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/lets-mica/mica-admin/agents-mdgit clone --depth 1 https://github.com/lets-mica/mica-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/instructions/lets-mica/mica-admin/agents-md)<a href="https://agentmods.dev/instructions/lets-mica/mica-admin/agents-md"><img src="https://agentmods.dev/badge/instructions/lets-mica/mica-admin/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 | $0.03190 | $0.03190 |
| Opus 5 | $0.01595 | $0.01595 |
| Sonnet 5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
mica-admin 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mica-admin CLAUDE.md — 88% identical, 50 lines differ
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
项目概述
mica-admin 是基于 mica 工具集的低代码权限管理平台，使用 Maven、Spring Boot 4.1、Spring Security、MyBatis-Plus（后端）+ Vben Admin 5.x（前端）+ uniapp x（移动 App）。
仓库根目录结构（mono-repo，单 git 仓库）：
| 目录 | 说明 | 技术栈 |
|---|---|---|
mica-admin-server/ |
Spring Boot 后端（Java 17+） | Maven 模块 |
mica-admin-web/ |
Web 管理端（Vben Admin 5.x 本地化） | Vite + Vue 3 + Naive UI |
mica-admin-uniapp/ |
移动 App（uniapp x） | uniapp x + Vue 3 + TypeScript + Pinia |
docs/ |
设计文档 | - |
mica-admin-uniapp/不进 Maven：它是独立的 npm/pnpm 工程，与mica-admin-web/平级。 三者放在同一 git 仓库是为了 AI 编码时能"看见完整上下文",便于跨模块协作。
工作准则(必读)
- ❌ 禁止擅自
git commit/git push。所有变更默认保持M/A状态,等用户明确说"提交"、"commit"、"push" 时再执行。需要提交时,先把git status摘要给用户看一眼。 - ❌ 禁止擅自重命名既有字段。即使觉得"更合理"也不动,字段名/列名属于业务决策,改之前必须先和用户确认。
- ✅ 改动默认只改类型,不改命名(除非用户明确要求)。
- 命名 / 删文件 / 改 schema 之前,先用
AskUserQuestion确认,不要先斩后奏。
构建命令
后端 (mica-admin-server)
从仓库根目录执行：
# 默认 dev profile，跳过前端构建
mvn package
# 生产构建：触发 pnpm install + pnpm build:prod，把 dist 打入 META-INF/resources
mvn clean package -Pprod -U -Dmaven.test.skip=true
# 单测
mvn test -Dtest=ClassName#methodName -DfailIfNoTests=false
# 本地启动
mvn spring-boot:run -Dspring-boot.run.profiles=dev
Maven profile 行为：
dev（默认激活）：skipNpmBuild=true，不构建前端。prod：skipNpmBuild=false，通过exec-maven-plugin触发前端构建，并把mica-admin-web/dist复制到META-INF/resources，与后端 jar 合并。
前端 (mica-admin-web)
cd mica-admin-web
pnpm install
pnpm dev # Vite dev server，端口 5888，/api 代理到 http://localhost:8080
pnpm typecheck # vue-tsc --noEmit --skipLibCheck
pnpm lint # eslint --fix
pnpm build # 类型检查 + 生产构建
pnpm build:prod # 仅打包，跳过类型检查（Maven prod profile 调的就是这个）
pnpm build:analyze # 构建并分析包体积
后端架构 (mica-admin-server)
主包：net.dreamlu.mica.admin，源码 src/main/java/：
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.
- 4d ago First seen · 177 lines · 3,190 tokens per session scan A d78776380bf3
mica-admin AGENTS.md is an instructions file published in the GitHub repository lets-mica/mica-admin (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 3,190 tokens to every session, about $0.0159 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 2026-08-31.
Other instructions, from other repositories
YiSmart-Cloud CLAUDE.md
Instructions for Siborne/YiSmart-Cloud, covering claude.md, project overview, commands, backend (yismartcloud-background) and full build (skip tests).
atmosphere AGENTS.md
AGENTS.md instructions for Atmosphere/atmosphere, covering build system: maven, commands, module build, build only atmosphere-runtime (cpr) and build only spring-boot-starter.
tiny-vue AGENTS.md
AGENTS.md instructions for opentiny/tiny-vue, covering agents.md, 项目概述, 关键目录结构, 环境要求 and 核心命令.
matecloud AGENTS.md
Instructions for mateaix/matecloud, covering agents.md, project overview, development commands, backend (java / maven) and full build (42 modules).
sentry-java AGENTS.md
AGENTS.md instructions for getsentry/sentry-java, covering agents.md, domain-specific rules, project overview, build system and essential commands.
plugins CLAUDE.md
Claude Code instructions for ihub-pub/plugins, covering project knowledge base, project structure, plugin id 速查表, version compatibility and commands（build / lint / test）.