Claw sync all

Skill Walliiee/agent-harness/skills/claw-sync-all

A drop-in self-improving memory + operations harness for AI agents (OpenClaw / Hermes / Claude Code / Codex). Layered memory, autonomous drift-fixing loop, evals, and one-command DR. Templates + scripts, no secrets.

Install

npx -y skills add Walliiee/agent-harness --skill claw-sync-all

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Scheduled OpenClaw workspace/config/state mirror sync. Runs claw-sync-all.sh through skill-wrapper so DR sync work is observable; cron/launchd-driven, manual use only for sync repair.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

0.9 KB, 158 tokens by cl100k_base, as published. Nobody here has run it

claw-sync-all

Launchd maintenance wrapper for ${OPENCLAW_HOME}/tools/claw-sync-all.sh.

Contract

Primary trigger: $HOME/Library/LaunchAgents/ai.openclaw.claw-sync-all.plist.
Must run through ${OPENCLAW_HOME}/bin/skill-wrapper --skill claw-sync-all --agent main --trigger launchd.
Sync scope and hook behavior live in the wrapped script and wiki/tools/openclaw-dr-defense.md.
Keep the plist as a thin trigger: schedule, wrapper, command, logs.

Verification