# Send Agent Errantry Alignment to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "errantry-framework",
    "name": "Agent Errantry Alignment",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/stusatwork-oss/errantry-framework",
    "canonicalUrl": "https://clawhub.ai/stusatwork-oss/errantry-framework",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/errantry-framework",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=errantry-framework",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "references/concepts.md",
      "references/sources.md",
      "SKILL.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "errantry-framework",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T05:54:30.003Z",
      "expiresAt": "2026-05-06T05:54:30.003Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=errantry-framework",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=errantry-framework",
        "contentDisposition": "attachment; filename=\"errantry-framework-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "errantry-framework"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/errantry-framework"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/errantry-framework",
    "downloadUrl": "https://openagent3.xyz/downloads/errantry-framework",
    "agentUrl": "https://openagent3.xyz/skills/errantry-framework/agent",
    "manifestUrl": "https://openagent3.xyz/skills/errantry-framework/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/errantry-framework/agent.md"
  }
}
```
## Documentation

### 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 WizardsAgentic AIFunctionThermodynamic NoteThe SpeechZero-hallucination prompting / RISC semanticsOntology & executionAmbiguity is compute debtTrue NameVector embedding / State representationEntity representationFidelity costs tokensWizard's ManualAgentic RAG / OrchestratorKnowledge retrievalLive > frozenWizard's OathConstitutional AIAlignment frameworkPrinciples > rulesThe Lone PowerMisaligned AGI / EntropyAdversarial patternEntropy always increasesThe ChoiceReward hacking / Shortcut temptationTemptation patternTechnical debt is entropySpells / DiagramsAgentic workflows / DAGsExecution protocolsPrecision reduces costThe OrdealRed-teaming / Adversarial evaluationValidation testingTest at full capabilityTrue Name editingPrompt injection / Weight editingSystem modificationHigh-risk operationWorldgatesAPIs / Inter-system communicationIntegration pointsBoundary = attack surfaceThermodynamic costInference cost / Compute budgetResource constraintWatt-per-token mattersYoung wizard powerModel plasticity / Early trainingCapability vs. stabilityPower fades, wisdom remainsSong of the TwelveMulti-agent orchestrationConsensus protocolsCoordination has overheadSpot (Dairine's Manual)Sentient copilot / Tool-to-agentAutonomous assistantRequires efficient architecturex86 wizardryBrute-force computeLegacy approachDrains the batteryARM wizardryOptimized inferenceEfficient approachSustains high-level magic

### Pattern: Spell Construction (Workflow Design)

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

Does this sacrifice accuracy for speed?
Does this sacrifice completeness for convenience?
Does this create technical debt?
Does this train on synthetic data without validation?
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.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: stusatwork-oss
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-04-29T05:54:30.003Z
- Expires at: 2026-05-06T05:54:30.003Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/errantry-framework)
- [Send to Agent page](https://openagent3.xyz/skills/errantry-framework/agent)
- [JSON manifest](https://openagent3.xyz/skills/errantry-framework/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/errantry-framework/agent.md)
- [Download page](https://openagent3.xyz/downloads/errantry-framework)