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.
/plugin marketplace add GRU-953/MTA_Pluginnpx agentmods add plugins/gru-953/mta_plugin/marketplacegit clone --depth 1 https://github.com/GRU-953/MTA_PluginGrade A, and why
memorised-them-all 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 yesterday.
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.
What it actually says
{
"name": "memorised-them-all",
"owner": {
"name": "GRU-953",
"url": "https://github.com/GRU-953"
},
"metadata": {
"description": "Local, token-free, deterministic file digestion → searchable knowledge-graph memory for any AI assistant (Claude, Gemini, Cursor, VS Code, Windsurf, Codex, Grok). Incremental, portable (export/import/merge/diff), model-free (no LLM/GPU), 100% private, open-source.",
"version": "3.3.0",
"pluginRoot": "."
},
"plugins": [
{
"name": "memorised-them-all",
"source": "./",
"description": "Convert any local file to Markdown, then digest it into a token-free, searchable knowledge-graph memory (entities, relations, themes) + exportable Markdown notes, with model-free BM25 recall — usable from Claude, Gemini, Cursor, VS Code, Windsurf, Codex and Grok via one `mta setup`. Re-digests are incremental; recall filters by document/entity-type and spans several projects; memories export, import, merge and diff across machines. Deterministic and model-free — no LLM/GPU; 100% local & private; open-source; auto-installing. Legacy Bengali (SutonnyMJ/Bijoy) auto-converted to Unicode.",
"license": "MIT",
"homepage": "https://github.com/GRU-953/memorised-them-all",
"keywords": ["memory", "knowledge-graph", "graphrag", "rag", "mcp", "markitdown",
"token-free", "deterministic", "offline", "local", "privacy", "bengali",
"claude", "gemini", "cursor", "vscode", "windsurf", "codex", "grok", "incremental", "portable"]
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 25 lines scan A 771586d27f8d
memorised-them-all is a plugin published in the GitHub repository GRU-953/MTA_Plugin (1 stars, last pushed 27d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
declared
Synthetic: skills path ADDS to the default scan, commands path REPLACES it.
outlook
Use Microsoft Outlook (classic desktop) end-to-end from your agent (Claude Code, Cowork, Copilot, Cursor, and other plugin-compatible agents) — read, search, triage, and send mail; manage calendar events and meeting invites; work with contacts, tasks, color categories, and mail rules; check Out-of-Office. Bundles the…
whetstone
Plugin marketplace listing 4 plugins: session-measurement, throughline, notify-me, strain.
google-search-console
Read Google Search Console from Claude Code: performance queries, indexing checks, cannibalisation and CTR analysis, plus a white-label HTML SEO audit in English or Italian.
throughline
Task-Track & Handoff for AI agents on long, multi-session work. Within a session it pins one ⭐️ MAIN goal (frozen title, explicit verdict at close) in an emoji-tagged task list so the agent doesn't drift; across sessions or agents it writes a plain-markdown handoff the next agent re-derives before trusting. Not for…
notify-me
Calls you back when an agent needs you. The moment an agent gets blocked waiting on your decision, notify-me pushes a notification to your phone (via ntfy) and/or plays a sound on your computer — so you can step away and still know when you're needed. Works with any agent that supports plugin hooks. No account, no…