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 skills add JonathanB555/torah-mcp --skill hebrewbooksgit clone --depth 1 https://github.com/JonathanB555/torah-mcpWrote 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/jonathanb555/torah-mcp/hebrewbooks)<a href="https://agentmods.dev/skills/jonathanb555/torah-mcp/hebrewbooks"><img src="https://agentmods.dev/badge/skills/jonathanb555/torah-mcp/hebrewbooks/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/jonathanb555/torah-mcp/hebrewbooks"><img src="https://agentmods.dev/badge/skills/jonathanb555/torah-mcp/hebrewbooks.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 | $0.00088 | $0.02671 |
| Opus 5 | $0.00044 | $0.01336 |
| Sonnet 5 | $0.00018 | $0.00534 |
| Haiku 4.5 | $0.00009 | $0.00267 |
Grade A, and why
hebrewbooks-source scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://www.sefaria.org/api/name/<title>" How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Primary sources for religious questions
When this skill is active, you must ground answers to Jewish religious questions in primary texts you have actually downloaded and read during this turn, before answering from general knowledge.
Two layers, never confused
hebrewbooks.org is behind a Cloudflare challenge since July 2026. Every automated request returns 403 (cf-mitigated: challenge), with or without a browser User-Agent, on hebrewbooks.org as on beta.hebrewbooks.org. Never attempt to bypass it. Independently of the 403, the collection is page scans: even reachable, it could not be used to verify the spelling of a Hebrew word.
So:
- Verification layer: Sefaria, via its API, in source text. This is where every Hebrew quote must come from.
- Reading layer: hebrewbooks.org, cited as a link at the end of the answer. Those links open fine in the user's browser; the challenge only blocks robots.
Both appear in the answer. Neither replaces the other.
When to activate
Activate automatically (without being asked) when the user's question involves:
- Halacha (Shulchan Aruch, Mishneh Torah, responsa, etc.)
- Tanakh commentary (Rashi, Ramban, Ibn Ezra, Malbim...)
- Talmud Bavli/Yerushalmi and meforshim
- Hassidout (Tanya, Likutei Moharan, Noam Elimelech, Sfat Emet...)
- Mussar (Mesillat Yesharim, Chovot HaLevavot, Orchot Tzaddikim...)
- Séfarade poskim (Ben Ish Chai, Kaf HaChaim, Yabia Omer...)
- Kabbalah (Zohar, Etz Chaim, Pri Etz Chaim...)
- Minhagim, customs, history of poskim
Skip if the question is purely cultural/historical with no halachic or textual dimension, or if the user explicitly says "don't use hebrewbooks".
Workflow
Step 1 — Resolve the exact reference
Guessing a Sefaria ref wastes a round-trip. Resolve it:
curl -s "https://www.sefaria.org/api/name/<title>"
The response gives is_ref and completions, which show the exact node names (e.g. Chovot HaLevavot, Fourth Treatise on Trust, Tanya, Part IV; Iggeret HaKodesh, Ben Ish Hai, Halachot 1st Year, <Parasha>). For a chapter structure, https://www.sefaria.org/api/v2/index/<title> returns the full tree.
What ships with it
1 file 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.
- 4d ago Changed · +42 lines a1a9028fbdb1
- 9d ago First seen · 107 lines · 88 tokens per session scan A 838f3e3b50f2
hebrewbooks-source is a skill published in the GitHub repository JonathanB555/torah-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 2,671 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.