memory-inheritance: Instructions file for Codex

AGENTS.md

memory-inheritance AGENTS.md is an instructions file for Codex, OpenCode from LukasZhao/memory-inheritance. It costs 340 tokens per session, scanned A, original, MIT.

Repository instructions for an AI coding agent working with Memory Inheritance, a system that keeps important project context in memory files.

In plain words
What is it for?
Use them when changing code in this repository, especially when deciding which project-memory files to read before editing a specific area.
Why use it?
They prevent the agent from missing the project's goals, architecture, current state, or relevant decisions while limiting unnecessary file reading.

Instructions file for CodexOpenCode

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

This is LukasZhao/memory-inheritance's own configuration. It tells Codex and OpenCode how to work on memory-inheritance 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 memory-inheritance configures →

Reuse

Borrowing it

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

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 memory-inheritance AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lukaszhao/memory-inheritance/agents-md/github.svg)](https://agentmods.dev/instructions/lukaszhao/memory-inheritance/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lukaszhao/memory-inheritance/agents-md"><img src="https://agentmods.dev/badge/instructions/lukaszhao/memory-inheritance/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.

agentmods 80×15 button for memory-inheritance AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lukaszhao/memory-inheritance/agents-md"><img src="https://agentmods.dev/badge/instructions/lukaszhao/memory-inheritance/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 340 This file is loaded in full into every session.
When invoked 340 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 $0.00340 $0.00340
Opus 5.5 $0.00136 $0.00136
Sonnet 5.5 $0.00068 $0.00068
Haiku 4.5 $0.00034 $0.00034

Measured 1mo ago against content hash 6cd85749bb8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-inheritance 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.

AGENTS.md · 50 lines

What it actually says

AGENTS.md

This repository uses Memory Inheritance.

Required Context

Before making changes, read:

  • PROJECT_MEMORY.md

PROJECT_MEMORY.md is the compact canonical project memory. It contains project intent, detected stack, important files, common commands, manual notes, architecture decisions, current development state, and memory references.

Token-aware Reading Rule

Do not load all files under .memory/ by default. If more detail is needed, consult:

  • .memory/index.json

Then read only the referenced memory files relevant to the current task. Prioritize references with higher criticality scores when context is limited.

Examples:

  • Editing CLI command routing -> read .memory/modules/cli.md
  • Editing sync or marker behavior -> read .memory/modules/markdown-sync.md
  • Editing generated templates -> read .memory/modules/templates.md
  • Editing tests -> read .memory/modules/testing.md
  • Understanding recent project changes -> read .memory/modules/git-memory.md

Agent Workflow

  1. Read PROJECT_MEMORY.md.
  2. Consult .memory/index.json only when detailed context is needed.
  3. Follow the project intent and constraints.
  4. Keep changes small and focused.
  5. Do not overwrite manual memory notes.
  6. After meaningful changes, run:
npx mem-extract sync
  1. If a change affects architecture, update the manual notes or architecture decision section.

Rules

  • Do not perform broad rewrites unless explicitly requested.
  • Prefer incremental, testable changes.
  • Explain major changes clearly.
  • Do not treat memory files as disposable generated artifacts.
  • Do not delete .memory/ references unless explicitly requested.
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. 1mo ago First seen · 50 lines · 340 tokens per session scan A 6cd85749bb8b

Subscribe to this mod's changes

memory-inheritance AGENTS.md is an instructions file published in the GitHub repository LukasZhao/memory-inheritance (2 stars, last pushed 4mo ago), licensed MIT. It adds 340 tokens to every session, about $0.0014 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.

Related

Other instructions, from other repositories