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.
git clone --depth 1 https://github.com/neoshopcn/neo-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/rules/neoshopcn/neo-admin/99-guard)<a href="https://agentmods.dev/rules/neoshopcn/neo-admin/99-guard"><img src="https://agentmods.dev/badge/rules/neoshopcn/neo-admin/99-guard/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/rules/neoshopcn/neo-admin/99-guard"><img src="https://agentmods.dev/badge/rules/neoshopcn/neo-admin/99-guard.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 | $0.00087 | $0.00087 |
| Opus 5.5 | $0.00035 | $0.00035 |
| Sonnet 5.5 | $0.00017 | $0.00017 |
| Haiku 4.5 | $0.00009 | $0.00009 |
Grade A, and why
99-guard 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 1mo 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
🔒 Protected Directories（禁止修改）
- vendor/**
- bootstrap/cache/**
⚠️ Conditional（仅在明确要求时允许）
- tests/**
🚫 Dangerous Operations（禁止主动执行）
- 删除目录
- 批量重构项目结构
- 修改第三方库源码
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.
- 1mo ago First seen · 25 lines · 87 tokens per session scan A fc0f3051d85a
99-guard is a cursor rule published in the GitHub repository neoshopcn/neo-admin (13 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session, about $0.0003 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.
Other cursor rules, from other repositories
owl-admin
A set of project rules for Owl Admin, a Laravel-based framework for building web administration panels. It guides how the project should use its page renderer, controllers, services, menus, permissions, APIs, and code generator.
vue
A set of coding rules for Vue, a JavaScript framework for building web interfaces. It covers component structure, naming, TypeScript usage, reactive data, properties, and routes.
project
A set of project-wide rules for a Vue or TypeScript-style web application, including imports, coding practices, dependency use, linting, and local tool versions. It specifies conventions such as path aliases and supported Node.js and pnpm versions.
ts
A set of TypeScript coding rules covering types, naming, file organization, error handling, and strict type checking. TypeScript is JavaScript with checks that help catch many mistakes before the program runs.
index
A set of Chinese-language rules for frontend development, especially Vue 3, Vue Router, Pinia, TypeScript, JavaScript, and Git. It also points to separate project, Vue, TypeScript, and commit-guideline files.
git
Git rules for writing commit messages and working with branches. A commit is a saved group of code changes, and a branch is a separate line of development.