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/taekchef/claude-code-zh-cn/agents-mdgit clone --depth 1 https://github.com/taekchef/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/instructions/taekchef/claude-code-zh-cn/agents-md)<a href="https://agentmods.dev/instructions/taekchef/claude-code-zh-cn/agents-md"><img src="https://agentmods.dev/badge/instructions/taekchef/claude-code-zh-cn/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 | $0.00940 | $0.00940 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade B, and why
claude-code-zh-cn AGENTS.md 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 5d 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.
- `install.sh` 安装时从上述两个 JSON 文件动态读取，现场组装合并到 `~/.claude/settings.json` Copies of this mod
1 near-identical copy found in the catalogue:
- claude-code-zh-cn CLAUDE.md — 91% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-zh-cn
Claude Code CLI 中文本地化插件。
项目结构
patch-cli.sh— CLI 硬编码文字 patch（被 install.sh 和 session-start hook 调用）cli-translations.json— 2070 条 UI 翻译对照表（英文→中文），patch-cli.sh 从此文件读取install.sh/uninstall.sh— 安装/卸载脚本compute-patch-revision.sh— patch 规则指纹计算，供 install.sh 和 session-start hook 共用settings-overlay.json— 合并到 settings.json 的中文设置（只含 language、spinnerTipsEnabled 等独有配置，不含 verbs 和 tips 数据）plugin/— 插件（manifest、hooks、commands 命令 stub、output-styles；hooks/user-prompt-submit.js实现/chinese/english切换）verbs/zh-CN.json— 187 个 spinner 动词翻译（唯一数据源）tips/zh-CN.json— 41 条 spinner 提示翻译（唯一数据源）CHANGELOG.md— 版本变更记录
数据流
翻译数据单一来源，不允许重复维护：
verbs/zh-CN.json是动词的唯一数据源tips/zh-CN.json是提示的唯一数据源settings-overlay.json不重复存放 verbs 和 tips 数据install.sh安装时从上述两个 JSON 文件动态读取，现场组装合并到~/.claude/settings.json
禁止把 verbs 或 tips 的内容复制到 settings-overlay.json 里。如果要修改翻译，只改 verbs/ 或 tips/ 里的文件。
技术要点
- patch-cli.sh 使用内容匹配（匹配英文原文），不依赖变量名，跨版本稳定
- 从
cli-translations.json批量读取翻译，按字符串长度降序替换（长字符串优先，避免子串冲突） - cli.js 里的
…是真实 U+2026 字符，不是\u2026转义序列 - node -e 在 bash 单引号里，用 Unicode 转义（
\uXXXX）写中文，避免引号嵌套问题 - Hook 等技术术语保留英文（Hook 不是"钩子"，同 API、PR）
- Windows 兼容：NTFS 上
fs.renameSync先 unlink 再 rename
维护流程规则
- 除非用户明确说“直接推 main”或“绕过 PR”，否则所有代码改动默认走新分支、推分支、开 PR，不直接 push
main。 - PR 合并或关闭后要做收尾清理：先
git fetch origin --prune，再检查git worktree list、git branch -vv和 PR 状态；确认无用且工作区干净的 worktree、本地分支、远端残留分支都要清掉。 - squash merge 后不能只按
git branch --merged判断是否可删；如果本地分支仍显示有独立提交，要结合 GitHub PR 已合并/已关闭状态和 worktree 干净状态再决定。
版本发布流程
每完成一批有意义的改动后，按以下步骤发布新版本：
- 升版本号 — 修改
plugin/manifest.json里的version（语义化版本） - 更新 CHANGELOG — 在
CHANGELOG.md顶部新增版本段落，分"新增/改进/修复" - 提交 —
git commit，提交信息带上版本号 - 打 tag —
git tag vX.Y.Z - 推送 —
git push origin main --tags - 发 Release —
gh release create vX.Y.Z --title "vX.Y.Z" --notes "变更摘要" - 发布状态校验 —
bash scripts/preflight.sh --release-state，确认 manifest / CHANGELOG / tag / GitHub Release 对齐
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.
- 5d ago First seen · 54 lines · 940 tokens per session scan B 58aba42d2b77
claude-code-zh-cn AGENTS.md is an instructions file published in the GitHub repository taekchef/claude-code-zh-cn (742 stars, last pushed 3d ago), licensed MIT. It adds 940 tokens to every session, about $0.0047 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 instructions, from other repositories
mattpocock-skills-zh CLAUDE.md
Instructions for devcxl/mattpocock-skills-zh, a project described as: Matt Pocock 技能集的中文翻译版 — 地道中文，原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步.
tolgee-platform AGENTS.md
AGENTS.md instructions for tolgee/tolgee-platform, covering agents.md, repository structure, backend development, database migrations and backend testing.
formkind AGENTS.md
Instructions for khanhcamap2020-sudo/formkind, covering agent guide, commands and change rules.
DialectOS CLAUDE.md
Instructions for KyaniteLabs/DialectOS, covering kyanitelabs engineering rules, project-specific context, kyanitelabs engineering rules, organization principles and issue-driven development.
globalize-skills CLAUDE.md
Claude Code instructions for globalize-now/globalize-skills, covering globalization skills, repository structure, conventions, installing a skill and install a single skill into the current project.
go-i18n CLAUDE.md
Instructions for kaptinlin/go-i18n, covering go-i18n, commands, tests, quality and architecture.