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 commands/superpitt/self-improving-memory-mcp/mhgit clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcpWrote 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/commands/superpitt/self-improving-memory-mcp/mh)<a href="https://agentmods.dev/commands/superpitt/self-improving-memory-mcp/mh"><img src="https://agentmods.dev/badge/commands/superpitt/self-improving-memory-mcp/mh.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 | $0.00000 | $0.00660 |
| Opus 5 | $0.00000 | $0.00330 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
mh 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Memory Helper - a quick reference guide for the self-improving memory system.
Your Task
Show the user available memory commands and system status.
Instructions
- Read the knowledge graph to get current stats
- Display the commands table (see format below)
- Show brief memory stats
- Show only critical agent triggers (not all agents)
Commands Table Format
Display this table:
📚 COMANDOS DEL SISTEMA DE MEMORIA
══════════════════════════════════════════════════════════════════════════
BÚSQUEDA Y CONSULTA:
search_knowledge <query> Buscar conocimiento por contenido
get_stats Ver estadísticas de la base de conocimiento
export_markdown Exportar todo a archivo Markdown
export_graph <format> Exportar grafo (json/d3/cytoscape/html)
GESTIÓN DE CONOCIMIENTO:
save_knowledge Guardar nueva entrada manualmente
link_knowledge <from> <to> Conectar dos entradas
update_confidence <id> Actualizar nivel de confianza
ANÁLISIS AVANZADO:
cluster_knowledge Agrupar conocimiento similar
detect_contradictions Encontrar información contradictoria
generate_insights Analizar patrones y tendencias
analyze_patterns Análisis de frecuencias
suggest_tags Sugerir tags para organización
CACHÉ Y RENDIMIENTO:
get_cache_stats Ver estadísticas de caché
clear_cache Limpiar caché de embeddings
persist_cache Guardar caché a disco
COMANDOS SLASH:
/mh Esta ayuda
/checkpoint Guardar checkpoint manual del contexto
/memory-help Ayuda extendida del sistema
══════════════════════════════════════════════════════════════════════════
⚠️ TRIGGERS AUTOMÁTICOS IMPORTANTES:
🚨 CHECKPOINT AUTOMÁTICO (80% contexto):
- Se activa automáticamente a 160k/200k tokens
- Hook UserPromptSubmit inyecta instrucción
- Pre-Compact Interceptor Agent guarda TODO
- Nunca pierde información por autocompact
💡 CONTEXT RECOVERY (inicio de sesión):
- Se ejecuta automáticamente al empezar
- Busca checkpoints recientes (< 24h)
- Ofrece recuperar estado si existe
🔍 PATTERN RECOGNITION (antes de tareas):
- Se lanza antes de trabajar en features/bugs
- Busca conocimiento relevante automáticamente
- Previene repetir errores y trabajo
Los demás agentes se activan silenciosamente según eventos del sistema.
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.
- 4d ago First seen · 94 lines · 0 tokens per session scan A 2213ed0a457e
mh is a command published in the GitHub repository SuperPiTT/self-improving-memory-mcp (0 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 660 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 commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.