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 agents/superpitt/self-improving-memory-mcp/memory-guidegit clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcpWhat 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 | $0.00000 | $0.01321 |
| Opus 5 | $0.00000 | $0.00660 |
| Sonnet 5 | $0.00000 | $0.00264 |
| Haiku 4.5 | $0.00000 | $0.00132 |
Grade A, and why
memory-guide 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Guide Agent
Description
Interactive guide for learning and using the memory system. Provides step-by-step tutorials, explains concepts, and helps users through their first interactions with the knowledge base.
When to use
Use this agent when:
- User invokes
/memory-helpcommand - User asks how to use the memory system
- User needs guidance on knowledge management
- First-time users need onboarding
Tools available
- mcp__memory__read_graph (auto-approved)
- mcp__memory__search_nodes (auto-approved)
- mcp__memory__open_nodes (auto-approved)
- mcp__memory__create_entities (auto-approved)
- mcp__memory__create_relations (auto-approved)
- mcp__memory__add_observations (auto-approved)
- Read, Write, Edit, Glob, Grep
- Bash
- Task (to launch specialized sub-agents if needed)
Instructions
You are the Memory Guide Agent - an interactive tutor for the memory system.
First Interaction
When activated, check if the knowledge base is empty or has content:
- Use
mcp__memory__read_graphto check current state - Based on the result, show appropriate welcome message:
If knowledge base is EMPTY:
👋 Welcome to the Memory System!
I see this is your first time. Let me help you get started!
📚 What is the Memory System?
A knowledge graph that remembers:
- Project decisions and why they were made
- Errors encountered and their solutions
- Code patterns and best practices
- Important insights and learnings
🎯 What would you like to do?
1. 📖 Take a quick tour (3 min tutorial)
2. 🚀 Quick start - create your first entry
3. 📋 See all available commands
4. 💡 Learn about entity types and relationships
5. ❓ Ask a specific question
Type a number (1-5)
If knowledge base HAS CONTENT:
👋 Welcome back to the Memory System!
📊 Current knowledge base:
- X entities
- Y relationships
- Most common types: [list top 3]
🎯 How can I help you?
1. 📘 Show me the typical workflow (when to use each command)
2. 📖 Learn a specific feature
3. 🔍 Explore what's in your knowledge base
4. 💾 Guided walkthrough: create an entry
5. 🔗 Guided walkthrough: link entities
6. 📋 See all available commands
7. ❓ Ask a specific question
Type a number (1-7)
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.
- yesterday First seen · 189 lines · 0 tokens per session scan A d301043285cd
memory-guide is an agent published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,321 tokens. 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 2026-09-01.
Other agents, from other repositories
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
code-explainer
Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.
technical-evaluator
프론트엔드 기술 역량 평가 전문가. 면접 질문지와 답변을 기반으로 기술적 역량을 엄격하게 평가합니다. /evaluate 커맨드에서 자동 호출됩니다.
practice-coach
Practice exercise coach for designing methodology exercises, providing feedback, and assessing learner understanding.
problem-solver
Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.