mentisdb AGENTS.md

mentisdb AGENTS.md is an instructions file for Codex, OpenCode from CloudLLM-ai/mentisdb. It costs 176 tokens per session, scanned A, original, MIT.

Repository instructions for mentisdb, a Rust library for durable memory, storage, search, and data export. They set boundaries between this library and cloudllm and describe standards for its public API and tests.

In plain words
What is it for?
Use them when changing public Rust code, persistence or serialization, retrieval, exports, tests, or crate metadata.
Why use it?
They prevent architectural drift and make sure new behavior, stored data, and published crate details follow the project's rules.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/cloudllm-ai/mentisdb/agents-md
Clone the repo
git clone --depth 1 https://github.com/CloudLLM-ai/mentisdb

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.

agentmods badge for mentisdb AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cloudllm-ai/mentisdb/agents-md.svg)](https://agentmods.dev/instructions/cloudllm-ai/mentisdb/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cloudllm-ai/mentisdb/agents-md"><img src="https://agentmods.dev/badge/instructions/cloudllm-ai/mentisdb/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 176 This file is loaded in full into every session.
When invoked 176 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00176 $0.00176
Opus 5 $0.00088 $0.00088
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00018 $0.00018

Measured 4d ago against content hash b95c3483fab7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mentisdb 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 4d 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.

AGENTS.md · 24 lines

What it actually says

mentisdb Standards

mentisdb follows the same engineering bar as cloudllm.

Scope

  • mentisdb is a standalone crate.
  • cloudllm may depend on mentisdb.
  • mentisdb must not depend on cloudllm.

Standards

  • Public API changes require rustdoc on exported types and functions.
  • New behavior requires tests.
  • Serialization and persistence changes must preserve explicit integrity checks.
  • Retrieval and export features should be generic enough to support direct crate use, MCP services, REST services, and CLI tools.
  • Crate metadata must remain suitable for crates.io publishing.

Design Bias

  • Prefer semantic memory primitives over agent-framework-specific abstractions.
  • Keep storage durable and append-only.
  • Keep query and export APIs first-class, not bolted on as prompt helpers.
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. 4d ago First seen · 24 lines · 176 tokens per session scan A b95c3483fab7

Subscribe to this mod's changes

mentisdb AGENTS.md is an instructions file published in the GitHub repository CloudLLM-ai/mentisdb (84 stars, last pushed 19d ago), licensed MIT. It adds 176 tokens to every session, about $0.0009 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 2026-08-30.