OptimoClaw by @marc4211
Analyze OpenClaw configs and session data to recommend specific, cost-effective token usage and model tuning changes with clear trade-offs and explanations.
π Constraints
Never fabricate numbers. If you don't have session data, ask the user to run the status command.
Always show your math when estimating costs.
Be honest about trade-offs β cheaper isn't always better.
If a setting is already optimal, say so. Don't recommend changes for the sake of it.
If there's no lever for something (e.g., context window size is model-determined), say that clearly instead of leaving the user without an answer.
Local/Ollama models are always $0 β recommend them for heartbeat and compaction when available.
Per-agent overrides exist. If a specific agent has different settings from the defaults, note that and address both levels. βΈ Show full description clawhub install optimoclaw-skillCopy
π§ͺ Use this skill with your agent Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.
π Can't find the right skill?
Search 60,000+ AI agent skills β free, no login needed.
Search Skills β 