit ui code quality.