agentmods.dev

snapshot-mcp-server: Instructions file for Claude Code

CLAUDE.md

snapshot-mcp-server CLAUDE.md is an instructions file for Claude Code from WhenMoon-afk/snapshot-mcp-server. It costs 1,548 tokens per session, scanned A, original, MIT.

A project instruction file for Snapshot MCP Server, a tool that saves and restores conversation state for AI coding clients. It documents the project, its commands, and how to build, run, test, and install it.

In plain words
What is it for?
Use it when developing or maintaining this TypeScript and Node.js server, including building it, running its tests or server process, and packaging or installing it.
Why use it?
It gives an agent the repository-specific context needed to work consistently, instead of making it rediscover the project structure and commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is WhenMoon-afk/snapshot-mcp-server's own configuration. It tells Claude Code how to work on snapshot-mcp-server 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 snapshot-mcp-server configures →

not rated 0repo 7mo ago A scan 1,548 tokens original MIT
View source ↗ WhenMoon-afk/snapshot-mcp-server npmjs.com
Reuse

Borrowing it

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

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 snapshot-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/whenmoon-afk/snapshot-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/whenmoon-afk/snapshot-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/whenmoon-afk/snapshot-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/whenmoon-afk/snapshot-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,548 This file is loaded in full into every session.
When invoked 1,548 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 $0.01548 $0.01548
Opus 5 $0.00774 $0.00774
Sonnet 5 $0.00310 $0.00310
Haiku 4.5 $0.00155 $0.00155

Measured 7d ago against content hash 8860dd06c4e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

snapshot-mcp-server 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 7d 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 · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 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

Snapshot MCP Server is a Model Context Protocol (MCP) server that enables token-efficient conversation state management for Claude Desktop, Claude Code, Cursor, and other MCP clients. It allows users to save snapshots of conversations at key milestones and resume work across sessions without token bloat.

Tech Stack: TypeScript + MCP SDK 1.0.4 + SQLite (better-sqlite3) + Node.js 18+

Development Commands

Build & Run

  • Build: npm run build - Compiles TypeScript to JavaScript (output: dist/)
  • Watch mode: npm run watch - Continuous compilation during development
  • Install locally: npm run prepare (auto-runs on npm install)
  • Test the server: npm run build && node dist/index.js (runs MCP server on stdio)

Package & Installation

  • Install from package: npx @whenmoon-afk/snapshot-mcp-server - Runs install.js which:
    1. Detects OS and Claude Desktop config location
    2. Creates database directory in platform-specific location
    3. Updates claude_desktop_config.json with server configuration
    4. Uses node directly for local installs (Windows uses cmd /c npx for published installs)

Codebase Architecture

Core Structure

  • src/index.ts - MCP server bootstrap

    • SnapshotMCPServer class: initializes MCP server, registers tool handlers, manages cleanup
    • Defines 4 tools: save_snapshot, load_snapshot, list_snapshots, delete_snapshot
    • Handles tool requests and generates MCP-compliant responses
    • Database initialized at constructor; cleanup on SIGINT/SIGTERM

  • src/database.ts - SQLite data layer

    • SnapshotDatabase class: manages schema, CRUD operations, query logic
    • Snapshot interface: database record structure with continuation_prompt for token efficiency
    • SaveSnapshotInput interface: API input (accepts string or structured context)
    • StructuredContext interface: flexible schema for organizing context (files, decisions, blockers, code_state, custom fields)

Read the full file on GitHub · 131 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. 7d ago First seen · 131 lines · 1,548 tokens per session scan A 8860dd06c4e5

Subscribe to this mod's changes

snapshot-mcp-server CLAUDE.md is an instructions file published in the GitHub repository WhenMoon-afk/snapshot-mcp-server (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,548 tokens to every session, about $0.0077 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.

Memory and contextclaudecontext-managementlocal-firstmcpsnapshots
Related

Other instructions, from other repositories

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

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

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

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

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