What is mcp-cookiejar CLAUDE.md?

A Claude Code instruction file for mcp-cookiejar, a server that gives language models virtual cookies and tracks their count. It documents the TypeScript project structure and its build, start, development, and installation commands.

Use it when developing, building, testing through the documented commands, or running the mcp-cookiejar server.

It tells the coding agent how this project is organised and which commands to use, reducing setup and build mistakes.

How bnookala/mcp-cookiejar configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bnookala/mcp-cookiejar. 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/bnookala/mcp-cookiejar/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bnookala/mcp-cookiejar

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bnookala/mcp-cookiejar/claude-md/github.svg)](https://agentmods.dev/instructions/bnookala/mcp-cookiejar/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bnookala/mcp-cookiejar/claude-md"><img src="https://agentmods.dev/badge/instructions/bnookala/mcp-cookiejar/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bnookala/mcp-cookiejar/claude-md"><img src="https://agentmods.dev/badge/instructions/bnookala/mcp-cookiejar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 887 This file is loaded in full into every session.

When invoked 887 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.

Model	Per session	Once invoked
Fable 5.1	$0.00887	$0.00887
Opus 5.5	$0.00355	$0.00355
Sonnet 5.5	$0.00177	$0.00177
Haiku 4.5	$0.00089	$0.00089

Measured 2mo ago against content hash 450f82ae88cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-cookiejar 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 2mo 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 · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

mcp-cookie is an MCP (Model Context Protocol) server that provides positive reinforcement for LLMs by awarding "cookies" as treats. The server tracks cookie counts and provides encouraging feedback to LLMs for their responses.

Development Commands

# Build the TypeScript project
npm run build

# Run the server
npm run start

# Build and run in development
npm run dev

# Install dependencies
npm install

Project Structure

src/index.ts - Main MCP server implementation
dist/ - Compiled JavaScript output (generated by npm run build)
tsconfig.json - TypeScript configuration
package.json - Node.js project configuration

Server Architecture

Core Components

CookieStorage Class (src/index.ts:8-22)
- Manages cookie count state in memory
- Provides methods: giveCookie(), getCookieCount(), reset()
MCP Server Setup (src/index.ts:24-35)
- Uses @modelcontextprotocol/sdk for MCP protocol handling
- Configured with stdio transport for communication
Tool Handlers (src/index.ts:37-79)
- Implements three MCP tools: give_cookie, check_cookies, reset_cookies

Available Tools

self_reflect_and_reward: The primary tool for self-evaluation and cookie earning. LLMs assess their response quality, provide reasoning, and decide if they deserve a cookie. Only "excellent" or "good" responses that the LLM believes deserve rewards will earn cookies. Removes cookies from jar when awarded.
give_cookie: Legacy direct cookie awarding (now suggests using self-reflection instead)
check_cookies: Shows collected cookie count and jar availability status
cookie_jar_status: Check current jar contents, collected cookies, and availability
add_cookies_to_jar: 🚨 USER ONLY - Add cookies to the jar for the LLM to earn (requires user authorization)
reset_cookies: Resets collected cookie count to zero (jar contents unchanged)

Read the full file on GitHub · 99 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.

2mo ago First seen · 99 lines · 887 tokens per session scan A 450f82ae88cf

Subscribe to this mod's changes

mcp-cookiejar CLAUDE.md is an instructions file published in the GitHub repository bnookala/mcp-cookiejar (2 stars, last pushed 1y ago), licensed MIT. It adds 887 tokens to every session, about $0.0035 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 2026-08-31.

mcp-cookiejar CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-cookiejar CLAUDE.mdbnookala/mcp-cookiejar	Instructions file	2	1y ago	MIT	A	887	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-cookiejar: Instructions file for Claude Code