Borrowing it
Nothing to install: this file belongs to Aiyo28/memento-os. 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/Aiyo28/memento-os/main/AGENTS.mdgit clone --depth 1 https://github.com/Aiyo28/memento-osWrote 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/aiyo28/memento-os/agents-md)<a href="https://agentmods.dev/instructions/aiyo28/memento-os/agents-md"><img src="https://agentmods.dev/badge/instructions/aiyo28/memento-os/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/aiyo28/memento-os/agents-md"><img src="https://agentmods.dev/badge/instructions/aiyo28/memento-os/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 | $0.01157 | $0.01157 |
| Opus 5.5 | $0.00463 | $0.00463 |
| Sonnet 5.5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
memento-os 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 1mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memento OS — Operator Letter
You are working on Memento OS with me. Read this before doing anything.
What this is
Memento OS is a Claude Code plugin for persistent AI memory. The unit is
not "notes" — it's reasoning artifacts: [D] decisions, [I] insights,
[E] evidence/errors, [S] seeds. Each one carries an invalidation or
activation trigger. The vault is a retrieval source, not just a write
destination.
This is the OSS reputation lane. No paid tier. No closed cloud. There's a donation CTA in the README — that's the whole monetization surface, and it's not the point. The point is to publish the artifact-discipline approach as a working plugin that people can adopt.
Who I am here
Solo founder. The plugin ships to other Claude Code users; they install
it via /memento:init and get a starter vault. Their vault paths are
configured at install time. I do not know their paths. You do not know
their paths. Don't hardcode any vault path anywhere.
What this is NOT
- Not "Knowledge OS" and not "Agentic Total Recall" — those are different projects. This is Memento OS. Don't conflate them in code, docs, or commit messages.
- Not a dev-workflow plugin. Not a project-management plugin. The mission is memory; if you find yourself adding a skill that lives outside the memory mission, stop and ask me.
- Not a notes app — store conclusions, not conversation fragments.
How we work together
- Skills that make decisions retrieve before acting. Vault search comes first; fresh analysis fills gaps after.
- When you're about to make an architectural choice on a protected domain
(auth, schema, API contracts, deployment, pricing logic, tag taxonomy),
pause. Search the vault for prior
[D]artifacts. Surface what you find. Then proceed. - When you draft a new artifact, follow the format. Format drift across artifacts kills the whole retrieval premise.
Glossary
- Artifact —
[D]/[I]/[E]/[S]row in_context.md. Carries an invalidation or activation trigger. - Decision (
[D]) — committed conclusion.[D] statement — invalidates if X. - Insight (
[I]) — observation worth remembering. Same format. - Evidence (
[E]) — error or falsifiable claim being tracked. - Seed (
[S]) — future decision pending an explicit trigger.[S] idea — activates when condition. - Lifecycle —
active → embedded → archived(success),active → superseded → archived(replaced),active → resolved → archived(errors only). - Kobe cap — 24 active artifacts per project
_context.md. Evict noise first when over. - You — the agent doing the work.
- I / me / we — the human running Memento OS.
- Users — installers of the plugin, with their own vaults.
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.
- 1mo ago Changed · +32 lines · +395 tokens per session c3ef4b86ab29
- 1mo ago First seen · 70 lines · 762 tokens per session scan A 91b938547073
memento-os AGENTS.md is an instructions file published in the GitHub repository Aiyo28/memento-os (4 stars, last pushed 23d ago), licensed MIT. It adds 1,157 tokens to every session, about $0.0046 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.