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 midvash/bible-mcp --skill scripture-lookupgit clone --depth 1 https://github.com/midvash/bible-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/midvash/bible-mcp/scripture-lookup)<a href="https://agentmods.dev/skills/midvash/bible-mcp/scripture-lookup"><img src="https://agentmods.dev/badge/skills/midvash/bible-mcp/scripture-lookup.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 | $0.00060 | $0.00943 |
| Opus 5 | $0.00030 | $0.00472 |
| Sonnet 5 | $0.00012 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
scripture-lookup 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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scripture lookup
Retrieve Scripture from the Bible MCP server instead of quoting from memory. Recalled verse text drifts between translations and misnumbers verses; the tools return the exact wording of the version you name.
Picking the right tool
| Situation | Tool |
|---|---|
| You have a reference in any language ("João 3:16", "Psalm 23") | get_passage |
| You know book, chapter and verse numbers exactly | get_verse |
| You need a whole chapter | get_chapter |
| You remember wording but not where it is | search_bible |
| You need the same passage in several versions | compare_passage |
| You need to know what is available | list_versions, list_books |
| You want related passages ("what else speaks to this?") | get_cross_references |
| You need background on a chapter, a person, or a term | search_study, get_commentary |
| The question is what an original-language word means | get_strongs |
get_passage is the usual entry point — it parses natural references and
accepts book names in the user's own language, so it saves a lookup step. It
also takes ranges that cross chapters ("Romans 8:1-9:5") and several references
at once ("John 3:16; Romans 8:1"), so a passage list is one call, not five.
For study, the natural order is: read the passage, call get_commentary for the
chapter's context, then get_cross_references on the verse that carries the
weight. The server also ships ready-made prompts — sermon preparation, a
devotional, a word study, a translation comparison — if the client exposes them.
Original languages
get_strongs takes a Strong's number ("H430", "G2316") or the word itself, in
the original script or transliterated ("elohim", "θεός"), and returns the lemma,
the senses, and how the KJV renders it, translated into the requested language.
There is no word-by-word mapping between a verse and its Strong's numbers. The morphological source this server has access to arrives without those tags. If you are not certain which entry a given word in a verse maps to, say so instead of asserting one.
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.
- 7d ago First seen · 84 lines · 60 tokens per session scan A 61112028d3c6
scripture-lookup is a skill published in the GitHub repository midvash/bible-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 943 once invoked, about $0.0003 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 skills, from other repositories
scripture-lookup
Look up, search, and cite Bible verses via the hosted Bible MCP. Use when the user asks for Scripture, a verse or passage reference, a chapter to read, a topical or keyword Bible search, a random verse, available translations, or a list of books. Never invent verse text.
baoyu-comic
A creator for educational comics, including biographies and tutorials, that turns supplied content or topics into illustrated comic pages.
canvas
Fetch Canvas LMS courses and assignments via API token.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
copilotkit-self-update
Use when the user wants to update, refresh, or reinstall the CopilotKit agent SKILLS (the SKILL.md files that teach this agent about CopilotKit). NOT for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit…
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…