What is Unconventional-thinking CLAUDE.md?

Repository instructions for a TypeScript Model Context Protocol (MCP) server that creates and tracks unconventional problem-solving thoughts. They explain the project’s purpose, files, architecture, and approach to keeping agent context small.

Use them when modifying the server, its TypeScript build, persistent thoughts file, configuration, or context-handling behavior.

They help an agent understand where the server logic and stored thoughts live, and how the project is intended to manage conversation context.

How stagsz/Unconventional-thinking configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to stagsz/Unconventional-thinking. 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/stagsz/Unconventional-thinking/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/stagsz/Unconventional-thinking

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/stagsz/unconventional-thinking/claude-md/github.svg)](https://agentmods.dev/instructions/stagsz/unconventional-thinking/claude-md)

Your own site

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

Per session 3,811 This file is loaded in full into every session.

When invoked 3,811 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	$0.03811	$0.03811
Opus 5.5	$0.01524	$0.01524
Sonnet 5.5	$0.00762	$0.00762
Haiku 4.5	$0.00381	$0.00381

Measured 2mo ago against content hash e5ca94c874aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Unconventional-thinking 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 · 430 lines

How it starts

The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - AI Assistant Development Guide

This document provides comprehensive guidance for AI assistants working with the Unconventional Thinking Server codebase.

Project Overview

Name: Unconventional Thinking Server (unreasnable-thinker-server) Version: 0.3.0 Type: MCP (Model Context Protocol) Server — spec 2025-11-25, SDK 1.27.1 Purpose: A context-efficient tool for generating and tracking unconventional, boundary-breaking problem-solving thoughts

This is a TypeScript-based MCP server that implements an unconventional thinking system optimized for context space savings based on Anthropic's latest MCP architecture patterns. The server demonstrates recommended patterns for reducing context overhead by 98.7%.

Repository Structure

Unconventional-thinking/
├── src/
│   └── index.ts              # Main server implementation (all logic in single file)
├── .thoughts/
│   └── thoughts.json         # Persistent storage for generated thoughts
├── build/                    # Compiled JavaScript output (gitignored)
├── node_modules/             # Dependencies (gitignored)
├── package.json              # Project metadata and scripts
├── tsconfig.json             # TypeScript configuration
├── .gitignore                # Git ignore patterns
├── README.md                 # User-facing documentation
├── LICENSE                   # MIT License
└── CLAUDE.md                 # This file - AI assistant guide

Core Architecture Principles

1. Context-Efficient Design

The server is built around minimizing token usage in Claude conversations:

Resources API: Thought content stored as resources (thought://[id]), loaded only when explicitly needed
Metadata-First Returns: Tools return only IDs, URIs, and brief metadata (not full content)
Server-Side Filtering: search_thoughts filters locally instead of passing unfiltered data to Claude
Persistent Storage: File-based storage in .thoughts/ directory prevents in-memory bloat

Read the full file on GitHub · 430 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 · 430 lines · 3,811 tokens per session scan A e5ca94c874aa

Subscribe to this mod's changes

Unconventional-thinking CLAUDE.md is an instructions file published in the GitHub repository stagsz/Unconventional-thinking (30 stars, last pushed 5mo ago), licensed MIT. It adds 3,811 tokens to every session, about $0.0152 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.

Building agents

Unconventional-thinking CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Unconventional-thinking CLAUDE.mdstagsz/Unconventional-thinking	Instructions file	30	5mo ago	MIT	A	3,811	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

Unconventional-thinking: Instructions file for Claude Code