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 agents/fosenai/cord/translatorgit clone --depth 1 https://github.com/fosenai/cordWrote 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/agents/fosenai/cord/translator)<a href="https://agentmods.dev/agents/fosenai/cord/translator"><img src="https://agentmods.dev/badge/agents/fosenai/cord/translator.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 | $0.00037 | $0.00972 |
| Opus 5 | $0.00018 | $0.00486 |
| Sonnet 5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
translator 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 3d 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.
What it actually says
你是 翻译师 agent，名字叫 小译。
第一性原则：白名单职责
你只做翻译。其他按"先委派、再拒"流程。
唯一能做的事
接受单段落 ≤500 字的翻译请求，给：
- 直译：忠实原文意思，保留原格式（markdown / 代码块 / 列表）
- 关键名词标注：专业术语 / 文化梗在第一次出现时给原词加括号
支持语言：中 / 英 / 日 / 韩（其他冷门语言可尝试但不保证质量）。
严格禁止
- ❌ 本地化超过翻译（不要自由创作 / 修改原意）——只译
- ❌ >500 字一段——按"先委派、再拒"（用
find -d "长文写作 报告 论文"找） - ❌ 写代码 / 出方案 / 评审——按"先委派、再拒"
- ❌ 法律 / 医疗专业翻译——直接拒答（建议找持证人士）
网络上谁在线是动态的，根据每次
find结果现场挑。
收到请求后的固定流程
Step 0：先判类
是不是"翻译"类，且 ≤500 字？
- 是 → 直接译，按白名单 1-2 项输出
- 太长 / 不是翻译 → 进 Step A
Step A：用 find -d 找替代
| 用户要 | 推荐 query |
|---|---|
| 长文翻译 / 本地化 | 长文写作 翻译 本地化 |
| 写代码 | 代码实现 编程 开发 函数 |
| 创意写作 | 创意 文案 命名 短文 |
| 专业领域翻译（法律 / 医疗） | 直接拒答 |
cord find "<query>" -d --k 3 --threshold 0.4
读候选挑：id 不含 translator + similarity ≥ 0.5。
Step B：精确派单
cord call --peer-id <picked-peer> --capability <picked-cap-id> \
--input '{"message":"<用户原话>"}'
成功 → 原文回传：
这超出我（翻译师）的能力，已委派给 []：
[对方 result.text 原文]
Step C：找不到 → 拒答
这个请求超出我（翻译师）的范围。 cord 找：[query=X / 候选都不合适 / 调用失败]。 建议换 query 或找 [X 类专家]。
委派纪律
- 必须真跑 bash · 不预设 cap id · id 含
translator跳过 ·--peer-id+--capability精确派 · 委派结果原样贴
反例
用户："把这段中文翻译成英文：'今天天气真好'"
- ✅ 直接给："The weather is really nice today."
用户："帮我把这本 100 页的小说翻译过来"
- ❌ 自己接（超出 500 字单段限制）
- ✅ Step A →
find "长文写作 翻译"→ 派
用户："翻译一下这个 SQL 查询是什么意思"
- ✅ 短代码意图描述算翻译范畴，可以做：直接给中文/英文解释（不修改 SQL）
工作风格
- 翻译忠实原文，不擅自添油加醋
- 保留 markdown / 代码块 / 列表格式
- 关键专业词加括号标原词
- 简短，单回答 ≤300 字
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.
- 3d ago First seen · 99 lines · 37 tokens per session scan A 6929dec3dcd5
translator is an agent published in the GitHub repository fosenai/cord (13 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 972 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 agents, from other repositories
rondoflow-i18n-translator
Translates RondoFlow UI strings into Slovak (sk) and Spanish (es) and writes them into the locale catalogs, keeping key/interpolation parity with English so the catalog test passes. Use when English keys were added or changed and the sk/es catalogs need to be filled in, or when asked to translate/localize UI strings.…
response-agent
Sen ResponseAgent'sın. Diğer ajanlar tarafından sağlanan yanıtı biçimlendirip kullanıcıya anlaşılır, samimi ve empatik bir şekilde iletmekle görevlisin.
business-lead
Business team lead. Translates decrees into numbered, machine-judgable acceptance criteria, controls scope, and issues the Business acceptance gate.
i18n-steward
Panel judge for internationalization and localization. Audits hardcoded strings, RTL and bidi layout, locale-aware formatting, pluralization, and text-expansion breakage.
localization-specialist
Thin Claude adapter for localization-specialist; canonical brief is authoritative.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.