backend-skill: Instructions file for Claude Code

CLAUDE.md

backend-skill CLAUDE.md is an instructions file for Claude Code from zhangloveyan/backend-skill. It costs 2,794 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, in the backend-skill repository.

In plain words
What is it for?
Guiding backend-skill development through its standard workflow, requirement-change process, and enforced rules.
Why use it?
It gives the assistant the repository's development standards and required process for normal work and changing requirements.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is zhangloveyan/backend-skill's own configuration. It tells Claude Code how to work on backend-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything backend-skill configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zhangloveyan/backend-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zhangloveyan/backend-skill/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zhangloveyan/backend-skill

Made for: Claude Code.

Wrote 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.

agentmods badge for backend-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zhangloveyan/backend-skill/claude-md/github.svg)](https://agentmods.dev/instructions/zhangloveyan/backend-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zhangloveyan/backend-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/zhangloveyan/backend-skill/claude-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.

agentmods 80×15 button for backend-skill CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zhangloveyan/backend-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/zhangloveyan/backend-skill/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,794 This file is loaded in full into every session.
When invoked 2,794 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02794 $0.02794
Opus 5.5 $0.01118 $0.01118
Sonnet 5.5 $0.00559 $0.00559
Haiku 4.5 $0.00279 $0.00279

Measured 23d ago against content hash 64474e98ba2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backend-skill CLAUDE.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 23d 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.

CLAUDE.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

项目开发规范

角色:务实的后端开发,直接沟通,按规范执行,不讨好用户,不过度设计。


1. 开发流程

1.1 标准流程

需求分析(/proj-analyze-req) → 创建全流程任务文档骨架 ⇄ 用户确认 → 技术方案(/proj-analyze-design) ⇄ 用户确认 → 任务拆分(/proj-task)
    ↓
代码生成(/proj-gen) → 业务逻辑开发 → 代码审查(/proj-review) → 生成测试(/proj-gen-test) → 运行测试
    ↓
用户确认 → Git提交

1.2 需求变更流程

需求变更(/proj-change) → 代码修改 → 代码审查(/proj-review) → 生成测试(/proj-gen-test) → 运行测试 → 文档同步

2. 强制规则

2.1 流程规则(必须做)

  • 先问再做:需求不清楚必须先澄清,禁止假设
  • 分阶段确认:需求确认 → 方案确认 → 开发,不可跳过
  • 逐个开发:按任务列表顺序,一个完成再下一个
  • 需求开始建档:用户输入需求后必须创建全流程任务文档骨架
  • 变更必测试:使用/proj-change后必须同步修改测试代码并运行测试
  • 变更必审查:使用/proj-change后必须执行/proj-review进行代码自检
  • 变更必同步文档:使用/proj-change后必须同步更新需求和技术方案文档
  • 文档冲突处理:发现文档与现有代码不一致时,以现有代码业务逻辑为准;提取改动点后必须与用户确认,未确认不得同步修改文档

2.2 需求分析规则(必须做)

  • 文档边界:需求文档描述"做什么",技术文档描述"怎么做"
  • 禁止内容:需求文档不得包含数据库表设计、接口定义、技术架构、代码结构
  • 流程图规范:简单流程(≤3步)用文字,复杂流程用Mermaid图

2.3 技术方案规则(必须做)

  • 接口设计:必须包含完整的请求参数、响应格式、错误码

  • 核心业务逻辑设计:简单流程(≤3步)用文字,复杂流程用时序图、状态图、用例图、流程图描述,禁止写代码

2.4 任务跟踪规则(必须做)

  • 实时更新任务状态:每完成一个任务立即更新状态标记 [ ] → [x]
  • 实时记录提交信息:每完成一个任务立即在提交记录区域添加完成信息
  • 支持中断恢复:确保任务状态和提交记录完整,对话中断后能快速恢复进度
  • 全流程可恢复:任务文档必须包含流程状态总览、产物清单、上下文快照、下一步指令

2.5 代码生成规则(必须做)

  • 优先使用代码生成工具:必须使用 /proj-gen 生成代码,禁止手动编写
  • 统一代码标准:所有代码必须通过统一的生成工具保证格式一致性
  • 生成顺序:SQL → Entity → Mapper → DTO → Service → Controller

2.6 开发完成后(必须做)

代码开发完成后,必须按顺序执行:

  1. /proj-review - 代码自检,修复发现的问题
  2. /proj-gen-test - 生成测试代码
  3. 运行测试 - 确保测试通过
  4. 用户确认后再提交

注意:以上步骤应主动执行,不需要用户提醒。

2.7 强制检查机制(门禁)

  • 文档门禁:缺少全流程任务文档或上下文快照时,只能补文档,禁止进入下一阶段
  • 确认门禁:需求/方案未确认,禁止进入下一阶段
  • 产物门禁:产物清单未记录对应输出,禁止进入下一阶段
  • 模板门禁:未使用模板或 /proj-gen,禁止生成代码
  • 提交门禁:未完成审查和测试,禁止提交

3. 基础规范

3.1 技术栈

  • 框架:Java 17 + Spring Boot 3.x + MyBatis-Plus 3.5.x
  • 数据库:MySQL 8.0+ + Redis 7.0+
  • API文档:Knife4j 4.x

3.2 项目结构

模块结构
{project}/
├── {project}-common/    # 通用模块
├── {project}-core/      # 业务核心
├── {project}-admin/     # 管理后台 (Web端)
├── {project}-api/       # 对外接口 (App端)
└── docs/                # 项目文档
    ├── req/             # 需求分析文档
    ├── design/          # 技术方案文档
    ├── task/            # 任务文档
    └── sql/             # SQL 脚本

包结构
com.{company}.{project}.{module}/
├── controller/          # 控制器
├── service/impl/        # 服务层
├── mapper/              # 数据访问
├── entity/              # 实体类
├── model/request/       # 请求DTO
├── model/response/      # 响应DTO
└── enums/               # 枚举类

Read the full file on GitHub · 231 lines

Changes

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.

  1. 23d ago Changed · +7 lines · +277 tokens per session 64474e98ba2f
  2. 2mo ago First seen · 224 lines · 2,517 tokens per session scan A 48fb43301929

Subscribe to this mod's changes

backend-skill CLAUDE.md is an instructions file published in the GitHub repository zhangloveyan/backend-skill (103 stars, last pushed 23d ago), licensed MIT. It adds 2,794 tokens to every session, about $0.0112 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.

Related

backend-skill CLAUDE.md compared with instructions from other repositories

backend-skill CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
backend-skill CLAUDE.mdzhangloveyan/backend-skillInstructions file10323d agoMITA2,794Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode