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.
npx agentmods add instructions/hudrazine/claude-code-memory-bank/claude-mdgit clone --depth 1 https://github.com/hudrazine/claude-code-memory-bankWrote 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.
[](https://agentmods.dev/instructions/hudrazine/claude-code-memory-bank/claude-md)<a href="https://agentmods.dev/instructions/hudrazine/claude-code-memory-bank/claude-md"><img src="https://agentmods.dev/badge/instructions/hudrazine/claude-code-memory-bank/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01342 | $0.01342 |
| Opus 5 | $0.00671 | $0.00671 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
claude-code-memory-bank 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Important: This is NOT a software development project. This is a prompt engineering and file management project for the Claude Code Memory Bank system.
This repository serves two primary purposes:
- Prompt Engineering: Development and refinement of the Memory Bank system methodology for Claude Code
- File Management: Storage and version control of the core files that constitute the Claude Code Memory Bank
Claude Code Memory Bank is an experimental adaptation of Cline Memory Bank, designed specifically for Claude Code. It provides:
- A hierarchical documentation structure (Memory Bank) for use in other projects
- Custom slash commands for workflow management
- Best practices for context preservation across sessions
Note: This project itself does not use the Memory Bank system (as that would be excessive for a methodology project). Instead, it contains the reference implementation and documentation that other projects can adopt.
Project Contexts
-
Claude Code memory management:
- Local documentation: @references/claude-code-manage-memory.md
- Web documentation: Manage Claude's memory - Anthropic
-
Claude Code custom slash commands:
- Local documentation: @references/claude-code-slash-commands.md
- Web documentation: Slash Commands - Anthropic
-
Cline Memory Bank (Original):
- Local documentation: @references/cline-memory-bank.md
- Web documentation: Cline Memory Bank
-
Claude Code Memory Bank (Customized for this project):
- Local documentation: @.claude/claude-memory-bank.md
Project Structure
Directory Structure
claude-code-memory-bank/
├── CLAUDE.md # This file - Project guidance for Claude Code
├── README.md # Project overview and usage instructions
├── LICENSE # Unlicense (public domain)
├── references/ # Reference documentation
│ ├── claude-code-manage-memory.md # Claude Code memory management features
│ ├── claude-code-slash-commands.md # Claude Code custom slash commands
│ └── cline-memory-bank.md # Original Cline Memory Bank documentation
└── .claude/ # Claude Code Memory Bank implementation
├── claude-memory-bank.md # Core Memory Bank system documentation (conceptual layer)
└── commands/ # Custom slash commands
├── init-memory-bank.md # Quick Memory Bank initialization
├── commit.md # Git commit workflow command
└── workflow/ # Memory Bank workflow commands
├── understand.md # Context analysis command
├── plan.md # Planning command
├── execute.md # Execution command
└── update-memory.md # Memory update command
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.
- 6d ago First seen · 121 lines · 1,342 tokens per session scan A 2c2dac8f8835
claude-code-memory-bank CLAUDE.md is an instructions file published in the GitHub repository hudrazine/claude-code-memory-bank (41 stars, last pushed 1y ago), licensed Unlicense. It adds 1,342 tokens to every session, about $0.0067 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.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.