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 commands/linfee/spec-kit-cn/translation-executegit clone --depth 1 https://github.com/Linfee/spec-kit-cnWhat 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 | $0.00025 | $0.01081 |
| Opus 5 | $0.00013 | $0.00541 |
| Sonnet 5 | $0.00005 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
translation-execute 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 2d 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 — 95 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: 基于检测结果或手动指定, 智能执行高质量的文件翻译, 确保语义准确性和本地化质量.
调用方式
独立使用
直接执行 /translation-execute 翻译所有检测到的文件, 或传入参数指定范围:
/translation-execute templates/commands/implement.md
由 /translation-detect 自动调用
当 detect 检测到差异并经用户确认后, detect 会自动调用本命令:
- detect 的同步计划会作为参数传入
- 翻译完成后应建议执行 /translation-review 进行审核
执行步骤
1. 翻译准备
- 加载翻译标准(@TRANSLATION_STANDARDS.md)和术语表(@TERMINOLOGY.md)
- 解析输入参数: 来自 detect 的同步计划 或 手动指定的文件列表
- 验证原版文件完整性
- 确定翻译优先级
2. 按优先级执行翻译
优先级顺序:
- 完全同步目录: 执行 rsync 同步 scripts/, .devcontainer/, media/
- 核心模板文件(templates/核心模板)
- CLI 相关文件(src/specify_cli/ 中的文案)
- 项目文档(docs/, README.md 等)
- 辅助文件(memory/, templates/commands/)
对每个文件执行:
- 读取原版文件, 分析内容和结构
- 上下文感知的智能翻译(对比同目录已翻译文件保持风格一致)
- 术语一致性检查(对照术语表)
- 格式和链接保持
- 代码块和占位符保护
3. 翻译质量控制
- 语义准确性验证: 对比原版确保内容完整性
- 术语一致性检查: 同一术语在整个项目中的使用
- 格式完整性: Markdown 格式、链接、图片引用
- 中文表达自然度: 避免机器翻译痕迹
4. 特殊处理规则
- CLI 命令:
specify→specify-cn - 包名:
specify-cli→specify-cn-cli - 路径引用: 保持原版路径不变, 不添加
.specify/前缀 - 代码块: 完全保持原样
- 占位符: 保持格式不变(如 [PROJECT_NAME])
- 技术标记: NEEDS CLARIFICATION, N/A, TODO, TKTK, ??? 绝对不翻译
- yaml.dump/yaml.safe_dump: 必须使用 allow_unicode=True
5. 同步后验证
- 对比原版确保内容完整性, 无新增或遗漏
- 检查 CLI 输出:
uv run specify-cn --help等命令 - 验证特殊规则执行情况
- 检查 repo_owner/repo_name/name 是否正确
- 运行
./tests/e2e/check-yaml-unicode.py确保 yaml.dump 配置正确 - 运行
./tests/e2e/check-cli-help-localization.py验证 CLI Help 完全本地化 - 对于 presets/extensions 更新, 运行
./tests/e2e/check-markdown-translation-coverage.py
6. 输出翻译报告并衔接工作流
生成翻译报告:
- 翻译文件列表和处理结果
- 遇到的问题和决策记录
- 需要人工审核的标记
工作流衔接:
- 使用 AskUserQuestion 询问用户:
"翻译完成. 是否执行 /translation-review 进行质量审核?"
- 用户确认 → 使用 Skill 工具执行 /translation-review
- 用户拒绝 → 输出报告, 结束
行为规则
- 严格遵循 @TRANSLATION_STANDARDS.md 翻译标准
- 使用 @TERMINOLOGY.md 确保术语一致性
- 采用上下文感知的翻译策略, 避免孤立翻译
- 保护所有技术元素(代码, 链接, 占位符)
- 确保翻译后的功能与原版完全一致
- 对不确定的翻译标记为需要人工审核
- 由 detect 调用时, 优先处理 detect 报告中的文件
- 翻译 src/specify_cli/ 时必须重新设置 repo_owner="linfee", repo_name="spec-kit-cn"
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.
- 2d ago First seen · 95 lines · 25 tokens per session scan A a8cb5c5bcc94
translation-execute is a command published in the GitHub repository Linfee/spec-kit-cn (695 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,081 once invoked, about $0.0001 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
language
Command "language" from ErisPulse/ErisPulse, covering erispulse.cli.commands.language 模块, 模块概述, 类列表 and class languagecommand(command).
wp-polylang
Translate an existing WordPress site into a second language using Polylang.
example
Example command that demonstrates CodexSpec extension functionality.
translate-docs
翻译项目文档到指定语言.
review-tasks
审查任务的忠实度、可执行性、依赖关系与验证.
pentester
AIOSON — Evidence-driven adversarial review, bounded hardening, and localized security coverage reports.