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/jthiruveedula/agent-memory-mcp/claude-mdgit clone --depth 1 https://github.com/jthiruveedula/agent-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/jthiruveedula/agent-memory-mcp/claude-md)<a href="https://agentmods.dev/instructions/jthiruveedula/agent-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jthiruveedula/agent-memory-mcp/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 | $0.00483 | $0.00483 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
agent-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 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory MCP — Claude Code Instructions
This project implements a self-improving agent memory server using the Model Context Protocol (MCP).
MCP Server
The agent-memory MCP server is configured in .claude/settings.json and provides persistent, cross-workspace memory for Claude Code.
Available Tools
| Tool | Purpose |
|---|---|
remember |
Store a memory, fact, preference, code pattern, or workflow |
recall |
Search memories by semantic similarity and full-text search |
recall_recent |
List recently accessed/created memories |
remember_correction |
Record a correction, optionally linked to a memory |
remember_tool_outcome |
Log tool call outcomes for recommendation learning |
get_preferences |
Retrieve learned preferences |
set_preference |
Manually set a preference |
get_tool_recommendations |
Get ranked tool recommendations for a task |
get_knowledge_graph |
Explore the knowledge graph around a topic |
reflect |
Run self-improvement analysis (merge duplicates, surface insights) |
update_memory_confidence |
Reinforce or penalize a memory's confidence |
Prompt
A memory-context prompt is available: call it with your current task to inject relevant memories and preferences.
Resources
memory://preferences— all learned preferences as JSONmemory://recent— recent memories as JSONmemory://stats— memory database statistics
Build & Run
npm install
npm run build
node dist/index.js
Configuration
Set AGENT_MEMORY_DIR to change the storage location (default: ~/.agent-memory-mcp).
Set OPENAI_API_KEY to use OpenAI embeddings instead of local hash-based ones.
Project Structure
src/
├── index.ts # Entry point
├── server.ts # MCP server wiring
├── config.ts # Configuration
├── types.ts # Zod schemas & types
├── db/ # SQLite schema, embeddings, MemoryStore
├── graph/ # Knowledge graph extraction
├── learning/ # Preference learning, tool recommender, self-improver
└── tools/ # MCP tool handlers
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 · 61 lines · 483 tokens per session scan A 5a4c97948be1
agent-memory-mcp CLAUDE.md is an instructions file published in the GitHub repository jthiruveedula/agent-memory-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 483 tokens to every session, about $0.0024 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 2026-09-01.
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.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.