mnemon-memory-mcp: Instructions file for Claude Code

CLAUDE.md

mnemon-memory-mcp CLAUDE.md is an instructions file for Claude Code from nikitacometa/mnemon-memory-mcp. It costs 2,115 tokens per session, scanned A, original, MIT.

Project instructions for Mnemon, a local memory service for AI agents that stores information in SQLite and supports full-text search. SQLite is a database stored in a file, and FTS5 is its feature for searching text efficiently.

In plain words
What is it for?
Use them when building or testing the memory MCP server, importing a knowledge base, running its JSON-RPC smoke test, or working with its task board.
Why use it?
They document how the service is built, tested, started, and loaded with Markdown knowledge-base files. They also explain where its shared task board and local knowledge base are kept.

Instructions file for Claude Code

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

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/nikitagorokhov/dev/mnemon/mnemon-mcp/dist/index.js.

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikitacometa/mnemon-memory-mcp/claude-md.svg)](https://agentmods.dev/instructions/nikitacometa/mnemon-memory-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nikitacometa/mnemon-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nikitacometa/mnemon-memory-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,115 This file is loaded in full into every session.
When invoked 2,115 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02115 $0.02115
Opus 5 $0.01058 $0.01058
Sonnet 5 $0.00423 $0.00423
Haiku 4.5 $0.00212 $0.00212

Measured 6d ago against content hash 60af5c27da81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mnemon-memory-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 6d 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 · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mnemon-mcp

MCP server providing persistent layered memory for AI agents. SQLite + FTS5 backend, zero-cloud, stdio transport.

Part of the Mnemon ecosystem. KB lives in ~/dev/mnemon/mnemon-kb. Task board shared with KB: ~/dev/mnemon/mnemon-kb/tasks/BOARD.md (T-NNN IDs).

Commands

npm run build      # compile TypeScript → dist/
npm run dev        # run via tsx (no build needed)
npm start          # run compiled dist/index.js (blocks on stdio — see Smoke Test)
npm test           # vitest (272 tests: 23 md-parser + 16 kb-import + 28 date-extractor + 48 validation + 133 integration + 8 embedder + 6 MCP dispatch + 5 http + 5 hybrid RRF)
npm run import:kb  # import mnemon-kb markdown → SQLite (skip unchanged)

Full re-import (ignore hashes, rewrite all):

npx tsx src/import/cli.ts --kb-path ~/dev/mnemon/mnemon-kb --force

Smoke test (verify server responds to JSON-RPC):

echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | node dist/index.js

Tech Stack

Tool Version Purpose
TypeScript 5.9 Strict mode, NodeNext modules
better-sqlite3 12.6 Synchronous SQLite (ideal for MCP stdio)
@modelcontextprotocol/sdk 1.27 MCP server framework
zod 4.3 Runtime input validation
snowball-stemmer.jsx 0.2.3 Russian/English stemming
vitest 3.2 Test runner
tsx 4.21 TypeScript execution without build step

Architecture

src/
  index.ts              MCP server entry (stdio transport, tool dispatch)
  index-http.ts         HTTP transport entry (StreamableHTTP, Bearer auth)
  db.ts                 SQLite schema, migrations, indexes, FTS5 triggers
  types.ts              TypeScript types (mirrors SQLite schema)
  tools/
    memory-add.ts       Insert memory, auto-supersede on source_file match
    memory-search.ts    FTS5 search with layer/scope/date filtering, recency boost, query-centered snippets
    memory-update.ts    In-place update or superseding chain
    memory-inspect.ts   Layer stats or single-memory history trace
    memory-export.ts    Export to json/markdown/claude-md with layer/scope/date filters
    memory-health.ts    Diagnostic report + optional expired entry cleanup
    session.ts          Session lifecycle: start, end, list
  import/
    cli.ts              CLI entry for KB import
    kb-config.ts        Import routing rules (which files → which layer)
    kb-import.ts        Bulk import engine (hash-based dedup)
    md-parser.ts        Markdown → memory records splitter
    __tests__/
      md-parser.test.ts 14 unit tests

Read the full file on GitHub · 182 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. 6d ago First seen · 182 lines · 2,115 tokens per session scan A 60af5c27da81

Subscribe to this mod's changes

mnemon-memory-mcp CLAUDE.md is an instructions file published in the GitHub repository nikitacometa/mnemon-memory-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 2,115 tokens to every session, about $0.0106 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 · 5,182 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

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