What is retrieval-augmented-thinking CLAUDE.md?

Instructions for a retrieval-augmented thinking tool named RAT. Retrieval-augmented thinking means using retrieved context while forming, checking, and revising lines of reasoning.

Running structured reasoning steps, testing hypotheses, exploring alternatives, proposing revisions, and marking verification points.

They explain how to install and connect the tool so an agent can preserve context while exploring and checking multiple hypotheses.

retrieval-augmented-thinking CLAUDE.md — Instructions file for coding agents by stat-guy: Instructions for a retrieval-augmented thinking to

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/stat-guy/retrieval-augmented-thinking/claude-md

Clone the repo

git clone --depth 1 https://github.com/stat-guy/retrieval-augmented-thinking

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/stat-guy/retrieval-augmented-thinking/claude-md.svg)](https://agentmods.dev/instructions/stat-guy/retrieval-augmented-thinking/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/stat-guy/retrieval-augmented-thinking/claude-md"><img src="https://agentmods.dev/badge/instructions/stat-guy/retrieval-augmented-thinking/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,253 This file is loaded in full into every session.

When invoked 1,253 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01253	$0.01253
Opus 5	$0.00626	$0.00626
Sonnet 5	$0.00251	$0.00251
Haiku 4.5	$0.00125	$0.00125

Measured 3d ago against content hash 3b5618ab7c1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retrieval-augmented-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 3d 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 · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAT (Retrieval Augmented Thinking) MCP Tool

Tool Name

rat

Description

A context-aware reasoning system that orchestrates structured thought processes through dynamic trajectories. Implements iterative hypothesis generation and validation cycles while preserving context coherence across non-linear reasoning paths.

Installation

Simple 3-Step Process

git clone https://github.com/stat-guy/retrieval-augmented-thinking.git
cd retrieval-augmented-thinking
npm install -g .

Verify Installation

Test before configuring Claude Desktop:

npx mcp-server-rat-node --help

Success indicator: If you see RAT MCP Server (Node.js) running on stdio, installation is complete!

Claude Desktop Configuration

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "rat": {
      "command": "npx",
      "args": ["mcp-server-rat-node"]
    }
  }
}

Restart Claude Desktop after adding the configuration.

Parameters

Required Parameters

thought (string): Structured reasoning step content
- Primary analysis chains
- Hypothesis formulation/validation
- Branch exploration paths
- Revision proposals
- Context preservation markers
- Verification checkpoints
nextThoughtNeeded (boolean): Signal for continuation of reasoning chain
- true: Continue to next thought
- false: Complete current reasoning trajectory
thoughtNumber (integer, min: 1): Position in current reasoning trajectory
- Sequential numbering starting from 1
- Must be ≤ totalThoughts unless needsMoreThoughts is true
totalThoughts (integer, min: 1): Dynamic scope indicator (adjustable)
- Initial estimation of reasoning steps needed
- Can be expanded via needsMoreThoughts

Optional Parameters

isRevision (boolean, default: false): Marks recursive refinement steps
revisesThought (integer): References target thought number for refinement
branchFromThought (integer): Indicates parallel exploration paths source
branchId (string): Context identifier for parallel reasoning chains
needsMoreThoughts (boolean, default: false): Signals scope expansion requirement

Read the full file on GitHub · 174 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.

3d ago First seen · 174 lines · 1,253 tokens per session scan A 3b5618ab7c1b

Subscribe to this mod's changes

retrieval-augmented-thinking CLAUDE.md is an instructions file published in the GitHub repository stat-guy/retrieval-augmented-thinking (24 stars, last pushed 1y ago), licensed MIT. It adds 1,253 tokens to every session, about $0.0063 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 2026-08-30.

Data and AI RAG and vectors

GPT-RAG AGENTS.md

Instructions for Azure/GPT-RAG, covering gpt-rag agent operating contract, priority, what this repository is, repository boundaries and how to work.

Azure/GPT-RAG · 1,538 tokens

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 207 tokens

retrieval-augmented-thinking CLAUDE.md