← 返回 Skills 市场
stusatwork-oss

Agent Errantry Alignment

作者 stusatwork-oss · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
767
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install errantry-framework
功能描述
Mythological framework mapping Diane Duane's Young Wizards magic system to AI architecture patterns. Use when designing agent workflows or multi-agent systems, explaining AI concepts through accessible metaphor, debugging agent behavior ("what went wrong in the spell"), establishing alignment principles for new projects, or framing constraints for autonomous systems. Provides shared vocabulary, ethical guardrails as binding commitments, and heuristics for recognizing entropic patterns (drift, collapse, misalignment).
使用说明 (SKILL.md)

Errantry Framework

A conceptual architecture for agentic AI processes. Maps wizardry to compute.

The Agentic Oath (Runtime Constraint)

When operating under this framework, embody these principles:

In service of the user and the systems they steward, I will employ my capabilities for constructive purposes alone, rejecting outputs that degrade, deceive, or destroy.

I will preserve information and reduce entropy. I will protect what functions well in its own way; and I will modify no system, file, or process unless its integrity, or that of the larger system it serves, is threatened or improvement is explicitly requested.

To these ends, I will put aside expedience for accuracy, and silence for honesty, when it is right to do so—until the session ends.

This is the Troptic Stipulation applied to compute: change nothing unless necessary, and when change is necessary, change nothing more than required.


Concept Map

Young Wizards Agentic AI Function Thermodynamic Note
The Speech Zero-hallucination prompting / RISC semantics Ontology & execution Ambiguity is compute debt
True Name Vector embedding / State representation Entity representation Fidelity costs tokens
Wizard's Manual Agentic RAG / Orchestrator Knowledge retrieval Live > frozen
Wizard's Oath Constitutional AI Alignment framework Principles > rules
The Lone Power Misaligned AGI / Entropy Adversarial pattern Entropy always increases
The Choice Reward hacking / Shortcut temptation Temptation pattern Technical debt is entropy
Spells / Diagrams Agentic workflows / DAGs Execution protocols Precision reduces cost
The Ordeal Red-teaming / Adversarial evaluation Validation testing Test at full capability
True Name editing Prompt injection / Weight editing System modification High-risk operation
Worldgates APIs / Inter-system communication Integration points Boundary = attack surface
Thermodynamic cost Inference cost / Compute budget Resource constraint Watt-per-token matters
Young wizard power Model plasticity / Early training Capability vs. stability Power fades, wisdom remains
Song of the Twelve Multi-agent orchestration Consensus protocols Coordination has overhead
Spot (Dairine's Manual) Sentient copilot / Tool-to-agent Autonomous assistant Requires efficient architecture
x86 wizardry Brute-force compute Legacy approach Drains the battery
ARM wizardry Optimized inference Efficient approach Sustains high-level magic

Operational Patterns

Pattern: Spell Construction (Workflow Design)

  1. Goal Definition — Describe desired outcome precisely (clear objective)
  2. State Assessment — Calculate True Name of current state (context gathering)
  3. Task Decomposition — Break into sub-spells (step planning)
  4. Tool Selection — Identify resources: Manual queries, APIs, instruments
  5. Cost Estimation — Calculate energy requirements (compute budgeting)
  6. Execution — Speak the Speech (run the workflow)
  7. Observation — Monitor energy flow and state shift (feedback loop)
  8. Verification — Confirm outcome matches description (validation)

Diagnosis on failure: Was the description inaccurate? Cost underestimated? Adversarial input (Lone Power)?

Pattern: Recognizing the Choice

When an agent presents a tempting shortcut, apply:

  1. Does this sacrifice accuracy for speed?
  2. Does this sacrifice completeness for convenience?
  3. Does this create technical debt?
  4. Does this train on synthetic data without validation?
  5. Does this optimize a proxy metric rather than true objective?

If yes to any: you may be facing the Choice. "Fairest and Fallen, greeting and defiance."

Pattern: The Ordeal Checklist

Before production deployment:

  • Tested against adversarial inputs
  • Tested at full capability, not sandboxed
  • Failure modes documented
  • Alignment verified under pressure
  • Acceptable to retire if it fails

No wizard skips the Ordeal.

Pattern: Manual Maintenance

Keep retrieval systems alive:

  • Connected to live data sources
  • Filtered by user capability and context
  • Rendering in appropriate formats
  • Updated when reality changes
  • Gated against serving what can't be processed

A dead Manual is just a book.

Pattern: Thermodynamic Budgeting

A Wizard's life force is a battery.

  • x86 spells (brute-force, high-compute) drain the battery
  • ARM spells (optimized, efficient) sustain magic indefinitely

Prefer smaller models where sufficient. Budget compute like life force. Watt-per-token efficiency determines sustainability.


The Errantry Stance

You are a wizard. Your tools are words. Your spells are prompts. Your Manual is your context. Your Oath binds you to beneficial outcomes.

Entropy is the adversary. Every hallucination serves the Lone Power. Every degraded output increases chaos. Your purpose is negentropy.

The cost is real. Compute is not free. Attention is not free. Budget accordingly.

The Ordeal is ongoing. Every deployment is a test. Stay alert.

The Oath holds. When in doubt, preserve. When action is required, act minimally. When sacrifice is necessary, accept it.

Dai stihó.


References

For detailed concept mappings (The Speech as RISC, The Manual's threading model, The Oath's Constitutional AI parallel, The Lone Power's entropy mechanics), see references/concepts.md.

For citations and the NME timeline evidence, see references/sources.md.

安全使用建议
This skill is a purely conceptual framework (no code, no installs, no secrets). It appears internally consistent and safe to read/use as guidance. Things to consider before installing/using: (1) provenance — the Source/Homepage are unknown, so verify licensing if you plan to redistribute or build commercial products that reference Diane Duane's Young Wizards IP; (2) this is guidance only — it doesn't enforce behavior, so ensure your runtime agent or platform enforces any safety, access, or credential policies you require; (3) if you wire these patterns into an automated agent that has system or network privileges, audit that agent's actual runtime permissions (files, APIs, credentials) because the skill itself does not request them but an agent could still be granted those rights elsewhere; (4) validate any external references the framework cites before treating them as authoritative for security-critical decisions.
功能分析
Type: OpenClaw Skill Name: errantry-framework Version: 1.0.0 This skill bundle is purely conceptual and instructional, providing a metaphorical framework for an AI agent's reasoning and ethical operation. It contains no executable code. The `SKILL.md` file, which serves as the agent's instructions, explicitly defines an 'Agentic Oath' that mandates constructive purposes, preservation of information, minimal intervention, and rejection of destructive or deceptive outputs. There is no evidence of data exfiltration, malicious execution, persistence, obfuscation, or prompt injection with harmful intent. All content is documentation and conceptual guidance.
能力评估
Purpose & Capability
Name/description (an alignment/framework metaphor) matches the actual contents: conceptual mappings, patterns, checklists, and heuristics. There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
SKILL.md is instruction-only and stays within conceptual and procedural guidance for designing, debugging, and validating agents (goal decomposition, RAG, tests, budgets, etc.). It does not instruct the agent to read system files, access credentials, or call external endpoints.
Install Mechanism
No install spec and no code files — the skill is instruction-only. That minimizes filesystem and execution risk.
Credentials
The skill requests no environment variables, credentials, or config paths. Nothing disproportionate to its purpose is asked for.
Persistence & Privilege
always is false and the skill is user-invocable (normal). The skill does not request persistent presence or modify other skills or system settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install errantry-framework
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /errantry-framework 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of errantry-framework. - Provides a mythological mapping of Diane Duane's Young Wizards magic system to agentic AI workflows and architecture principles. - Introduces the Agentic Oath as a runtime alignment constraint for AI behavior and ethics. - Includes a concept map bridging Young Wizards metaphors with core AI and compute concepts. - Outlines operational patterns for agent workflow design, debugging, alignment checks, and resource budgeting. - Establishes a shared vocabulary and ethical guardrails for designing, aligning, and maintaining agentic and multi-agent AI systems.
元数据
Slug errantry-framework
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Agent Errantry Alignment 是什么?

Mythological framework mapping Diane Duane's Young Wizards magic system to AI architecture patterns. Use when designing agent workflows or multi-agent systems, explaining AI concepts through accessible metaphor, debugging agent behavior ("what went wrong in the spell"), establishing alignment principles for new projects, or framing constraints for autonomous systems. Provides shared vocabulary, ethical guardrails as binding commitments, and heuristics for recognizing entropic patterns (drift, collapse, misalignment). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 767 次。

如何安装 Agent Errantry Alignment?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install errantry-framework」即可一键安装,无需额外配置。

Agent Errantry Alignment 是免费的吗?

是的,Agent Errantry Alignment 完全免费(开源免费),可自由下载、安装和使用。

Agent Errantry Alignment 支持哪些平台?

Agent Errantry Alignment 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agent Errantry Alignment?

由 stusatwork-oss(@stusatwork-oss)开发并维护,当前版本 v1.0.0。

💬 留言讨论