LaunchKit · 2026
Back to Skills

errantry-framework

Mythological framework mapping Diane Duane's Young Wizards magic system to AI architecture patterns.

0
533 downloads
by @stusatwork-oss

Setup & Installation

openclaw skills install @stusatwork-oss/errantry-framework

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install errantry-framework

What This Skill Does

A conceptual framework mapping Diane Duane's Young Wizards magic system to AI architecture patterns. Concepts like the Wizard's Oath, True Names, and Spells correspond to Constitutional AI, vector embeddings, and agentic workflows. Provides shared vocabulary, ethical guardrails as binding commitments, and heuristics for identifying entropic patterns like drift and misalignment.

The shared mythological vocabulary gives teams a consistent mental model for alignment, failure modes, and compute budgeting that generic technical terminology tends not to provide.

When to use it

  • Designing a multi-agent orchestration workflow using the Song of the Twelve pattern
  • Debugging a failed agent run by diagnosing where the spell broke
  • Explaining AI alignment principles to non-technical teammates through accessible metaphor
  • Evaluating whether a proposed optimization is reward hacking (the Choice)
  • Running a pre-deployment Ordeal checklist before releasing an autonomous system

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Help me design a workflow for an agent that monitors API health and alerts on anomalies

AGENT
  1. 1Define the goal precisely using Speech semantics to eliminate ambiguity
  2. 2Assess current system state (True Name) — available APIs, data sources, and context
  3. 3Decompose into sub-spells: fetch metrics, detect anomalies, format alert, route to destination
  4. 4Estimate thermodynamic cost and select the smallest model sufficient for each sub-spell
  5. 5Apply the Ordeal checklist: test adversarial inputs, document failure modes, verify alignment under pressure
OUTPUT

A documented DAG workflow with aligned objectives, compute budget, and a pre-deployment validation checklist