memory-store

A command for saving a new memory in Mnemosyne, a memory store for coding-agent work, with added context and importance settings.

In plain words
What is it for?
It helps save notes with optional importance and context while automatically choosing the relevant project or global storage area.
Why use it?
It provides a consistent way to record information for later use across a project or session.

Command for Claude Code

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/rand/mnemosyne/memory-store
Clone the repo
git clone --depth 1 https://github.com/rand/mnemosyne

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 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 $0.00015 $0.00503
Opus 5 $0.00008 $0.00251
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00002 $0.00050

Measured 2d ago against content hash 8494df3b4d96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-store 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-store.md · 58 lines

What it actually says

I will help you store a memory in Mnemosyne. Please provide the content you want to store as arguments to this command.

Usage:

  • /memory-store <content> - Store with default importance (5)
  • /memory-store --importance <1-10> <content> - Store with specific importance
  • /memory-store --context <context> <content> - Store with additional context

Instructions for me:

  1. Parse the arguments:

    • Extract --importance flag if present (default: 5)
    • Extract --context flag if present (default: "User-provided memory")
    • The remaining text is the memory content
  2. Auto-detect namespace:

    • Use the Bash tool to detect the current project
    • Check for git root: git rev-parse --show-toplevel 2>/dev/null
    • If in a git repo, read .claude/CLAUDE.md or CLAUDE.md for project name
    • Parse YAML frontmatter for project: field, or use first H1 heading
    • Construct namespace as project:<name>
    • If no project detected, use global
  3. Call Mnemosyne MCP tool:

    {
      "name": "mnemosyne.remember",
      "arguments": {
        "content": "<parsed content>",
        "namespace": "<detected namespace>",
        "importance": <parsed importance>,
        "context": "<parsed context>"
      }
    }
    
  4. Format the output:

    ✓ Memory stored successfully
    
    ID: <memory_id>
    Summary: <llm-generated summary>
    Tags: <comma-separated tags>
    Importance: <importance>/10
    Namespace: <namespace>
    
  5. Error handling:

    • If MCP server not available: "Error: Mnemosyne MCP server not running. Start with 'mnemosyne serve'"
    • If API key not configured: "Error: Anthropic API key not set. Configure with 'mnemosyne config set-key'"
    • If content is empty: "Error: No content provided. Usage: /memory-store "

Please proceed to store the memory with the arguments I provided.

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 · 58 lines · 15 tokens per session scan A 8494df3b4d96

Subscribe to this mod's changes

memory-store is a command published in the GitHub repository rand/mnemosyne (84 stars, last pushed 9mo ago), licensed MIT. It adds 15 tokens to every session and 503 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 2026-08-30.

Related

Other commands, from other repositories