ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

wayfound

Lightweight self-supervision that piggybacks on your existing memory system. Adds a simple rubric to SOUL.md and a daily review cron job — no new infrastructure, no parallel systems. Your agent reviews its own day in ~200 tokens, writes findings to memory where they compound naturally, and surfaces issues that need your attention. Use after installing to add the rubric to SOUL.md and set up the daily review. Use when the user asks about quality, performance, or improving how you work.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/cburnette/wayfound
Or

What This Skill Does

Wayfound is a lightweight self-supervision framework designed to help your OpenClaw agent maintain high-quality performance by integrating a structured rubric into your existing SOUL.md file. Rather than adding complex, heavy-weight monitoring infrastructure, Wayfound leverages your existing memory system. By embedding a 3-5 point rubric into your identity file and scheduling a daily review cron job, the agent evaluates its own actions against your established standards at the end of each day. This feedback loop ensures that lessons learned from one day of work directly influence the agent's behavior for the next, allowing performance improvements to compound naturally over time.

Installation

To begin using Wayfound, run the following command in your terminal: clawhub install openclaw/skills/skills/cburnette/wayfound. Once installed, you must perform two manual setup steps. First, edit your SOUL.md file to include a '## Self-Review Rubric' section containing 3-5 concrete, actionable checkpoints. Second, initialize the automated review process by running the cron command: openclaw cron add wayfound:daily-review --schedule "0 23 * * *" --isolated --model cheap --low-thinking. Always ensure you have obtained explicit user approval before scheduling automated tasks.

Use Cases

Wayfound is best utilized for long-term project management, consistent codebase maintenance, and behavioral alignment. It is ideal for users who want their AI agent to be more self-reflective without adding significant latency or cost. It is particularly effective for teams or individuals working on complex tasks where 'drift' in quality or process adherence is a concern. Use this skill when you want to ensure the agent is consistently following your protocols—such as always confirming before deployment or thoroughly documenting code changes.

Example Prompts

  1. "I'm worried my current workflow is getting sloppy. Can you help me set up a Wayfound rubric in my SOUL.md that focuses on better documentation?"
  2. "Review the last week of memory files and tell me if you've been adhering to the standards in our new Wayfound rubric."
  3. "Can you set up the daily review cron job for Wayfound so I can start getting these automated feedback reports?"

Tips & Limitations

To get the most out of Wayfound, keep your rubric checkpoints specific and measurable—vague goals lead to vague reviews. Remember that because this is a self-supervision tool, the agent is essentially 'grading its own exam.' While this is excellent for catching pattern-based mistakes and adherence issues, it cannot replace an external auditor or human oversight for critical safety or security concerns. If you find the agent consistently struggling with specific tasks, use the daily review output to refine your SOUL.md instructions further. Avoid over-complicating the rubric; if you add too many points, the quality of the review may degrade due to token constraints.

Metadata

Author@cburnette
Stars4044
Views0
Updated2026-04-12
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-cburnette-wayfound": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#self-supervision#productivity#automation#quality-assurance#workflow
Safety Score: 4/5

Flags: file-write, file-read