Borrowing it
Nothing to install: this file belongs to MinistryPlatform-Community/MPNext. 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/MinistryPlatform-Community/MPNext/main/CLAUDE.mdgit clone --depth 1 https://github.com/MinistryPlatform-Community/MPNextWrote 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/ministryplatform-community/mpnext/claude-md)<a href="https://agentmods.dev/instructions/ministryplatform-community/mpnext/claude-md"><img src="https://agentmods.dev/badge/instructions/ministryplatform-community/mpnext/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.
<a href="https://agentmods.dev/instructions/ministryplatform-community/mpnext/claude-md"><img src="https://agentmods.dev/badge/instructions/ministryplatform-community/mpnext/claude-md.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 | $0.06329 | $0.06329 |
| Opus 5.5 | $0.02532 | $0.02532 |
| Sonnet 5.5 | $0.01266 | $0.01266 |
| Haiku 4.5 | $0.00633 | $0.00633 |
Grade A, and why
MPNext 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 28d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - MPNext Development Guide
This guide provides essential information for AI assistants (like Claude) working on the MPNext project.
Ministry Platform Data Safety — MANDATORY
NEVER delete, update, or create records in Ministry Platform without explicit user confirmation first. No exceptions. No agents. No scripts. No "cleanup" operations. No "it's just one record." No "it's obviously safe."
Ministry Platform is a shared production database containing real church member data — contacts, communications, subscriptions, donations, groups, events. Unauthorized writes can affect thousands of people.
Before ANY write operation (DELETE, UPDATE, INSERT, or any API call that modifies data — including deleteTableRecords, updateTableRecords, createTableRecords, stored procedures that mutate state, or any HTTP POST/PUT/DELETE to the MP API):
- Stop. Do not execute the operation.
- Show the user exactly what will be affected: the table name, the record IDs, the fields that will change, and the old → new values where applicable.
- Wait for the user to explicitly say yes before proceeding.
- If the user says no, do not retry or suggest alternatives unless asked.
Read-only operations are always fine — SELECT queries, GET requests, getTableRecords calls. Only writes require confirmation.
This rule applies to:
- The main agent
- All subagents and background agents
- All general-purpose, Explore, and Plan agents
- All one-off scripts (e.g.,
npx tsxscripts) - All automated cleanup, migration, or fix operations
- All hooks and scheduled tasks
There are zero exceptions. If you think "this is obviously safe and I don't need to ask," you are wrong. Ask anyway.
Commands
- Dev:
npm run dev(Next.js dev server) - Build:
npm run build(production build with Turbopack, runs type checking) - Lint:
npm run lint(ESLint CLI —next lintwas removed in Next.js 16) - Generate MP Types:
npm run mp:generate:models(generates TypeScript types + Zod schemas from Ministry Platform API, cleans output directory first) - Generate MP Types (custom):
npm run mp:generate(same generator, no preset flags — pass your own) - Generate MP Stored Procs:
npm run mp:generate:storedprocs(regenerates.claude/references/ministryplatform.storedprocs.md) - Tests:
npm test(Vitest in watch mode),npm run test:run(single run),npm run test:coverage(with coverage — thresholds are enforced, see Testing),npm run test:scripts(only thescripts/project) - Prerender check:
npm run build:check-prerender(afternpm run build; fails if any route other than/_not-foundand/_global-errorwas prerendered — a nonce-less static page breaks under the CSP) - Setup:
npm run setup(interactive project setup wizard),npm run setup:check(validate setup without changes) - Dependencies:
npm run deps:relock(regeneratepackage-lock.json— the only supported way),npm run deps:verify(check it for platform drift)
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.
- 28d ago Changed · +16 lines · +1,071 tokens per session 6ad9a535a519
- 29d ago Changed · +3 lines · +235 tokens per session 05c80f05b779
- 1mo ago Changed · +23 lines · +1,445 tokens per session cc75f7ed2e51
- 1mo ago First seen · 255 lines · 3,578 tokens per session scan A 1625aa33ff45
MPNext CLAUDE.md is an instructions file published in the GitHub repository MinistryPlatform-Community/MPNext (14 stars, last pushed 7d ago), licensed MIT. It adds 6,329 tokens to every session, about $0.0253 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.