export-memory

A command for exporting a project’s stored memory as Markdown notes and supporting index files.

In plain words
What is it for?
Exporting the main memory file, per-document notes, a relationship graph, and the search index to a chosen destination.
Why use it?
It makes project memory portable so it can be copied to another location or preserved outside the current setup.

Command

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/gru-953/mta_plugin/export-memory
Clone the repo
git clone --depth 1 https://github.com/GRU-953/MTA_Plugin
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 121 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 $0.00008 $0.00121
Opus 5 $0.00004 $0.00060
Sonnet 5 $0.00002 $0.00024
Haiku 4.5 $0.00001 $0.00012

Measured today against content hash 8566d42dfdc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

export-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 today.

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.

commands/export-memory.md · 15 lines

What it actually says

Export the project's memory as portable Markdown files.

Destination: $ARGUMENTS

Steps:

  1. If no destination was given, ask where to export (default: the current directory).
  2. Call export_memory with the destination (and project if named).
  3. It copies memory.md, the per-document memory/ notes, graph.json, and the recall index (vectors.npz/.json) to the destination. Confirm what was written.
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. today First seen · 15 lines · 8 tokens per session scan A 8566d42dfdc5

Subscribe to this mod's changes

export-memory is a command published in the GitHub repository GRU-953/MTA_Plugin (1 stars, last pushed 26d ago), licensed MIT. It adds 8 tokens to every session and 121 once invoked, about $0.0000 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.