TheologAI: Instructions file for Claude Code

CLAUDE.md

TheologAI CLAUDE.md is an instructions file for Claude Code from TJ-Frederick/TheologAI. It costs 4,173 tokens per session, scanned A, original, ISC.

Developer instructions for TheologAI, a research server about Christian theology that provides Bible translations, commentaries, historical documents, and language tools through MCP.

In plain words
What is it for?
Use it when developing, testing, building, or updating TheologAI’s research tools, prompts, database, or server transports.
Why use it?
It explains the project’s supported transports, build and test commands, data sources, and release-authority rules so changes can be checked against the right information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is TJ-Frederick/TheologAI's own configuration. It tells Claude Code how to work on TheologAI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TheologAI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TJ-Frederick/TheologAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TJ-Frederick/TheologAI/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/TJ-Frederick/TheologAI

Made for: Claude Code.

Wrote 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.

agentmods badge for TheologAI CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tj-frederick/theologai/claude-md/github.svg)](https://agentmods.dev/instructions/tj-frederick/theologai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tj-frederick/theologai/claude-md"><img src="https://agentmods.dev/badge/instructions/tj-frederick/theologai/claude-md/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.

agentmods 80×15 button for TheologAI CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tj-frederick/theologai/claude-md"><img src="https://agentmods.dev/badge/instructions/tj-frederick/theologai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,173 This file is loaded in full into every session.
When invoked 4,173 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04173 $0.04173
Opus 5 $0.02086 $0.02086
Sonnet 5 $0.00835 $0.00835
Haiku 4.5 $0.00417 $0.00417

Measured 9d ago against content hash afa33eec0e64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

TheologAI 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 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.

CLAUDE.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TheologAI — Development Guide

This developer guide is not release-identity authority. For the sole active production and preview-control snapshot, see docs/CURRENT-RELEASE.md; release identities below are dated historical evidence.

Production MCP server for theological research. Eleven tools, six prompts, eight Bible translations, six commentaries, 35 historical documents and works, Greek/Hebrew language tools, and on-chain donation support. Tools, resources, and prompts are available on every transport; MCP Logging is stdio-only because HTTP is stateless.

Quick Start

npm run dev          # Start dev server (stdio, tsx watch)
npm run build        # TypeScript compile + copy data to dist/
npm run build:db     # Rebuild SQLite database from source data
npm test             # Run all tests (vitest)
npm run test:unit    # Unit tests only
npm start            # Production server (requires build first)

Set PORT=3000 in .env for HTTP transport; omit for stdio.

Architecture

src/
├── index.ts              # Entry point — stdio or HTTP transport (Node.js)
├── worker.ts             # Entry point — Cloudflare Workers (Streamable HTTP)
├── server.ts             # Node wrapper around the shared MCP registrar
├── worker-server.ts      # Worker wrapper around the shared MCP registrar
├── mcp/                  # Shared tools/resources/prompts, schemas, and errors
├── http/                 # Node and Worker transport policies
├── worker-env.ts         # Env type for Workers bindings (D1, secrets, vars)
├── tools/v2/             # Tool handlers + Node.js composition root
│   └── index.ts          # createCompositionRoot() — Node.js wiring (better-sqlite3)
├── tools/worker/         # Workers composition root
│   └── index.ts          # createWorkerCompositionRoot() — D1 wiring (per-request)
├── services/             # Business logic — async, works with both SQLite and D1
│   ├── bible/            # BibleService, CrossReferenceService, ParallelPassageService
│   ├── commentary/       # CommentaryService
│   ├── historical/       # HistoricalDocumentService
│   ├── languages/        # StrongsService, MorphologyService
│   └── donation/         # DonationService
├── adapters/             # External API clients + data repositories
│   ├── bible/            # EsvAdapter, NetBibleAdapter, HelloAoAdapter
│   ├── commentary/       # HelloAoCommentaryAdapter, metadata-only CcelSearchAdapter
│   ├── donation/         # OnChainVerifier
│   ├── data/             # SQLite repositories (Node.js — better-sqlite3)
│   ├── d1/               # D1 repositories (Workers — Cloudflare D1)
│   └── shared/           # Database.ts, HttpClient.ts, HtmlParser.ts
├── formatters/           # Pure Markdown formatting functions
├── kernel/               # Shared domain primitives
│   ├── reference.ts      # THE canonical Bible reference parser
│   ├── books.ts          # 66-book registry with all external format codes
│   ├── repositories.ts   # Async repository interfaces (shared by SQLite + D1)
│   ├── types.ts          # Shared TypeScript interfaces
│   ├── errors.ts         # Typed error hierarchy
│   └── cache.ts          # Generic LRU cache with TTL
└── data/                 # Compiled data (parallel-passages.json)

data/                     # Source data files
├── theologai.db          # SQLite database (built from source data)
├── biblical-languages/   # Strong's concordance, STEPBible morphology/lexicons
├── cross-references/     # OpenBible.info cross-reference TSV
├── historical-documents/ # 17 legacy creeds, confessions, catechisms (JSON)
└── historical-source-packs/ # 18 reviewed, sectioned-only source-pack editions

skills/                   # Agent skill workflows
├── word-study/           # Greek/Hebrew word study methodology
├── passage-exegesis/     # Systematic exegetical analysis
└── confession-study/     # Cross-tradition doctrinal comparison

test/
├── unit/                 # Fast unit, contract, parity, and boundary tests
│   ├── kernel/           # reference, books, cache, errors (94 tests)
│   ├── formatters/       # bibleFormatter, commentary, historical, languages (75 tests)
│   ├── services/         # bible/, commentary/, historical/, languages/, async-compat/ (64 tests)
│   ├── adapters/d1/      # D1 repository tests (61 tests)
│   ├── tools/worker/     # Worker composition root (11 tests)
│   └── worker/           # Worker entry point and policy tests
├── integration/current/  # Shared Node/Worker MCP contract tests
├── worker-runtime/       # Real Workerd endpoint with isolated D1
├── helpers/              # Reusable test utilities (mockD1.ts)
├── fixtures/             # Shared test data
└── setup.ts              # Global test config

Read the full file on GitHub · 258 lines

Changes

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.

  1. 9d ago First seen · 258 lines · 4,173 tokens per session scan A afa33eec0e64

Subscribe to this mod's changes

TheologAI CLAUDE.md is an instructions file published in the GitHub repository TJ-Frederick/TheologAI (24 stars, last pushed yesterday), licensed ISC. It adds 4,173 tokens to every session, about $0.0209 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens