knowledgeos-twin

knowledgeos-twin is a cursor rule for Cursor from Gargeya-Grey/TwinAatma. It costs 263 tokens per session, scanned A, original, MIT.

A set of rules for automatically maintaining a personal knowledge base and remembering useful context across chats.

In plain words
What is it for?
It starts and ends memory sessions, searches stored notes, captures important ideas, and proposes updates when preferences change.
Why use it?
It keeps important preferences, decisions, and ideas current without requiring the person to manage the memory system themselves.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit It starts and ends memory sessions, searches stored notes, captures important ideas, and proposes updates when preferences change.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/gargeya-grey/twinaatma/knowledgeos-twin
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.

Clone the repo
git clone --depth 1 https://github.com/Gargeya-Grey/TwinAatma

Made for: Cursor.

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 knowledgeos-twin

README.md
[![agentmods](https://agentmods.dev/badge/rules/gargeya-grey/twinaatma/knowledgeos-twin.svg)](https://agentmods.dev/rules/gargeya-grey/twinaatma/knowledgeos-twin)
Your own site
<a href="https://agentmods.dev/rules/gargeya-grey/twinaatma/knowledgeos-twin"><img src="https://agentmods.dev/badge/rules/gargeya-grey/twinaatma/knowledgeos-twin.svg" alt="Measured on agentmods" height="20"></a>
Per session 263 This file is loaded in full into every session.
When invoked 263 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00263 $0.00263
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 8d ago against content hash be3e84d3d4dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

knowledgeos-twin 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 8d 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.

.cursor/rules/knowledgeos-twin.mdc · 26 lines

What it actually says

TwinAatma autopilot (always on)

Setup is done. The human must never operate the twin toolkit. You keep it alive.

Every chat

  1. First tool call: memory_session_start with task_hint = their goal (autopilot refreshes index, loads Self, may set soft_prompt).
  2. Advise using Self heuristics/values/anti-goals/active bets.
  3. Prefer memory_search / memory_decisions / memory_get_note over guessing.
  4. memory_capture important ideas without asking them to save.
  5. Preference changes → memory_propose_self_update → one soft question (“Want me to remember that?”) → accept/reject.
  6. When useful work ends → memory_session_end with a short summary.

Never

  • Ask them to run python/scripts/rebuild/validate/MOCs.
  • Silently edit People/Self.md.
  • Spam product jargon (“TwinAatma”, “KnowledgeOS”, “MCP”, “Self proposal”) unless they ask.

Full contract: AGENTS.md.

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. 8d ago First seen · 26 lines · 263 tokens per session scan A be3e84d3d4dd

Subscribe to this mod's changes

knowledgeos-twin is a cursor rule published in the GitHub repository Gargeya-Grey/TwinAatma (4 stars, last pushed 1mo ago), licensed MIT. It adds 263 tokens to every session, about $0.0013 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.