Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/nathannorman/claude-memory/claude-mdgit clone --depth 1 https://github.com/NathanNorman/claude-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/nathannorman/claude-memory/claude-md)<a href="https://agentmods.dev/instructions/nathannorman/claude-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/nathannorman/claude-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 | $0.04509 | $0.04509 |
| Opus 5 | $0.02254 | $0.02254 |
| Sonnet 5 | $0.00902 | $0.00902 |
| Haiku 4.5 | $0.00451 | $0.00451 |
Grade A, and why
claude-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 — 295 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.
What This Is
claude-memory is a persistent memory system for Claude Code, implemented as an MCP server. It has three main subsystems:
- Python MCP server (
src/unified_memory_server.py) — The runtime that Claude Code connects to. Handles search, read, write, and status tools via stdio. This is what runs in production. - Node.js indexer (
src/indexer.tsand friends) — Batch indexer that scans conversation archives, chunks content, generates embeddings, and maintains the SQLite search index. Runs on-demand via reindex. - Webhook pipeline (
src/webhook_server.py,src/index_worker.py,src/mirror_manager.py) — FastAPI server that receives GitHub push webhooks and incrementally re-indexes changed files via bare git mirrors.
Build & Development Commands
# Node.js indexer
npm install # Install dependencies
npm run build # Build MCP server + doctor CLI (esbuild, single-file ESM bundles → dist/)
npm run build:doctor # Build doctor CLI only
npm run typecheck # TypeScript type checking (tsc --noEmit)
npm test # tsc compile + integration tests (node --test)
# Reindex (rebuild search index from memory files + conversation archives)
npx tsc && node dist/reindex-cli.js # Backs up DB to ~/.claude-memory/backups/ before reindexing
# Python MCP server (uses venv at ~/.claude-memory/graphiti-venv/)
~/.claude-memory/graphiti-venv/bin/python3 src/unified_memory_server.py # Run directly
python3 -c "import py_compile; py_compile.compile('src/unified_memory_server.py', doraise=True)" # Syntax check
# Python tests (pytest-style, run individually)
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_conversation_parser.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_code_chunker.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_build_parser.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_cross_repo_deps.py -v
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_turboquant_backend.py -v
# Or run all Python tests at once:
~/.claude-memory/graphiti-venv/bin/python3 -m pytest scripts/test_*.py -v
# Database diagnostics
node dist/doctor-cli.js # Diagnose (read-only)
node dist/doctor-cli.js --fix # Diagnose and repair
# Retrieval benchmarks
~/.claude-memory/graphiti-venv/bin/python3 benchmarks/retrieval_bench.py
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 · 295 lines · 4,509 tokens per session scan A 97b5537abbe7
claude-memory CLAUDE.md is an instructions file published in the GitHub repository NathanNorman/claude-memory (1 stars, last pushed 4mo ago), licensed MIT. It adds 4,509 tokens to every session, about $0.0225 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
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).