MEMORY

A command set for managing a graph of stored facts and links between them. It can search, add, update, connect, tag, merge, and remove entries.

In plain words
What is it for?
Use it to inspect graph statistics, find or open stored facts, record new observations, connect related entries, assign importance, and clean up or merge duplicates.
Why use it?
It keeps useful context organised across coding sessions instead of relying on scattered notes or memory. It also helps find duplicates and maintain the stored information.

Command for Claude Code

Part of the memory-mcp plugin — 1 skill, 9 commands, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/danielsimonjr/memory-mcp/memory
Clone the repo
git clone --depth 1 https://github.com/danielsimonjr/memory-mcp

Made for: Claude Code.

Or install memory-mcp, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 1 MCP server.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00012 $0.00743
Opus 5 $0.00006 $0.00371
Sonnet 5 $0.00002 $0.00149
Haiku 4.5 $0.00001 $0.00074

Measured 2d ago against content hash 7fec3e5b0550, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MEMORY 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 2d 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/commands/MEMORY.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Graph Operations

Comprehensive access to memory-mcp for maintaining cross-session context.

Actions

Read Operations

Action Description
stats Show graph statistics (entity/relation counts, types, dates)
search <query> Search for entities matching query
open <name> Open specific entity by name
read Read entire graph (use sparingly)
duplicates Find potential duplicate entities

Write Operations

Action Description
update <entity> <observation> Add observation to existing entity
create <name> <type> <observation> Create new entity
relate <from> <to> <type> Create relation between entities
tag <entity> <tags...> Add tags to entity
importance <entity> <0-10> Set entity importance score
delete <entity> Delete an entity

Maintenance Operations

Action Description
compress Preview graph compression (merge similar entities)
merge <entity1> <entity2> Merge two entities into one
cleanup Run full maintenance (stats + duplicates + recommendations)

Usage Examples

# Read operations
/project:MEMORY stats
/project:MEMORY search typescript project
/project:MEMORY open memory-mcp
/project:MEMORY duplicates

# Write operations
/project:MEMORY update memory-mcp "Added new feature X"
/project:MEMORY create my-project project "New project started"
/project:MEMORY relate my-project memory-mcp uses
/project:MEMORY tag memory-mcp sqlite storage
/project:MEMORY importance memory-mcp 9

# Maintenance
/project:MEMORY compress
/project:MEMORY merge old-entity new-entity
/project:MEMORY cleanup

Session Workflow

  1. Session Start: /project:MEMORY stats - Check what's stored
  2. During Work: /project:MEMORY update <entity> <observation> - Record discoveries
  3. Session End: /project:MEMORY update <project> "Session summary..." - Persist learnings
  4. Periodically: /project:MEMORY cleanup - Maintain graph hygiene

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 12 tokens per session scan A 7fec3e5b0550

Subscribe to this mod's changes

MEMORY is a command published in the GitHub repository danielsimonjr/memory-mcp (3 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 743 once invoked, about $0.0001 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.