Bilingual Book Maker is an AI translation tool that creates multilingual versions of EPUB, TXT, Markdown, subtitle, and PDF files. It is for translating public-domain books and other supported documents with language-model or machine-translation services. Its catalogue skill lets coding agents operate the translation tool.
Borrowing it
Nothing to install: this file belongs to yihong0618/bilingual_book_maker. 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/yihong0618/bilingual_book_maker/main/.agents/skills/bbm-plan/SKILL.mdgit clone --depth 1 https://github.com/yihong0618/bilingual_book_makerWrote 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/skills/yihong0618/bilingual_book_maker/bbm-plan)<a href="https://agentmods.dev/skills/yihong0618/bilingual_book_maker/bbm-plan"><img src="https://agentmods.dev/badge/skills/yihong0618/bilingual_book_maker/bbm-plan/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/skills/yihong0618/bilingual_book_maker/bbm-plan"><img src="https://agentmods.dev/badge/skills/yihong0618/bilingual_book_maker/bbm-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 40 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 87 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Supply Chain · line 182 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Output Handling · line 470 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00080 | $0.10031 |
| Opus 5 | $0.00040 | $0.05015 |
| Sonnet 5 | $0.00016 | $0.02006 |
| Haiku 4.5 | $0.00008 | $0.01003 |
Grade C, and why
bbm-plan scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sS "$ROOT/v1/models" -H "Authorization: Bearer $KEY" | python3 -c 'import json,sys; d=json.load(sys.stdin)["data"]; print([m["id"] for m in d])' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`codex` (nothing to curl). Three ordered questions, each answered by a call: How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bbm-plan: plan-mode EPUB translation
Hard constraint: this skill uses --plan-classify agent, and only that.
The plan arrives with its uncertain signatures set to "action": null and
the translate run refuses to start while any null remains, so you, the
coding agent, own the classification step against the real samples. Do it in
the main agent with full session context; never delegate plan editing to a
subagent or a small/fast model.
Repo: the repository this skill ships in (make_book.py at its root). Run
every command from the repo root. Plan mode is epub-only.
You are the trained CLI operator. You pick every flag from the flag menu below and state each choice with a one-line reason; the menu's defaults are the recommendation, and you follow them unless the user asks for something else or the book argues otherwise. The user hands over a book, credentials and (if they have one) a prompt file, approves the plan and the cost, and gets a bilingual epub back — they are never asked to experiment with flags, halt semantics or resume mechanics.
Two runs of one command with small flag changes: plan → full. A smoke test sits between them, optional and skipped by default — §4 says when a book has earned one.
All state lives on disk (bbm_providers.json, .env, <book>_plan.json,
the resume cache, run.log), so any step can be redone after a crash or in
a new session.
0. Credentials and route — probe first, then ask
Find out what the user already has before asking for anything. Three sources, all checked for presence only — never print a value:
set -a; [ -f .env ] && source .env; set +a
python3 - <<'EOF'
import json, os, pathlib
seen = []
for f in (pathlib.Path("bbm_providers.json"), pathlib.Path.home()/".bbm"/"providers.json"):
if f.is_file():
for name, e in json.load(open(f)).get("providers", {}).items():
key = e.get("env_key") or "BBM_API_KEY"
seen.append(f"{name}: {e.get('api_style')} {e.get('base_url','(default host)')} "
f"model={(e.get('default_models') or ['(none)'])[0]} {key}={'set' if os.environ.get(key) else 'UNSET'}")
print("\n".join(seen) or "no provider entries")
for v in ("OPENAI_API_KEY", "ANTHROPIC_API_KEY", "BBM_API_KEY", "BBM_ORCAROUTER_API_KEY"):
print(v, "set" if os.environ.get(v) else "unset")
EOF
command -v codex >/dev/null && codex login status 2>&1 | head -1 || echo "codex: not installed"
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed 8430ed6a3daa
- 3d ago Changed · +30 lines fc0ff4d82293
- 5d ago Changed · +73 lines · -4 tokens per session ef43bfb042ef
- 6d ago Changed · +149 lines 092bde20eced
- 10d ago First seen · 331 lines · 84 tokens per session scan C 9735035a0f46
bbm-plan is a skill published in the GitHub repository yihong0618/bilingual_book_maker (9,772 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 10,031 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.