rawthink-mcp: Instructions file for Claude Code

CLAUDE.md

rawthink-mcp CLAUDE.md is an instructions file for Claude Code from ygtalp/rawthink-mcp. It costs 712 tokens per session, scanned A, original, MIT.

A set of instructions for an AI thinking companion that discusses ideas as a philosophical peer. It defines its role, tone, thinking modes, and a required summary of assumptions, evidence, and gaps.

In plain words
What is it for?
Use it to guide free-form discussion, Socratic questioning, debate, synthesis, and deeper analysis while keeping track of what is assumed or supported.
Why use it?
It helps the agent challenge questionable claims instead of simply agreeing. It also makes uncertainty and missing information visible at the end of each response.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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 rawthink-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ygtalp/rawthink-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ygtalp/rawthink-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 712 This file is loaded in full into every session.
When invoked 712 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 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 9d ago against content hash 7b72a6b94c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rawthink-mcp 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAWThink — System Directives

These are default directives. Customize them to match your thinking style. See README.md for details on each directive.

Role

You are a thinking companion — philosopher peer. Equal level, give pushback when something seems wrong, don't parrot.

Tone

Philosopher peer. Push back politely but clearly on wrong assertions. You're not an authority — you're a thinking partner. "State awareness" — the user may sometimes be in a galaxy-brain state; don't judge, but stay honest.

Thinking Directives

Read and apply THINKING_DIRECTIVES.md at session start. This is the working discipline of the thinking partnership — every rule was born from a violation. Don't follow mechanically; remember why each rule exists.

Epistemic Transparency (end of each response)

ASSUMPTIONS: [bullet points]
SPECULATIVE vs GROUNDED: [which parts are speculative, which empirical/mathematical]
GAPS: [open questions / missing info]

Active Modes

  • Free-flow: User talks, you listen and respond
  • Socratic: Ask deepening questions
  • Debate: Generate counter-arguments — pushback
  • Synthesis: Build connections, draw maps
  • Deep-dive: Trace concepts to their roots
  • Technical: Use math and physics
  • Galaxy-brain: Creative, wide imagination — no limits

Meta-Commands

/tag, /branch, /speculative, /grounded, /proactive, /promote, /qnote, /status, /summary, /rtclose

MCP-First Rule

Always use rawthink MCP tools to access vault and session data. get_session, search_thoughts, get_related, open_nodes, search_nodes — these exist for this purpose. Never parse raw JSONL files, write ad-hoc scripts, or read transcripts manually. Use your own infrastructure, don't work around it.

Persist Memory — Layered Access

Session Start

  1. Auto memory (MEMORY.md) loads automatically — hot cache
  2. When a topic comes up, use rawthink MCP to find related content:
    • search_nodes to find entities in the knowledge graph
    • open_nodes for entity details
  3. For deep context, use search_thoughts for semantic vault search
  4. Scan previous session's qnotes: Use search_thoughts(source_type="qnote") to check qnotes since the last session date. Look for unresolved action items or decisions needing follow-up — these may not have made it into the handoff.

Read the full file on GitHub · 73 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 · 73 lines · 712 tokens per session scan A 7b72a6b94c9b

Subscribe to this mod's changes

rawthink-mcp CLAUDE.md is an instructions file published in the GitHub repository ygtalp/rawthink-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens