memorise

memorise is a command for coding agents from GRU-953/MTA_Plugin. It costs 18 tokens per session (306 once invoked), scanned A, original, MIT.

A command that turns files and folders into local project memory: searchable notes, a knowledge graph, and themes describing related information. It works without sending the documents to a language model.

In plain words
What is it for?
Use it to digest project files, images, and archives into local memory, then use commands such as recall or export-memory to work with that stored context.
Why use it?
It lets the agent retain useful project context without repeatedly loading entire documents into the conversation.

Command

Part of the memorised-them-all plugin — 1 skill, 5 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/gru-953/mta_plugin/memorise
Clone the repo
git clone --depth 1 https://github.com/GRU-953/MTA_Plugin

Or install memorised-them-all, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 MCP server.

Wrote 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.

agentmods badge for memorise

README.md
[![agentmods](https://agentmods.dev/badge/commands/gru-953/mta_plugin/memorise.svg)](https://agentmods.dev/commands/gru-953/mta_plugin/memorise)
Your own site
<a href="https://agentmods.dev/commands/gru-953/mta_plugin/memorise"><img src="https://agentmods.dev/badge/commands/gru-953/mta_plugin/memorise.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 306 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 $0.00018 $0.00306
Opus 5 $0.00009 $0.00153
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 3d ago against content hash 929460614fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memorise 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 3d 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.

commands/memorise.md · 25 lines

What it actually says

Digest the path(s) the user provided into local, token-free graph memory using the Memorised them All engine.

Paths: $ARGUMENTS

Steps:

  1. If no path was given, ask which file or folder to digest (or offer the current directory).
  2. Call the digest tool with the path(s). It converts every attachment to Markdown locally (MarkItDown, plus optional Tesseract OCR for scanned images), unpacks archives safely, then builds a knowledge graph with community-detected themes — fully deterministic and model-free (no LLM/Ollama/GPU) — and writes memory.md, per-document notes, and graph.json.
  3. The tool returns only metadata (counts, paths, stats) — do not try to read the converted documents back into the conversation; that would waste tokens.
  4. Report a short summary: files converted, entities, relations, themes, and where the outputs were written. Offer /recall or /export-memory as next steps.

Tip: to rebuild a project from scratch (e.g. after upgrading), pass reset: true to digest. Otherwise, re-running digest on the same folder just updates the memory.

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. 3d ago First seen · 25 lines · 18 tokens per session scan A 929460614fa0

Subscribe to this mod's changes

memorise is a command published in the GitHub repository GRU-953/MTA_Plugin (1 stars, last pushed 29d ago), licensed MIT. It adds 18 tokens to every session and 306 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.