Rainman Translate Book is an agent skill that translates complete PDF, DOCX, or EPUB books into other languages by splitting them into chunks handled by parallel subagents. It is used with Codex, Claude Code, and OpenClaw to produce resumable, validated translations in several output formats.
Borrowing it
Nothing to install: this file belongs to deusyu/translate-book. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/deusyu/translate-book/main/CLAUDE.mdgit clone --depth 1 https://github.com/deusyu/translate-bookWrote 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/deusyu/translate-book/claude-md)<a href="https://agentmods.dev/instructions/deusyu/translate-book/claude-md"><img src="https://agentmods.dev/badge/instructions/deusyu/translate-book/claude-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 5.1 | $0.00718 | $0.00718 |
| Opus 5 | $0.00359 | $0.00359 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
translate-book CLAUDE.md 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
translate-book is a Claude Code Skill that translates books (PDF/DOCX/EPUB) into any language using parallel subagents. Published on ClawHub as translate-book and on GitHub as deusyu/translate-book.
Structure
SKILL.md— Skill definition, the orchestration logic that Claude Code / OpenClaw followsscripts/convert.py— PDF/DOCX/EPUB → Markdown chunks (via Calibre HTMLZ)scripts/manifest.py— SHA-256 chunk tracking and merge validationscripts/glossary.py— Term-consistency glossary; per-chunk term tables injected into sub-agent promptsscripts/chunk_context.py— Read-only previous/next chunk excerpts injected into sub-agent promptsscripts/meta.py— Per-chunk sub-agent observation file schemascripts/merge_meta.py— Batch-boundary merge of sub-agent observations into the canonical glossaryscripts/run_state.py— Selective re-translation planner and run_state.json recorderscripts/merge_and_build.py— Merge translated chunks → HTML/DOCX/EPUB/PDFscripts/calibre_html_publish.py— Calibre format conversion wrapperscripts/template.html,scripts/template_ebook.html— HTML templates
Testing changes
Test with a small PDF to verify the full pipeline:
python3 scripts/convert.py /path/to/small.pdf --olang zh
# then run translation via the skill
python3 scripts/merge_and_build.py --temp-dir <name>_temp --title "test"
Verify: all output_chunk*.md files exist, manifest validation passes, output formats generate.
Conventions
- Only
chunk*.mdnaming — nopage*legacy support - Pipeline output artifacts use the canonical names
book.html,book_doc.html,book.docx,book.epub,book.pdf. Internal scripts and skip/cache logic depend on these names; if title-based filenames are added later they must be optional aliases/copies, not silent replacements - SKILL.md frontmatter must stay single-line per field (OpenClaw parser requirement)
- Script paths in SKILL.md use
{baseDir}not hardcoded paths - Subagent instructions in SKILL.md must be platform-neutral (work on Claude Code, OpenClaw, Codex)
- README changes must be synced to both README.md and README.zh-CN.md
- Releases follow
.claude/commands/release.md— three commands in order:git push origin main,git tag vX.Y.Z && git push --tags,npx clawhub@latest publish ./ --version X.Y.Z. Do not skip the git tag; it's the only version anchor in the repo
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.
- 6d ago First seen · 49 lines · 718 tokens per session scan A ad208b20ca4e
translate-book CLAUDE.md is an instructions file published in the GitHub repository deusyu/translate-book (1,575 stars, last pushed 1mo ago), licensed MIT. It adds 718 tokens to every session, about $0.0036 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.