Borrowing it
Nothing to install: this file belongs to marc-shade/enhanced-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.
curl -O https://raw.githubusercontent.com/marc-shade/enhanced-memory-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/marc-shade/enhanced-memory-mcpWrote 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/marc-shade/enhanced-memory-mcp/claude-md)<a href="https://agentmods.dev/instructions/marc-shade/enhanced-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marc-shade/enhanced-memory-mcp/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.
<a href="https://agentmods.dev/instructions/marc-shade/enhanced-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marc-shade/enhanced-memory-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02780 | $0.02780 |
| Opus 5.5 | $0.01112 | $0.01112 |
| Sonnet 5.5 | $0.00556 | $0.00556 |
| Haiku 4.5 | $0.00278 | $0.00278 |
Grade A, and why
enhanced-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 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.
How it starts
The opening of the file, as written. The whole thing — 233 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.
Overview
Enhanced Memory MCP Server - persistent, compressed, searchable memory for AI
agents. SQLite storage behind a single-owner Unix-socket daemon, 4-tier
architecture, Git-like versioning, and layered RAG retrieval. 206 tools
listed over stdio from the repo venv with the optional backends installed
(measured 2026-08-26 at 141e00f, identical under the default and full
ENHANCED_MEMORY_SURFACE: the surface stamps front-door _meta, it does not
change registration). 192 tools with only requirements.txt installed
(fresh Python 3.12 venv, same day, same commit; the re-ranking, hybrid/NMF
and OmniMEM groups log a skip reason). Any tool-count claim without its
environment stated is underspecified.
Figures in this file were measured at commit 99dc95e; re-measure before
citing them elsewhere.
Build & Test Commands
setup/setup.sh # venv, deps, .env, database dir (idempotent)
setup/bin/memory-db-daemon.sh & # the daemon; nothing works without it
./healthcheck.sh # post-install gate: real write/read/cleanup round trip
# Functional suite (needs the daemon). Judge it by EXIT CODE, not pass count:
# with no ENHANCED_MEMORY_*/MEMORY_DB_* vars set it builds its own sandbox and
# runs everything; with them set it runs operator-directed and skips the checks
# that describe a sandbox it did not create. Measured on one machine at one
# commit: 106 isolated / 102 operator-directed, both exit 0. The run prints its
# own mode and names what it skipped.
python3 comprehensive_test.py
# Developer suite (needs: pip install -r dev-requirements.txt).
# 164 passed at 99dc95e.
python -m pytest tests/
# RAG integration suite - registration and class-level, no daemon needed.
# 22/22 at 99dc95e, verified under an isolated ENHANCED_MEMORY_DIR.
python3 test_rag_integration_comprehensive.py
Store-safety warning: test_agi_phase2.py, test_agi_phase3.py,
and test_agi_phase4.py operate on whatever
database the environment resolves - on a configured machine that is the REAL
store. Run them only with ENHANCED_MEMORY_DIR pointed at a scratch
directory. (The pytest suite under tests/ is isolated by its conftest; these
standalone scripts are not.)
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 · 233 lines · 2,780 tokens per session scan A 823aafce2855
enhanced-memory-mcp CLAUDE.md is an instructions file published in the GitHub repository marc-shade/enhanced-memory-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,780 tokens to every session, about $0.0111 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.
enhanced-memory-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| enhanced-memory-mcp CLAUDE.mdmarc-shade/enhanced-memory-mcp | Instructions file | 2 | 2mo ago | MIT | A | 2,780 | 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 |