What is membot AGENTS.md?

Project instructions for using Membot, a searchable store that an agent can read, annotate and extend through tools. They describe how to start a session, choose tools and understand results.

Use them when an agent needs to check status, find information across mounted memory collections, inspect nearby topics or add notes. They also explain how to interpret returned data.

They prevent empty or misleading searches caused by using an unmounted store, and explain when writing is unavailable. They give the agent a consistent way to work with stored project knowledge.

How project-you-apps/membot configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to project-you-apps/membot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/project-you-apps/membot/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/project-you-apps/membot

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/project-you-apps/membot/agents-md/github.svg)](https://agentmods.dev/instructions/project-you-apps/membot/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/project-you-apps/membot/agents-md"><img src="https://agentmods.dev/badge/instructions/project-you-apps/membot/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/project-you-apps/membot/agents-md"><img src="https://agentmods.dev/badge/instructions/project-you-apps/membot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,563 This file is loaded in full into every session.

When invoked 2,563 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.

Model	Per session	Once invoked
Fable 5.1	$0.02563	$0.02563
Opus 5.5	$0.01025	$0.01025
Sonnet 5.5	$0.00513	$0.00513
Haiku 4.5	$0.00256	$0.00256

Measured today against content hash 2d6859c614e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

membot 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 today.

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.

AGENTS.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — using Membot as an agent

For an agent consuming Membot through MCP. If you are working on this codebase, read README.md first.

Membot gives you a searchable store you can read, annotate and extend. Retrieval calls no model, so searching is cheap enough to do liberally — the cost is latency, not tokens.

1 · The shape of a session

get_status            → is anything mounted? what?
list_cartridges       → what is available
mount_cartridge(name) → mount it
memory_search(query)  → search the mounted cart

⛔ Search before mounting returns nothing useful. If a search comes back empty, call get_status before concluding the store is empty — an unmounted cart and an empty cart look identical from the outside.

⚠ The server is read-only unless it was started with --writable. memory_store and save_cartridge will refuse. Notes are a separate path and are usually available.

2 · Which tool for which job

You want to…	Use	Not
Find passages matching an idea	`memory_search`	—
Search several mounted carts at once	`multi_search`	calling `memory_search` per cart
Find what is adjacent to a topic	`walk_associate`	`memory_search` with a vaguer query
Read a result in full	`get_passage`	assuming the snippet is the whole passage
Record why something is the way it is	`note_add(kind="why")`	`memory_store`
Say a note is wrong	`propose_correction`	editing or re-storing
Add a new fact to the store	`memory_store`	`note_add`
See what changed since last time	`what_changed`	re-searching and diffing yourself
Keep your own working set	`seat_hot_stack`	a local scratch file

⭐ note_add versus memory_store is the distinction worth getting right. A note is commentary about a passage — reasoning, a caution, a decision. A store adds a new passage to the corpus. ⇒ If what you are writing would be meaningless without the thing it points at, it is a note.

Read the full file on GitHub · 207 lines

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.

today Changed · +16 lines · +265 tokens per session 2d6859c614e4
yesterday First seen · 191 lines · 2,298 tokens per session scan A 2b5c5d708861

Subscribe to this mod's changes

membot AGENTS.md is an instructions file published in the GitHub repository project-you-apps/membot (7 stars, last pushed today), licensed MIT. It adds 2,563 tokens to every session, about $0.0103 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 2026-11-11.

Memory and context

membot AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
membot AGENTS.mdproject-you-apps/membot	Instructions file	7	today	MIT	A	2,563	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

membot: Instructions file for Codex