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.
git clone --depth 1 https://github.com/Gargeya-Grey/TwinAatmaWrote 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.
[](https://agentmods.dev/rules/gargeya-grey/twinaatma/knowledgeos-twin)<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>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.
| Model | Per session | Once 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 |
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.
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
- First tool call:
memory_session_startwithtask_hint= their goal (autopilot refreshes index, loads Self, may setsoft_prompt). - Advise using Self heuristics/values/anti-goals/active bets.
- Prefer
memory_search/memory_decisions/memory_get_noteover guessing. memory_captureimportant ideas without asking them to save.- Preference changes →
memory_propose_self_update→ one soft question (“Want me to remember that?”) → accept/reject. - When useful work ends →
memory_session_endwith 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.
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.
- 8d ago First seen · 26 lines · 263 tokens per session scan A be3e84d3d4dd
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.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
A modular system for recording project context, decisions, requirements, and lessons in structured files. It divides the recorder into core, template, advanced, and edge-case modules.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.