Borrowing it
Nothing to install: this file belongs to feng111222-113/mcp-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/feng111222-113/mcp-memory/main/CLAUDE.mdgit clone --depth 1 https://github.com/feng111222-113/mcp-memoryWrote 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.
[](https://agentmods.dev/instructions/feng111222-113/mcp-memory/claude-md)<a href="https://agentmods.dev/instructions/feng111222-113/mcp-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/feng111222-113/mcp-memory/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01136 | $0.01136 |
| Opus 5 | $0.00568 | $0.00568 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
mcp-memory 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 83 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.
Build / Test Commands
# Run all tests (sequential)
bun run test.mjs && bun run test-dedup.mjs && bun run test-compaction.mjs
# Run individual test
bun run test.mjs # smoke test (save/recall/stats/list)
bun run test-dedup.mjs # dedup: verify 3 saves → 1 doc
bun run test-compaction.mjs # compaction: single-file append mode
# Type-check only (no emit)
bun run tsc
# Start server local dev
bun run src/index.ts
# Dry-run publish
.\scripts\publish.ps1
# Actual publish
.\scripts\publish.ps1 -Execute
Tests spawn the server as a subprocess, talk stdio JSON-RPC, then clean up .test-memory/. No test framework — pure .mjs scripts.
Architecture
MCP Memory Server — cross-session persistent memory for AI coding assistants (OpenCode / Claude Code). Markdown files as the source of truth + SQLite FTS5 for search.
Data flow
Agent (LLM) ↔ stdin/stdout (JSON-RPC) ↔ src/index.ts (MCP server) ↔ src/store.ts (MemoryStore) ↔ .md files on disk + SQLite FTS5 index
Key source files
| File | Role |
|---|---|
src/index.ts |
MCP server setup, 8 tool handlers, background compaction poller (periodic fetch to OpenCode API) |
src/store.ts |
MemoryStore class: save, search (FTS5 BM25), list, delete, reconcile, stats. LRU compaction body cache, file-write serialization queue. |
src/paths.ts |
Path parsing regex (/memory/{scope}/{scope_id?}/{key}.md), safe path construction with traversal guards, resolveProjectId() for stable project hashes |
src/types.ts |
All TypeScript interfaces: Scope, MemoryType, SaveInput, SearchInput (now with search_mode), MemoryEntry, etc. |
src/fts-query.ts |
buildFtsQuery() — free-text → FTS5 MATCH, tokenize by [\p{L}\p{N}_]+, OR-join for recall, quoted for safety |
src/cjk.ts |
addCjkSpacing() / removeCjkSpacing() — insert spaces between CJK chars so FTS5 unicode61 tokenizer indexes each character individually |
src/embedder.ts |
Optional Ollama embedding integration. Embedder class with isAvailable(), embed() (nomic-embed-text, 768d), cosineSimilarity(). Async, fail-soft — Ollama down → pure FTS5. |
src/embedder.ts |
Ollama embedding (nomic-embed-text, 768d). Embedder class: isAvailable(), embed(), cosineSimilarity(). Async fail-soft. |
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.
- 5d ago First seen · 83 lines · 1,136 tokens per session scan A 318509e180b9
mcp-memory CLAUDE.md is an instructions file published in the GitHub repository feng111222-113/mcp-memory (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,136 tokens to every session, about $0.0057 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.
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.
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.
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).
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).
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.
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.