mcp-paprika: Instructions file for Claude Code

CLAUDE.md

mcp-paprika CLAUDE.md is an instructions file for Claude Code from bojanrajkovic/mcp-paprika. It costs 2,875 tokens per session, scanned A, original, MIT.

A project guide for AI coding agents working on the mcp-paprika recipe-manager server. It points agents to the project structure, technology choices, commands, and documentation.

In plain words
What is it for?
Use it when an agent needs to understand the project, run development commands, or update the right architecture and documentation files.
Why use it?
It gives agents a consistent map of the codebase and tells them where detailed information belongs.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is bojanrajkovic/mcp-paprika's own configuration. It tells Claude Code how to work on mcp-paprika 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 mcp-paprika configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bojanrajkovic/mcp-paprika. 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/bojanrajkovic/mcp-paprika/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bojanrajkovic/mcp-paprika

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 mcp-paprika CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bojanrajkovic/mcp-paprika/claude-md"><img src="https://agentmods.dev/badge/instructions/bojanrajkovic/mcp-paprika/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,875 This file is loaded in full into every session.
When invoked 2,875 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 $0.02875 $0.02875
Opus 5 $0.01437 $0.01437
Sonnet 5 $0.00575 $0.00575
Haiku 4.5 $0.00287 $0.00287

Measured 12d ago against content hash 303182bee8d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-paprika 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 12d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI Agent Index

Keep this file lean. It is the project-wide pointer index for agents. Detailed docs live under docs/; the human dev workflow lives in CONTRIBUTING.md; the rules that govern the doc system live in docs/documentation-system.md. When you change a feature, update its architecture doc or the relevant directory CLAUDE.md, not this index.

Project

mcp-paprika — an MCP server for the Paprika recipe manager. Two transports, selected by MCP_TRANSPORT: stdio (default; unauthenticated local pipe for Claude Desktop/Code, Cursor, mcp-cli) and Streamable HTTP (remote clients; OAuth 2.1 + OIDC delegation). See docs/architecture.md for the shape and docs/adr/ for the decisions behind it.

Tech stack

TypeScript 6 (ESM, @tsconfig/strictest) on Node.js 24 (mise-managed), pnpm via corepack. MCP via @modelcontextprotocol/sdk; HTTP via hono; validation via zod; errors via neverthrow; resilience via cockatiel; logging via pino; image normalization via sharp. The full dependency set lives in package.json and is not re-listed here. Ships as a distroless container (3-stage Dockerfile).

Commands

pnpm dev · pnpm build · pnpm test · pnpm typecheck · pnpm lint · pnpm format. Full reference and dev setup: CONTRIBUTING.md.

Fresh git worktree: run pnpm install --ignore-scripts once before anything else, or lefthook's prepare step (lefthook install) makes every pnpm / git commit / git push fail (mechanism in CONTRIBUTING.md).

The source tree is a typed composition kernel over self-registering domain modules (ADR-0009).

  • src/index.ts, src/transport/ — transport dispatch and the stdio / Streamable-HTTP entry points; each transport assembles the kernel Infra and calls buildKernel.
  • src/kernel/ — the composition substrate: defineModule/register, the declaration-merged DomainRegistry, buildKernel (dependency-ordered construction, the sync driver, boot phases), and the generated module barrel. See src/kernel/CLAUDE.md and docs/adr/0009-domain-isolated-tool-modules-kernel.md.
  • src/domains/<domain>/ — one directory per cohesive domain (recipe, grocery, menu, meal, meal-type, pantry, aisle, meal-planner): its module.ts + api.ts, its ids.ts branded-UID leaf (kind-safe FKs; imports nothing but zod, one owning leaf per brand — ADR-0016), its defining entity's types.ts/store.ts at the root (a disk.ts only when the cache carries behavior, e.g. recipe's), any additional owned entity in an <entity>/ subdir, and co-located tools/, resources/, and the reconcile (sync.ts, or a syncs/ dir when there are several), with tests beside them. See src/domains/CLAUDE.md.
  • src/features/<feature>/ — kernel modules that are optional features, not data domains: semantic search (discover) and AI photo generation (photo-gen). See src/features/CLAUDE.md.
  • src/shared/ — the few genuinely cross-cutting tool helpers: the MCP textResult envelope + the uid-or-text lookup abstraction (tools.ts), the SSRF-guarded image fetch (photo-fetch.ts), and the resourceNotFound boundary helper (resources.ts). See src/shared/CLAUDE.md.
  • src/server/ — the composition root's remaining pieces: the Notifier abstraction, buildInfraBase + buildBrandedServer, the background sync loop, and the cross-entity index-event seam. See src/server/CLAUDE.md.
  • src/paprika/ — the Paprika cloud-sync HTTP client and syncReplaceAllEntity (the shared per-module reconcile helper). Wire formats: docs/wire-format.md.
  • src/telemetry/ — the OpenTelemetry substrate: the dual-path bootstrap + SDK assembly, vendored semconv constants, the shared instruments, and the Result-native span helper. Recording happens at the seams, not here. See src/telemetry/CLAUDE.md and ADR-0018.
  • src/entity/ — the shared EntityStore base class. See src/entity/CLAUDE.md.
  • src/cache/ — the persistence layer: per-entity DiskCaches (plus the auth-only buildAuthCaches), keeping the in-memory stores warm across restarts. See src/cache/CLAUDE.md.
  • src/auth/ — the OAuth 2.1 authorization-server surface; loaded only under the HTTP transport.
  • src/utils/ — config (Zod schema), logging, resilience, dates, XDG paths.
  • scripts/, docs/wire-captures/, Dockerfile, .github/workflows/ — tooling, sanitized wire captures, container build, CI.

Read the full file on GitHub · 80 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. 12d ago First seen · 80 lines · 2,875 tokens per session scan A 303182bee8d7

Subscribe to this mod's changes

mcp-paprika CLAUDE.md is an instructions file published in the GitHub repository bojanrajkovic/mcp-paprika (2 stars, last pushed today), licensed MIT. It adds 2,875 tokens to every session, about $0.0144 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.

Related

Other instructions, from other repositories

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 · 7,126 tokens

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

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

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