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.
git clone --depth 1 https://github.com/Linfee/spec-kit-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/commands/linfee/spec-kit-cn/translation-review)<a href="https://agentmods.dev/commands/linfee/spec-kit-cn/translation-review"><img src="https://agentmods.dev/badge/commands/linfee/spec-kit-cn/translation-review.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 | $0.00034 | $0.02131 |
| Opus 5 | $0.00017 | $0.01066 |
| Sonnet 5 | $0.00007 | $0.00426 |
| Haiku 4.5 | $0.00003 | $0.00213 |
Grade A, and why
translation-review 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户输入可以直接由代理提供或作为命令参数提供给你 - 你必须考虑它(如果不为空).
用户输入: $ARGUMENTS
目标: 系统性审核翻译质量, 包含对比原版 review、关键修复点专项检查、质量评分和发布验证, 确保翻译达到发布标准.
确保本地版本号与原版严格对齐, 禁止本地版本自增.
第一阶段: 环境与基础验证
1. 验证环境准备
- 确认 spec-kit 目录存在且包含原版文件
- 确认各目录结构与原版一致: templates/, docs/, memory/, src/, scripts/, .devcontainer/, media/
- 确认 AGENTS.md 文件存在且正确引用 CLAUDE.md
- 确认 pyproject.toml 配置文件与原版结构一致
rsync 使用安全规则:
- 禁止同步:
.github/目录(本项目有独立的工作流) - 完全同步目录 (可使用 rsync --delete):
scripts/,.devcontainer/,tests/,media/ - 翻译目录禁止 --delete (增量合并):
templates/,docs/,memory/, 根目录文档 - 禁止使用:
rsync --delete同步翻译目录, 会永久丢失中文翻译
2. 关键修复点专项检查
以下检查必须全部通过才能继续后续步骤, 任何一项失败都必须优先修复:
A. GitHub 仓库配置 (严重)
grep -n 'repo_owner = "linfee"' src/specify_cli/__init__.py # 期望: repo_owner = "linfee"
grep -n 'repo_name = "spec-kit-cn"' src/specify_cli/__init__.py # 期望: repo_name = "spec-kit-cn"
B. CLI 命令统一性 (严重)
grep -n 'name="specify-cn"' src/specify_cli/__init__.py # 期望: 匹配
grep -n "specify[^-]" src/specify_cli/__init__.py # 期望: 无匹配(无遗留 specify)
grep -n "specify-cn init" src/specify_cli/__init__.py | wc -l # 期望: >5
C. 用户界面翻译 (重要)
grep -n "已准备就绪\|正在检查\|提示 : " src/specify_cli/__init__.py # 期望: 找到中文
grep -n -E "(Tip:|Checking for|ready to use|Display version)" src/specify_cli/__init__.py # 期望: 无匹配
D. 包名一致性 (重要)
grep -n "specify-cn-cli" src/specify_cli/__init__.py # 只在文档字符串中出现
E. 技术变量保护 (严重)
grep -n "_specify_tracker_active" src/specify_cli/__init__.py # 保持不变
grep -n "scripts_root.*specify" src/specify_cli/__init__.py # .specify 路径不变
F. 斜杠命令格式 (重要)
grep -n "/speckit\." src/specify_cli/__init__.py # 期望: 无匹配
grep -n -E "(建立项目原则|创建基线规范|创建实施计划|生成可执行任务|执行实施)" src/specify_cli/__init__.py # 期望: 找到中文
翻译覆盖检测:
grep -c "用户输入\|概述\|执行步骤\|目标:" templates/commands/specify.md # 期望: >10
grep -r "规范驱动开发\|用户故事\|验收标准" templates/ || echo "关键术语缺失"
第二阶段: 翻译质量审核
3. review 核心 md 文件翻译质量
- 深度遍历 templates/, memory/, docs/ 目录, 对每个 md 文件对比原版对应文件, review 翻译质量
- 使用 Task 工具并行执行
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 · 149 lines · 34 tokens per session scan A aad3b691635a
translation-review is a command published in the GitHub repository Linfee/spec-kit-cn (695 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,131 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
translate-docs
A command that translates project documentation into a requested language while preserving its technical meaning and formatting. It is intended for documents such as Markdown files and other project materials.
plan-localization
Plan localisation covering extraction, translation workflow, and the layout and format issues that follow.
growth-localization
Localization strategy and international expansion.
brand-update
Recalibrate the brand pack after positioning, personas, pricing or naming changed — propagate the change through terminology, strings and every locale in the same edit.
init-deep
Initiates a repository traversal to create localized PIPELINE-CONTEXT.md hierarchical context files.
export
A command that exports completed translation data into a finished EPUB or TXT file.