mcp-titan: Instructions file for Claude Code

CLAUDE.md

mcp-titan CLAUDE.md is an instructions file for Claude Code from henryhawke/mcp-titan. It costs 784 tokens per session, scanned A, original, MIT.

Repository guidance for working on mcp-titan, a neural memory system for language models exposed through an MCP server. It documents the project, development commands, server commands, and model-training commands.

In plain words
What is it for?
Use it when developing mcp-titan, including type checking, linting, running tests, starting the server, downloading data, or training and testing its model.
Why use it?
It gives a coding agent the repository context and the commands needed to build, check, test, run, clean, and train the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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-titan CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/henryhawke/mcp-titan/claude-md"><img src="https://agentmods.dev/badge/instructions/henryhawke/mcp-titan/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 784 This file is loaded in full into every session.
When invoked 784 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 $0.00784 $0.00784
Opus 5 $0.00392 $0.00392
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 10d ago against content hash 08629f8909ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-titan 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 10d 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 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

This is mcp-titan, a sophisticated neural memory system for LLMs that provides persistent memory capabilities through an MCP (Model Context Protocol) server. The system uses TensorFlow.js for neural computations and implements transformer-based memory mechanisms.

Development Commands

Core Commands

  • bun run build - Compile TypeScript to JavaScript
  • bun run typecheck - Type check without emitting files
  • bun run lint - Run ESLint with zero warnings policy
  • bun run lint:fix - Auto-fix ESLint issues
  • bun test - Run Jest tests with experimental VM modules
  • bun run clean - Remove build artifacts

Model Training Commands

  • bun run train-model - Train the model with default settings
  • bun run train-quick - Quick training for development
  • bun run train-production - Full production training
  • bun run download-data - Download training datasets
  • bun run test-model - Test model functionality

Server Commands

  • bun start - Start the MCP server (production)
  • bun --watch src/index.ts - Development mode with auto-restart

Architecture Overview

Core Components

TitanMemoryServer (src/index.ts) - Main MCP server that registers 16 tools for memory operations including:

  • Model initialization and configuration
  • Forward passes and training steps
  • Memory state management and pruning
  • Checkpoint saving/loading
  • Bootstrap memory from URLs/text
  • Online learning service

TitanMemoryModel (src/model.ts) - Neural memory implementation with:

  • Transformer-XL inspired architecture
  • Hierarchical memory (short-term, long-term, meta)
  • Information-gain based pruning
  • Surprise-based learning
  • Tensor memory management

Key Services:

  • LearnerService (src/learner.ts) - Online learning with replay buffer
  • AdvancedTokenizer (src/tokenizer/) - BPE tokenization and embeddings
  • MemoryPruner (src/pruning.ts) - Intelligent memory pruning
  • VectorProcessor (src/utils.ts) - Text encoding and vector operations

Read the full file on GitHub · 101 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. 10d ago First seen · 101 lines · 784 tokens per session scan A 08629f8909ce

Subscribe to this mod's changes

mcp-titan CLAUDE.md is an instructions file published in the GitHub repository henryhawke/mcp-titan (91 stars, last pushed 2mo ago), licensed MIT. It adds 784 tokens to every session, about $0.0039 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.

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

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 · 7,104 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