Summon (Grade A) logo

Summon (Grade A)Security-tested data-ai skill for Claude AI. Grade A. Summon a spirit — a persistent agent that runs on a schedule or watches for conditions. Unlike `/loop` (dumb scheduler), `/summon` designs the pro

— (0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

Summon is a security-tested data-ai skill for Claude AI that allows users to design and launch a persistent agent process, also referred to as a 'spirit'. This spirit can run on a schedule or watch for specific conditions. Unlike the '/loop' command, which is a simple scheduler, '/summon' uses adaptive questioning to understand the user's intent, generates a reviewable specification, and then launches the agent. The tool is useful for creating recurring tasks, monitoring conditions, or managing spirits without directly interacting with the graph database. It operates in two modes: connected mode, which relies on graph context, and local mode, which bypasses graph-related operations.

Key features

  • Adaptive questioning for agent specification
  • Reviewable specification generation
  • Scheduled and condition-driven task support
  • Local and connected mode operation
  • Spirit management through .spirits/ directory

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Monitoring Active Quests

Summon a spirit to periodically check on the status of active quests and report any changes or issues.

Recurring Task Automation

Use Summon to create a recurring task that runs on a schedule, such as daily or weekly, to perform specific actions or checks.

Pros & Cons

Pros

  • Adaptive questioning for precise agent specification
  • Reviewable spec before launching the agent
  • Operates in both connected and local modes for flexibility
  • Can be used for scheduled or condition-driven tasks

Cons

  • Complexity in understanding and specifying agent behavior
  • Dependence on Claude AI and specific configuration
  • Limited direct control over low-level agent operations

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

What limitations should I be aware of when using Summon?

Summon requires a Claude AI environment and proper configuration; specifying complex agent behavior can be challenging, and low‑level control over the agent is limited compared to manual graph edits.

Asked by Hosanna Marte · Oct 30, 2025

What are the main steps in creating a spirit with Summon?

Summon first asks for the spirit’s purpose, generates options based on context (quests, sessions, existing spirits), then creates a reviewable spec before launching the agent via the chosen mode.

Asked by Xavier Costa · Oct 3, 2025

Can Summon run without connecting to the graph database?

Yes. In local mode, Summon bypasses all graph operations, generating and storing the spirit spec in the .spirits/ directory and using CronCreate/CronDelete for scheduling.

Asked by Zain Malik · Sep 13, 2025

How does Summon differ from the /loop command?

Summon uses adaptive questioning to build a reviewable specification for a persistent agent, while /loop is a simple scheduler that requires the user to know the exact task in advance.

Asked by Cristina Moreno · Jul 8, 2025

Ask a question

Skills alternatives

Manage Headers (Grade A) logo
Manage Headers (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Inspects and configures the security headers a Power Pages site sends to browsers — Content Security Policy, frame and clickjacking protection

— (0)
Free
Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

— (0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

— (0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

— (0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

— (0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

— (0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

— (0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

— (0)
Free