mh

mh is a command for Claude Code from SuperPiTT/self-improving-memory-mcp. It costs 0 tokens per session (660 once invoked), scanned A, original, MIT.

A command that lists the available commands and current status of a self-improving memory system. It also shows brief knowledge-base statistics and selected agent triggers.

In plain words
What is it for?
Use it to search or export stored knowledge, save and connect entries, update confidence, group similar information, and find contradictions.
Why use it?
It gives you a quick reference for managing stored knowledge without searching through system files or documentation.

Command for Claude Code

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 commands/superpitt/self-improving-memory-mcp/mh
Clone the repo
git clone --depth 1 https://github.com/SuperPiTT/self-improving-memory-mcp

Made for: Claude Code.

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 mh

README.md
[![agentmods](https://agentmods.dev/badge/commands/superpitt/self-improving-memory-mcp/mh.svg)](https://agentmods.dev/commands/superpitt/self-improving-memory-mcp/mh)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00660
Opus 5 $0.00000 $0.00330
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 4d ago against content hash 2213ed0a457e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/commands/mh.md · 94 lines

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

  1. Read the knowledge graph to get current stats
  2. Display the commands table (see format below)
  3. Show brief memory stats
  4. 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.

Read the full file on GitHub · 94 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.

  1. 4d ago First seen · 94 lines · 0 tokens per session scan A 2213ed0a457e

Subscribe to this mod's changes

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.