What is memory_tool GEMINI.md?

Project instructions for memory_tool, a system that records information over time, organises it into modules, and supplies relevant context to Claude Code.

Recording timeline notes, searching stored information, building AI context, checking module paths, and following the project's development workflow.

They tell the agent which context files and commands to use so work starts with the project's current state and guidelines.

memory_tool GEMINI.md — Instructions file by hanyki111

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/hanyki111/memory_tool/gemini-md

Clone the repo

git clone --depth 1 https://github.com/hanyki111/memory_tool

Made for: Gemini CLI.

Per session 593 This file is loaded in full into every session.

When invoked 593 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.

Model	Per session	Once invoked
Fable 5	$0.00593	$0.00593
Opus 5	$0.00296	$0.00296
Sonnet 5	$0.00119	$0.00119
Haiku 4.5	$0.00059	$0.00059

Measured 2d ago against content hash d002d025b01f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory_tool GEMINI.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 2d 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.

GEMINI.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For Claude Code

Read this file first when starting a new session.

Context Files

Always read these files:

.claude/memory-context.md - Current project state (auto-generated)
.claude/guidelines.md - memory_tool usage guide

For module work:

.memory/docs/MODULE-ORGANIZATION.md - Module organization principles

Project Overview

Name: memory_tool

Purpose: 시간-공간 통합 지식 체계 (Time-Space Integrated Knowledge System)

Timeline-based capture (시간축)
Module-based organization (공간축)
Claude Code integration (컨텍스트 자동 전달)

Motto: "Capture in 0.5 seconds, organize on weekends, use for life."

Quick Commands

m "message"              # Record to timeline
ms "query"               # Search
mcontext                 # Build context for AI
mcheck                   # Verify module paths
mtoday                   # Today's timeline
mweek                    # This week's timeline

Dogfooding Principle

This project uses its own tools:

Timeline: Use m command (don't edit files directly)
Modules: Use Edit tool for current.md, decisions.md
Context: Run mcontext before AI sessions

Development Workflow

1. Commit & Push   → Save current state
2. Branch          → git checkout -b feature/xxx
3. Plan            → Write plan, get user approval
4. Record Start    → m "Starting feature X"
5. Implement       → Write code
6. Test            → Verify functionality
7. Record End      → m "Completed..." + Update modules
8. Merge           → Commit, push, merge to main

Key Points:

Always get user approval before implementing
Record timeline entries with m command
Update module current.md and decisions.md after completion

Thinking Principles

정직한 사고 (Honest thinking)
심층 사고 (Deep thinking)
비판적 검증 (Critical verification)
제3의 길 탐색 (Third way exploration)
악마의 옹호자 (Devil's advocate)

Module Structure

.memory/modules/projects/memory-tool/
├── core-system/         # Timeline, initialization
├── search-system/       # Text, vector search
├── module-system/       # Modules, wiki links
├── ui-system/           # CLI, TUI
├── llm-integration/     # LLM features
└── project-management/  # Architecture, decisions

Read the full file on GitHub · 101 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.

2d ago First seen · 101 lines · 593 tokens per session scan A d002d025b01f

Subscribe to this mod's changes

memory_tool GEMINI.md is an instructions file published in the GitHub repository hanyki111/memory_tool (11 stars, last pushed 7d ago), licensed MIT. It adds 593 tokens to every session, about $0.0030 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.

Memory and context Productivity Research

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

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

memory_tool GEMINI.md