Token Optimization

Reduce OpenClaw per-turn prompt costs by 70%+ through file splitting, prompt caching, context pruning, and model routing. Tested on production setup with 69...

This is a coherent, instruction-only optimization guide, but take precautions before applying it: 1) Back up your ~/.openclaw/workspace and openclaw.json (don't rely on the mv .bak as your only copy). 2) Test changes in a staging or non-production agent first — splitting/removing BOOTSTRAP.md or shrinking AGENTS.md can unintentionally change behavior. 3) Be cautious about caching command outputs or file contents: allowing 'exec' and 'read' to be cached may store sensitive data in prompts that could later be sent to models or logs. 4) Understand heartbeat recommendations — they keep caches warm but can increase calls/costs. 5) Ensure you have the OpenClaw CLI/tools available (session_status, openclaw gateway restart) — the registry metadata doesn't list these but SKILL.md assumes them. If you want further review, provide your current openclaw.json and a list of workspace files (or test changes on a copy) so I can point out exact edits and potential impacts.

Type: OpenClaw Skill Name: token-optimization Version: 1.1.0 The skill bundle provides a legitimate and systematic guide for optimizing token usage and reducing API costs in OpenClaw. It includes instructions for the agent to audit workspace file sizes, split large markdown files (e.g., AGENTS.md, MEMORY.md), and update the 'openclaw.json' configuration to enable prompt caching and context pruning. The commands used (e.g., 'wc', 'mv', 'openclaw gateway restart') and the configuration changes are directly aligned with the stated purpose and do not exhibit signs of malicious intent or data exfiltration.