Token Optimizer

If your OpenClaw agent is burning through tokens on background tasks or re-reading entire histories every turn, this is the fix. It walks you through isolating cron jobs to separate sessions, setting up local RAG with memory_search to pull only what you need, and running a "Reset & Summarize" protocol when context bloats past 100k tokens. The documentation is practical, with actual config snippets for openclaw.json and a clear troubleshooting section. Written by Pépère and Zayan, it treats token management as infrastructure work, not an afterthought. Most useful once you've hit the pain point of sluggish responses or surprise context overflows.

skills.sh installs: 504
GitHub stars: 20
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add d4kooo/openclaw-token-memory-optimizer --skill token-optimizer --agent claude-code

Installs into .claude/skills of the current project.

Files

Token Optimizer Skill

This skill provides the procedural knowledge to keep your OpenClaw instance lean and efficient.

Quick Reference

Problem	Solution
Background tasks bloating context	Cron isolation (`sessionTarget: "isolated"`)
Reading entire history every turn	Local RAG with `memory_search`
Context exceeds 100k tokens	Reset & Summarize protocol
Finding old conversations	Session transcript indexing

Workflow 1: Periodic Task Isolation

To prevent background tasks from bloating your main conversation context, always isolate them.

Steps

Locate your openclaw.json config.
In the cron.jobs array, set sessionTarget: "isolated" for any task that doesn't need to be part of the main chat history.
Use the message tool within the task's payload if human intervention is required.