Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add taekchef/claude-code-zh-cn/plugin install claude-code-zh-cnWrote 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/taekchef/claude-code-zh-cn/zh-cn-setup)<a href="https://agentmods.dev/skills/taekchef/claude-code-zh-cn/zh-cn-setup"><img src="https://agentmods.dev/badge/skills/taekchef/claude-code-zh-cn/zh-cn-setup.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 5.1 | $0.00078 | $0.01176 |
| Opus 5 | $0.00039 | $0.00588 |
| Sonnet 5 | $0.00016 | $0.00235 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade B, and why
zh-cn-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. **合并 spinner 中文化配置**到 `~/.claude/settings.json`（从插件内置的 verbs/tips 数据构建，只补齐缺失项，不覆盖用户已有配置；带备份 + 原子写） How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zh-cn-setup：中文本地化增强安装
本 skill 是 claude-code-zh-cn 插件的首次增强安装入口。在用户通过 claude plugin marketplace add + claude plugin install 装好插件后，运行本 skill 可补齐以下"装插件本身不会自动完成"的步骤。
何时使用
当用户表达以下意图时主动触发：
- "spinner 还是英文" / "转圈的文字没翻译"
- "怎么完整启用中文" / "安装完后还要做什么"
- 在 Windows / macOS / Linux 上刚装好插件，想确认中文化是否完整
执行步骤
运行跨平台安装脚本（macOS / Linux / Windows 通用，需 Node.js）：
node "${CLAUDE_PLUGIN_ROOT}/skills/zh-cn-setup/scripts/setup.js"
脚本会自动完成：
- 合并 spinner 中文化配置到
~/.claude/settings.json（从插件内置的 verbs/tips 数据构建，只补齐缺失项，不覆盖用户已有配置；带备份 + 原子写） - 检测 CC Switch：若检测到 CC Switch 的通用配置缺少中文设置，脚本会输出需要用户确认的提示——因为是交互式安装，请把脚本输出的指令原文转达给用户，让用户决定是否授权同步
- 报告 patch 状态并提示是否需要重启
- 输出 skill 描述汉化的只读扫描、翻译和恢复命令；CC Switch skill 位于
~/.claude外时，使用ZH_CN_SKILL_I18N_EXTRA_ROOTS指定真实目录 - 检测 CC Switch 数据库 skill 描述：若
~/.cc-switch/cc-switch.db的skills表中描述仍为英文、但对应SKILL.md已翻译为中文，脚本会提示运行可选工具cc-switch-descriptions.js（默认只读预览，--apply才写入并先备份数据库，输出还原命令）
重要约束
- 不要在 skill 里调用
claude plugin install/claude plugin update：插件本体的安装/更新由用户手动或 Claude plugin manager 负责，避免"插件装自己/更新自己"的循环 - CLI patch（npm cli.js / native exe）由 session-start hook 自动维护，不在本 skill 内手动 patch。native exe 更新后需要用户关闭所有 Claude Code 窗口再重开，脚本会提示
- CC Switch 数据库写入必须由用户主动授权：
cc-switch-descriptions.js的--apply只在用户主动运行时执行，skill 只输出命令，不在进程内替用户写数据库 - 脚本所有写操作都带备份和失败回滚，不会让机器配置损坏
CC Switch skill 描述同步工具
ZH_CN_SKILL_I18N_EXTRA_ROOTS 只翻译 SKILL.md 文件本体，不会写 CC Switch 数据库。若脚本检测到 ~/.cc-switch/cc-switch.db 的 skills 表描述仍为英文，把以下命令原文转达给用户：
# 只读预览（默认，不写入）
node "${CLAUDE_PLUGIN_ROOT}/skills/zh-cn-setup/scripts/cc-switch-descriptions.js"
# 确认后写入（先备份数据库，输出还原命令）
node "${CLAUDE_PLUGIN_ROOT}/skills/zh-cn-setup/scripts/cc-switch-descriptions.js" --apply
同一份 description 同时用于 CC Switch 管理界面、Claude Code /skills 面板和 model 自动触发，所以默认只读、由用户决定是否 --apply。
给用户的最终提示
脚本跑完后，根据其输出告诉用户：
- 如果提示"请重启 Claude Code"：说明 CLI patch 已由 hook 处理，重启后生效
- 如果提示 CC Switch 同步：把脚本给出的手动步骤或授权命令转给用户
- 如果提示 Windows 需手动运行
install.ps1 -UpdateOnly：确认用户已完全退出所有 Claude Code 窗口后，把脚本输出的两行命令原文转给用户（Set-Location '<目录>'+powershell ... -File .\install.ps1 -UpdateOnly）。务必提醒扩展名必须是.ps1（末尾的1不能漏），否则 PowerShell 会报the file does not have a '.ps1' extension。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 62 lines · 78 tokens per session scan B ebd38d90576c
zh-cn-setup is a skill published in the GitHub repository taekchef/claude-code-zh-cn (753 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,176 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
content-rewriter
Cross-platform content repurposer. Takes one piece of content and rewrites it for multiple Chinese social media platforms, adapting tone, format, length, and style.
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
detect-task
Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
session-boundary
Internal skill for commands. Resolve and VALIDATE this branch's session boundary - the ref a session's commit range is measured from - and report how much it can be trusted. Do not trigger on user conversation; only when a command needs the session range.