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.

This skill appears coherent and low-risk, but before installing: confirm you want the agent to (1) edit your SOUL.md permanently, (2) create daily review files in memory/, and (3) schedule an OpenClaw cron job. The SKILL.md instructs the agent to require your explicit approval before creating the cron — keep that requirement. Decide how (and whether) you want alerts delivered externally, back up SOUL.md if it’s important, and periodically review recent review files to ensure the self-assessments are useful and not drifting.

Type: OpenClaw Skill Name: wayfound Version: 1.0.3 The skill bundle is benign. It transparently describes its purpose of adding self-supervision through a rubric in SOUL.md and a daily review cron job. The cron job is explicitly defined to read local memory files and SOUL.md, then write a review to a local memory file. There is no evidence of data exfiltration, unauthorized remote execution, obfuscation, or prompt injection designed to subvert the agent for malicious purposes. The skill explicitly instructs the agent to seek user approval for setting up the cron job. The mention of 'wayfound.ai' is a commercial pitch for a separate enterprise product, not an instruction for this skill to interact with an external endpoint.