Borrowing it
Nothing to install: this file belongs to underfitting-lu/open-ui-scout. 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/underfitting-lu/open-ui-scout/master/AGENTS.mdgit clone --depth 1 https://github.com/underfitting-lu/open-ui-scoutWrote 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/underfitting-lu/open-ui-scout/agents-md)<a href="https://agentmods.dev/instructions/underfitting-lu/open-ui-scout/agents-md"><img src="https://agentmods.dev/badge/instructions/underfitting-lu/open-ui-scout/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/underfitting-lu/open-ui-scout/agents-md"><img src="https://agentmods.dev/badge/instructions/underfitting-lu/open-ui-scout/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 | $0.00281 | $0.00281 |
| Opus 5.5 | $0.00112 | $0.00112 |
| Sonnet 5.5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
open-ui-scout 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 2mo 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.
What it actually says
Open UI Scout Agent Guide
This repository contains Open UI Scout, a frontend UI resource selection skill for coding agents.
The primary skill file is:
.claude/skills/open-ui-scout/SKILL.md
Before frontend UI, page design, component library selection, vibe coding, dashboard, landing page, AI chat, editor workspace, canvas, mobile UI, icon, token, or visual mood work, read the skill first.
When executing the skill:
- Understand the page type, product context, visual mood, technical stack, and production constraints before selecting resources.
- If the user names a style, follow it. If style is implied by context, state the assumption. If several styles are plausible, ask first or offer 2-3 directions.
- Inspect the existing project UI stack before introducing new libraries.
- Select from GitHub open-source UI resources only after scoring fit for stack, page type, mood, dependency cost, license clarity, and maintenance.
- Do not default to black-purple AI tech aesthetics.
- Do not mix too many UI libraries or visual systems.
- Use at most 3 primary UI sources per task.
- Do not introduce a large UI library for one isolated component.
- Output a short selection summary before generating UI unless the user explicitly asks for code only.
- Keep this skill general, public, and reusable when editing it.
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.
- 2mo ago First seen · 25 lines · 281 tokens per session scan A 86b82a617390
open-ui-scout AGENTS.md is an instructions file published in the GitHub repository underfitting-lu/open-ui-scout (11 stars, last pushed 6mo ago), licensed MIT. It adds 281 tokens to every session, about $0.0011 per session on Opus 5.5. 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.
open-ui-scout AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| open-ui-scout AGENTS.mdunderfitting-lu/open-ui-scout | Instructions file | 11 | 6mo ago | MIT | A | 281 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |