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 skills add slowlyo/owl-admin --skill owl-admin-frontend-assetsgit clone --depth 1 https://github.com/slowlyo/owl-adminWrote 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/skills/slowlyo/owl-admin/owl-admin-frontend-assets)<a href="https://agentmods.dev/skills/slowlyo/owl-admin/owl-admin-frontend-assets"><img src="https://agentmods.dev/badge/skills/slowlyo/owl-admin/owl-admin-frontend-assets/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/skills/slowlyo/owl-admin/owl-admin-frontend-assets"><img src="https://agentmods.dev/badge/skills/slowlyo/owl-admin/owl-admin-frontend-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.00548 |
| Opus 5 | $0.00040 | $0.00274 |
| Sonnet 5 | $0.00016 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
owl-admin-frontend-assets 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.
What it actually says
Owl Admin Frontend Assets
用于 Owl Admin 前端资源、admin-views、发布后的前端源码和自定义前端开发。
参考索引
需要完整路径和命令时，读取 ../_references/owl-admin-dev-index.md。
需要按开发文档主题选择 skill 时，读取 ../_references/owl-admin-docs-map.md。
路径判断
- 安装后的静态资源：
public/admin-assets - 安装后可发布的前端源码：
resources/admin-views - Composer 包内前端源码：
vendor/slowlyo/owl-admin/admin-views - 框架源码仓库前端源码：
admin-views
开发原则
- 普通后台页面优先用后端 amis schema，不要为了页面需求直接改前端。
- 动态加载资源优先使用框架提供的
js()、css()、styles()、script()能力。 - 前端全局函数相关需求先查退出登录、登录回调、刷新 amis 页面、刷新前端路由和关闭 tab。
- 不要编译
vendor/slowlyo/owl-admin/admin-views。 - 只有用户明确要自定义框架前端时，才进入
resources/admin-views或框架源码admin-views。 - 执行前端命令前先确认当前目录和包管理器；该项目使用
pnpm-lock.yaml。 - 修改前端源码后，提示用户需要重新发布或同步前端资源。
常用命令
php artisan admin:publish --assets
php artisan admin:publish --views
在确认需要构建且用户允许后，才在正确前端目录执行：
pnpm install
pnpm run dev
pnpm run build
验证
- 资源缺失先执行
php artisan admin:doctor。 - 前端源码变更先检查
package.json和pnpm-lock.yaml。 - 构建产物需要发布到
public/admin-assets后才会影响运行中的后台。
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 · 53 lines · 80 tokens per session scan A fc1c3315f902
owl-admin-frontend-assets is a skill published in the GitHub repository slowlyo/owl-admin (617 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 548 once invoked, about $0.0004 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 skills, from other repositories
antd
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.
tanstack-form
Headless, performant, and type-safe form state management for TS/JS, React, Vue, Angular, Solid, Lit, and Svelte.
tanstack-query
TanStack Query v5 data fetching patterns including useSuspenseQuery, useQuery, mutations, cache management, and API service integration. Use when fetching data, managing server state, or working with TanStack Query hooks.
pro-upgrade
An upgrade guide for projects built with Ant Design Pro, a React-based application template for business software. It compares the project with the latest official template and merges framework updates while preserving application code.
creative-tim-ui
Creative Tim UI block library assistant. Use when adding, generating, or modifying UI blocks/components/pages from creative-tim.com/ui. Covers design philosophy (minimalism, the 95% rule, research-first), block discovery, both CLI install methods, PRO API key setup, and Creative Tim design rules (orange brand…
electrik-slate
Build Laravel Blade UI with Electrik Slate 3.x and optional slate-blocks. Use when writing x-slate or x-slate-block components, Livewire forms, tokens, toasts, blocks, or when the user mentions Slate, electrik/slate, electrik/slate-blocks, or slate.electrik.dev.