agentmods.dev

memohood: Instructions file for Codex

AGENTS.md

memohood AGENTS.md is an instructions file for Codex, OpenCode from maximskorohod/memohood. It costs 1,318 tokens per session, scanned A, original, MIT.

Installation instructions for MemoHood, a conversation-memory provider for the Hermes agent system. It explains how to install the plugin and select it in Hermes's configuration.

In plain words
What is it for?
Use it when installing MemoHood from an archive or configuring it as Hermes's memory provider.
Why use it?
It prevents installation instructions from being confused with MemoHood's separate memory-use instructions and emphasizes the supported setup paths.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is maximskorohod/memohood's own configuration. It tells Codex and OpenCode how to work on memohood itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything memohood configures →

not rated 23repo +1 1mo ago A scan 1,318 tokens original MIT
View source ↗ maximskorohod/memohood
Reuse

Borrowing it

Nothing to install: this file belongs to maximskorohod/memohood. 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/maximskorohod/memohood/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/maximskorohod/memohood

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 memohood AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maximskorohod/memohood/agents-md.svg)](https://agentmods.dev/instructions/maximskorohod/memohood/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/maximskorohod/memohood/agents-md"><img src="https://agentmods.dev/badge/instructions/maximskorohod/memohood/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,318 This file is loaded in full into every session.
When invoked 1,318 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01318 $0.01318
Opus 5 $0.00659 $0.00659
Sonnet 5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured 7d ago against content hash f0f2c7b3e3bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

memohood 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 7d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — установка плагина MemoHood

Этот файл — инструкция по установке плагина MemoHood в hermes. Применяй её только когда пользователь явно просит установить/поставить MemoHood (обычно прислав архив плагина в чат). Во всех остальных случаях игнорируй этот файл — он не про использование памяти (для этого есть скилл memohood), а только про разовую установку.

Что это

MemoHood — провайдер памяти диалогов для hermes (kind: exclusive). Устанавливается копированием в $HERMES_HOME/plugins/memohood/ и включается как memory.provider: memohood в config.yaml. Внутри плагина уже есть готовый идемпотентный установщик (install.sh для Linux/macOS, install.ps1 для Windows), который делает всю работу — тебе не нужно копировать файлы, ставить пакеты или править конфиг вручную.

Способ A — установка из присланного архива (ты, агент, ставишь сам)

Нужен доступ к terminal-инструменту и к venv, где стоит hermes.

  1. Возьми путь к присланному архиву. Когда пользователь прислал файл в чат, ядро уже сохранило его на диск и подставило путь в контекст — используй этот локальный путь.
  2. Распакуй во временную папку и найди внутри каталог, где лежит plugin.yaml (плагин может быть как в корне архива, так и в подпапке):
    • Linux/macOS: mkdir -p /tmp/memohood-inst && unzip -o "<путь-к-архиву>" -d /tmp/memohood-inst
    • Windows: Expand-Archive -Force "<путь-к-архиву>" "$env:TEMP\memohood-inst"
  3. Проверь, что это действительно MemoHood: в каталоге есть plugin.yaml со строкой name: memohood и файл install.sh/install.ps1. Если нет — остановись и скажи пользователю, что архив не похож на MemoHood.
  4. Спроси режим векторного поиска (или поставь по умолчанию облачный):
    • облачный (по умолчанию): вектор через Cloudflare; ключи можно добавить позже, без них память работает в keyword-режиме;
    • локальный офлайн (--local/-Local): скачает модель intfloat/multilingual-e5-large (~2.2 ГБ, один раз), работает без ключей и без Cloudflare.
  5. Запусти штатный установщик из каталога плагина:
    • Linux/macOS: bash install.sh (или bash install.sh --local)
    • Windows: powershell -ExecutionPolicy Bypass -File install.ps1 (или ... -Local)

Read the full file on GitHub · 85 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.

  1. 7d ago First seen · 85 lines · 1,318 tokens per session scan A f0f2c7b3e3bb

Subscribe to this mod's changes

memohood AGENTS.md is an instructions file published in the GitHub repository maximskorohod/memohood (23 stars, last pushed 1mo ago), licensed MIT. It adds 1,318 tokens to every session, about $0.0066 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.

LLMMemory and contextagent-memoryai-agentai-memoryhermeshybrid-search
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens