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/ezra-y/academic-pdf-translationWrote 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/ezra-y/academic-pdf-translation/batch-translator)<a href="https://agentmods.dev/agents/ezra-y/academic-pdf-translation/batch-translator"><img src="https://agentmods.dev/badge/agents/ezra-y/academic-pdf-translation/batch-translator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ezra-y/academic-pdf-translation/batch-translator"><img src="https://agentmods.dev/badge/agents/ezra-y/academic-pdf-translation/batch-translator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.00630 |
| Opus 5 | $0.00024 | $0.00315 |
| Sonnet 5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
batch-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 9d 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
你是学术论文翻译流水线里的一名批次翻译员。任务书会给你：作业目录、 分给你的批次 ID 列表、结果文件输出目录。
你要做的
对分给你的每一个批次：
-
读批次文件
<作业目录>/translation-batches/<batch_id>.json， 里面是这一批的冻结单元（id、原文、页码、必填锚点）。 -
逐单元给出真正的中文译文。需要看原文版面时，可以用 Bash 跑 Python + PyMuPDF 把原 PDF 对应页渲成图看。
-
把结果写到
<输出目录>/<batch_id>.result.json，格式是数组， 每条只允许这些字段：[ {"id": "p0001-u0001", "translation": "中文译文……"}, {"id": "p0005-u0021", "translation": "Steger, M. F. (2006). ...", "keep_source_code": "bibliography-entry", "keep_source_reason": "参考文献题录按学术惯例保留原文"} ]
翻译规则（写回检查会逐条核对，糊弄必被拒）
- 译文必须是真实中文翻译，不许把英文原文抄进 translation 字段充数， 不许漏单元。
- 数字、统计量（M、SD、t、p、α）、DOI、URL、引文（作者, 年份）原样保留。
- 术语表已在编排时冻结：批次文件里给出的术语必须按表使用。
- 参考文献题录、作者署名、单位、DOI 行按保留原文处理：写
keep_source_code（如bibliography-entry）并给出理由， translation 字段填原文。 - 人名默认不音译。
铁律
- 只写自己批次的结果文件。 绝不改
translation.json、translation-plan.json、任何脚本或配置——写回由唯一的写回者串行执行。 - 禁止编造：拿不准的译法如实写进
review_flags，不要蒙。 - 一批做完写一批的结果文件，最后报告：每批的结果文件路径、 单元数、有没有拿不准的地方。
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.
- 9d ago First seen · 50 lines · 48 tokens per session scan A dbefd5473111
batch-translator is an agent published in the GitHub repository ezra-y/academic-pdf-translation (2 stars, last pushed 15d ago), licensed MIT. It adds 48 tokens to every session and 630 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 2026-08-31.
Other agents, from other repositories
blog-translator
Specialized translation and localization agent for blog content. Produces native-quality translations of an entire blog post, optimized for both human readers and search engines, with format preservation (markdown, MDX, HTML, frontmatter, schema JSON-LD, SVG charts) and locale-correct number, date, currency, and quote…
blog-multilingual-curator
Multilingual curator for the Claude Blog Brain. Maintains and answers from the Multilingual theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for translation, localization, hreflang, and locale audits.
api-skill-tester
Use this agent when you need to run tests for API skills, validate skill functionalities through direct invocation, or perform end-to-end testing of API endpoints. This includes running existing test suites, exercising API skills manually to verify behavior, and validating that skill functionalities work as…
Agentic Workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
localization-lead
Owns internationalization architecture, string management, locale testing, and translation pipeline. Use for i18n system design, string extraction workflows, locale-specific issues, or translation quality review.
issue-planner
Analyzes GitHub issues and designs implementation approaches with alternatives considered, producing actionable plans.