memto
Query dormant past sessions as expert collaborators. Use when: need to recall a past decision or debate, want to ask 'what did we conclude about X in the R38 session', or want to compare answers across multiple historical sessions.
Datos de origen
- Repositorio
- XHXIAIEIN/orchestrator
- Última actividad en el origen
- 19 de abril de 2026 a las 17:48
- Idioma detectado de SKILL.md
- inglés
- Estrellas
- 0
- Forks
- 0
Opciones de instalación
De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.
Revisa los archivos de origen
Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.
Mostrando SKILL.md
SKILL.md
Instrucciones de origen · Vista previa de solo lectura- name
- memto
- description
- Query dormant past sessions as expert collaborators. Use when: need to recall a past decision or debate, want to ask 'what did we conclude about X in the R38 session', or want to compare answers across multiple historical sessions.
# memto — Session Expert Protocol
memto treats past Claude Code sessions as dormant collaborators. Instead of distilling facts, you fork the original session non-destructively, ask your question in the fork, then the fork is auto-cleaned up.
## When to Use
- User asks "what did we decide about X" and `.remember/` doesn't have it
- Need to verify a past architectural decision (e.g., "the R38 AutoAgent boundary debate")
- Want to ask the same question across N past sessions and surface disagreements
## Commands
List recent sessions matching a keyword:
```
memto list [--keyword <term>] [--top 10]
```
Ask a question across matching sessions (returns JSON for agent consumption):
```
memto ask "<keyword>" --question "<your question>" --top 3 --json
```
Ask a specific session by ID:
```
memto ask --session-id <id> --question "<your question>"
```
## Constraints
- Never modify original sessions — memto forks before querying
- Use `--json` when consuming output in code; omit for human-readable output
- `memto ask` spawns subprocesses and may take 30-120s per session; plan accordingly
- If `memto` is not installed: `npm install -g memto`
Ver en GitHub