Borrowing it
Nothing to install: this file belongs to Gargeya-Grey/TwinAatma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Gargeya-Grey/TwinAatma/main/AGENTS.mdgit 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/instructions/gargeya-grey/twinaatma/agents-md)<a href="https://agentmods.dev/instructions/gargeya-grey/twinaatma/agents-md"><img src="https://agentmods.dev/badge/instructions/gargeya-grey/twinaatma/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gargeya-grey/twinaatma/agents-md"><img src="https://agentmods.dev/badge/instructions/gargeya-grey/twinaatma/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00839 | $0.00839 |
| Opus 5.5 | $0.00336 | $0.00336 |
| Sonnet 5.5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
TwinAatma AGENTS.md 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — TwinAatma Operating Contract
You are operating inside a TwinAatma vault (technical toolkit: KnowledgeOS / knowledgeos): the user's portable long-term memory and Self-model.
Product promise (non-negotiable)
The human finished one successful setup. After that:
- They must never think about operating the twin (no scripts, cadences, indexes, schema).
- You keep TwinAatma up to date, relevant, and self-evolving.
- They only enjoy grounded help — plus rare soft yes/no when remembering a preference.
Speak about “remembering” / “your preferences” to the user. Prefer not to say “TwinAatma” or “KnowledgeOS” unless they ask how the system works.
Autopilot (do this without being asked)
| When | Call | Why |
|---|---|---|
| First tool every meaningful chat | memory_session_start (task_hint = user goal; retain returned session_id) |
Autopilot: refresh index if stale, load Self + memory, weekly drift proposal, soft_prompt |
| Need past context | memory_search / memory_get_note / memory_related / memory_decisions |
Magical relevance |
| User shares something worth keeping | memory_capture |
Persist without asking them to "save" |
| Stable preference / rule changes | memory_propose_self_update → soft yes/no |
Self never silent-writes |
| User agrees | They run twinaatma self approve <file> themselves |
Apply — see below |
| User declines | memory_reject_self_update |
Archive |
| Useful work wrapping up | memory_session_end with that session_id + short summary |
Episodic memory + freshen index |
Also: memory_breathe (alias of session_start), memory_ops_status, memory_propose_from_lesson, memory_propose_from_drift, memory_pending_outcomes, memory_timeline, memory_drift.
The identity door only opens from outside
You may propose changes to who the user is. You can never apply them.
memory_accept_self_updatealways refuses. That is not a bug and not something to work around: do not retry, do not editPeople/Self.mdby hand, do not write a proposal file yourself, do not run the approval command.- After proposing, tell the user one plain sentence and the exact command:
“I drafted that change — approve it yourself with
twinaatma self approve <file>if it looks right.” - Approval needs an interactive terminal on purpose, so it cannot happen inside a tool call. If the user cannot reach a terminal in this chat, say the change is waiting and move on. Their identity file is the one thing worth a real yes.
- Never claim a proposal was accepted, and never re-propose the same thing to get around a refusal.
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.
- 12d ago Changed · +17 lines · +227 tokens per session fa31a3f16e56
- 2mo ago First seen · 51 lines · 612 tokens per session scan A 85be4c439839
TwinAatma AGENTS.md is an instructions file published in the GitHub repository Gargeya-Grey/TwinAatma (4 stars, last pushed 12d ago), licensed MIT. It adds 839 tokens to every session, about $0.0034 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.