What is acheron-mcp-server CLAUDE.md?

Project instructions for Acheron, a server that lets Claude Chat, Claude Code, and Claude Cowork share saved context. MCP, or Model Context Protocol, is a way for an AI assistant to connect to external tools and data.

Use it when developing or contributing to the Acheron MCP server, including understanding its purpose, project identity, architecture, and Git commit rules.

It addresses the problem of each Claude surface keeping separate knowledge about the user, conversations, files, and work sessions.

How timmx7/acheron-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to timmx7/acheron-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/timmx7/acheron-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/timmx7/acheron-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/timmx7/acheron-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/timmx7/acheron-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/timmx7/acheron-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/timmx7/acheron-mcp-server/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/timmx7/acheron-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/timmx7/acheron-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,957 This file is loaded in full into every session.

When invoked 2,957 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	$0.02957	$0.02957
Opus 5.5	$0.01183	$0.01183
Sonnet 5.5	$0.00591	$0.00591
Haiku 4.5	$0.00296	$0.00296

Measured 2mo ago against content hash 171d91023f62, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

acheron-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 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 · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Acheron MCP Server

Project identity

Author: timmx7
Repository: github.com/timmx7/acheron-mcp-server
Package: acheron-mcp-server (npm)
License: MIT

Git configuration for this project:

git config user.name "timmx7"
git config user.email "<tim's email>"

No other contributors. All commits must be authored by timmx7 only. Do not add co-author trailers or any other attribution metadata to commits.

What is this project?

Acheron is an MCP (Model Context Protocol) server that solves the biggest structural gap in the Claude ecosystem: Chat, Code, and Cowork are three separate surfaces with zero shared context between them.

Claude Chat has memory about the user but cannot touch files or execute code
Claude Code has Auto Memory for code projects but knows nothing about Chat conversations or Cowork sessions
Claude Cowork can act on local files but resets completely every session with no persistent memory at all

Acheron is the missing link. A single MCP server that, once connected, works across all three surfaces. It captures context from any surface and makes it available to all others — a shared persistent brain for all Claude instances.

Why this matters

Cowork's lack of cross-session memory is the most reported user complaint across community forums, blog posts, and GitHub issues
Claude Code Auto Memory is siloed to code projects and inaccessible from Cowork or Chat
Every existing workaround (CLAUDE.md files, context files, Personal Preferences) is manual and fragile
MCP servers are the only technical mechanism that natively crosses all three Claude surfaces
No tool currently provides automated cross-surface context persistence

Architecture overview

See ARCHITECTURE.md for the complete technical design. Summary:

Language: TypeScript (standard for the MCP ecosystem)
Storage: SQLite with FTS5 via better-sqlite3 (fast, zero-config, local-first, single file)
Transport: stdio (local process, no network)
Security model: local-only, no network calls, no telemetry, no data exfiltration, prepared statements only, strict input validation, hardened file permissions

Read the full file on GitHub · 287 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 · 287 lines · 2,957 tokens per session scan A 171d91023f62

Subscribe to this mod's changes

acheron-mcp-server CLAUDE.md is an instructions file published in the GitHub repository timmx7/acheron-mcp-server (7 stars, last pushed 7mo ago), licensed MIT. It adds 2,957 tokens to every session, about $0.0118 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 2026-08-31.

Building agents Memory and context

acheron-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
acheron-mcp-server CLAUDE.mdtimmx7/acheron-mcp-server	Instructions file	7	7mo ago	MIT	A	2,957	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

acheron-mcp-server: Instructions file for Claude Code