What is take-skills CLAUDE.md?

Project instructions and an index for a Chinese-language Claude Code toolkit. The toolkit contains agents, commands, domain skills, rules, scripts, and a staged workflow from requirements discovery through delivery.

Use it to navigate the toolkit, choose commands such as interview, specification, planning, coding, testing, review, and debugging, and run scripts for project analysis, scope, memory, and architecture checks.

It tells the coding agent which repository components exist and how they fit together. The documented stages and validation scripts make the development process easier to follow consistently.

How an8079/take-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to an8079/take-skills. 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/an8079/take-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/an8079/take-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/an8079/take-skills/claude-md/github.svg)](https://agentmods.dev/instructions/an8079/take-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/an8079/take-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/an8079/take-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/an8079/take-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/an8079/take-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 614 This file is loaded in full into every session.

When invoked 614 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.

Model	Per session	Once invoked
Fable 5.1	$0.00614	$0.00614
Opus 5.5	$0.00246	$0.00246
Sonnet 5.5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 2mo ago against content hash 2a56e8d77b2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

take-skills 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 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.

CLAUDE.md · 93 lines

What it actually says

CLAUDE.md - 项目配置索引

版本： v2.0.0 | 更新日期： 2026-03-01 | 适配 Claude Code 使用

核心文件索引

类别	文件	说明
Agent	`agents/`	5 个核心 Agent
Command	`commands/`	8 个核心命令
Skills	`skills/`	领域技能库
Rules	`rules/`	架构/安全规则
Scripts	`scripts/`	工程化脚本

Agents（5 个）

Agent	职责
`interviewer`	需求访谈
`architect`	架构设计
`coder`	编码实现
`reviewer`	代码审查
`debug-helper`	调试助手

Commands（8 个）

命令	用途
`/interview`	需求访谈
`/spec`	规格设计
`/plan`	任务计划
`/code`	编码实现
`/tdd`	TDD 模式
`/test`	测试验证
`/review`	代码审查
`/debug`	调试模式

增量开发命令： /import, /analyze, /scope

阶段流程

需求访谈 → 规格设计 → 实现计划 → 编码 → 测试 → 审查 → 交付

关键脚本

脚本	用途
`phase-manager.js`	阶段管理
`scope-manager.js`	边界管理
`memory-manager.js`	记忆管理
`architecture-validator.js`	架构验证
`code-entropy.js`	代码熵治理
`project-analyzer.js`	项目分析

触发词

输入	行为
`开始访谈`	进入访谈模式
`导入项目`	导入现有项目
`分析项目`	分析项目架构
`设置范围`	管理开发边界

文档目录

docs/ - 技术规格文档
docs/spec-template.md - 规格模板
docs/deploy/ - 部署配置模板

规则目录

rules/architecture-boundary.md - 架构分层规则

详细文档请查阅对应文件。

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.

2mo ago First seen · 93 lines · 614 tokens per session scan A 2a56e8d77b2b

Subscribe to this mod's changes

take-skills CLAUDE.md is an instructions file published in the GitHub repository an8079/take-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 614 tokens to every session, about $0.0025 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 2026-08-31.

take-skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
take-skills CLAUDE.mdan8079/take-skills	Instructions file	4	7mo ago	MIT	A	614	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	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	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

take-skills: Instructions file for Claude Code