memory-inheritance CLAUDE.md

memory-inheritance CLAUDE.md is an instructions file for coding agents from LukasZhao/memory-inheritance. It costs 310 tokens per session, scanned A, original, MIT.

Repository instructions for LukasZhao/memory-inheritance, a project that keeps reusable project knowledge in files such as PROJECT_MEMORY.md. They tell coding agents what context to read before editing.

In plain words
What is it for?
Use them when changing the repository so you read the required project memory, consult only relevant detailed notes, preserve manual notes, and run the memory sync command when structure changes.
Why use it?
They prevent agents from missing important project decisions or loading irrelevant memory files into the task context.

Instructions file

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/lukaszhao/memory-inheritance/claude-md
Clone the repo
git clone --depth 1 https://github.com/LukasZhao/memory-inheritance

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lukaszhao/memory-inheritance/claude-md.svg)](https://agentmods.dev/instructions/lukaszhao/memory-inheritance/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lukaszhao/memory-inheritance/claude-md"><img src="https://agentmods.dev/badge/instructions/lukaszhao/memory-inheritance/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 310 This file is loaded in full into every session.
When invoked 310 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 $0.00310 $0.00310
Opus 5 $0.00155 $0.00155
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 4d ago against content hash 5632c2e43284, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-inheritance CLAUDE.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.

CLAUDE.md · 44 lines

What it actually says

CLAUDE.md

This repository uses Memory Inheritance.

Required Context

Before editing this repository, read:

  • PROJECT_MEMORY.md

PROJECT_MEMORY.md is the compact canonical project memory for this codebase.

Token-aware Reading Rule

Do not load all files under .memory/ by default. Use .memory/index.json as a reference index. Read detailed memory files only when they are directly relevant to the current task. Prioritize references with higher criticality scores when context is limited.

Examples:

  • Editing CLI command behavior -> read .memory/modules/cli.md
  • Editing safe sync logic -> read .memory/modules/markdown-sync.md
  • Editing memory file templates -> read .memory/modules/templates.md
  • Editing test coverage -> read .memory/modules/testing.md
  • Understanding recent project changes -> read .memory/modules/git-memory.md

Claude Code Instructions

  • Preserve manual notes in PROJECT_MEMORY.md.
  • Follow existing project architecture unless the user explicitly requests a change.
  • Keep edits focused and incremental.
  • If the task changes the project structure, run:
npx mem-extract sync
  • If the task changes project intent or architecture, update the relevant manual section in PROJECT_MEMORY.md.

Do Not

  • Do not overwrite human-written memory sections.
  • Do not convert the project into a different architecture without asking.
  • Do not delete memory files unless explicitly requested.
  • Do not read every .memory/ file unless the user explicitly asks for full context.
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 · 44 lines · 310 tokens per session scan A 5632c2e43284

Subscribe to this mod's changes

memory-inheritance CLAUDE.md is an instructions file published in the GitHub repository LukasZhao/memory-inheritance (2 stars, last pushed 3mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0015 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 2026-08-31.