※v2026.3.11.1** | OpenClaw v2026.3.11 に準ずる | CLI-first Advisor

[!警告] メンテナンスサンセットのお知らせ ツイート OpenClawを自分のエージェントソリューションに移行したので、このプロジェクトはもはや積極的に維持されていない。 この[v2026.3.11.1]リリースは最終更新です。 ツイート 私は、ユーザーがこのリポジトリをフォークし、必要に応じてOpenClawの将来のリリースのためのスキルを更新し続けることを強くお勧めします。 このオプティマイザに使用して貢献した皆様、ありがとうございました!

OpenClaw のセットアップを「動作する」からチューニング、コスト効率、自己文書化システムに変えるAIスキル。 あなたが持っていることを監査します。, 正確に変更する何を伝えます, あなたがコミットする前にロールバックコマンドを表示, そして、それがあなたの展開について学ぶすべてのことを覚えておいてください。 – 恒久的に, セッション全体で, ツール.

免責事項: この技術はAI主導のアドバイザーです。 どのAIモデルがスキルを発揮し、モデル、バージョン、デプロイメントと異なる結果が生成されます。 ※応募前に、全ての行為・推奨事項を点検・確認する責任があります.

The OpenClaw Optimizer

v2026.3.11.1 | Aligned with OpenClaw v2026.3.11 | CLI-first advisor

[!WARNING] 🌅 Maintenance Sunset Notice

As I have transitioned off OpenClaw to my own agentic solution, this project is no longer actively maintained. This v2026.3.11.1 release is the final update.

I highly encourage users to fork this repository and continue updating the skill for future releases of OpenClaw as needed. Thank you to everyone who has used and contributed to this optimizer!

An AI skill that turns your OpenClaw setup from “it works, I think” into a tuned, cost-efficient, self-documenting system. It audits what you have, tells you exactly what to change, shows you the rollback command before you commit, and remembers everything it learns about your deployment – permanently, across sessions, across tools.

Disclaimer: This skill is an AI-driven advisor. Its recommendations are generated by whichever AI model runs the skill, and results may vary between models, versions, and deployments. You are responsible for inspecting and confirming every action and recommendation before applying it. The authors assume no liability for any damage, data loss, misconfiguration, or unexpected costs resulting from the use of this skill. Use at your own risk.

---

Overview Demo

---

Why This Exists

Most OpenClaw users are running with default model routing (expensive), bloated bootstrap files (burning tokens every turn), cron jobs piling up on the same minute (thundering herd), and no idea that a stuck delivery queue is silently saturating their gateway’s event loop.

This skill finds all of that. Then it fixes it – but only when you say so.

---

Highlights

50-95% Cost Reduction Through Tiered Routing

Not every request needs Opus. The skill builds a 4-tier routing plan that sends heartbeats and cron to the cheapest models, daily tasks to mid-tier, and reserves premium models for coding and orchestration. Exact config and rollback commands included.

40+ Model Providers, Ready to Go

Anthropic, OpenAI, OpenAI Codex (subscription-based OAuth with GPT-5.4), Google Gemini, Google Vertex AI, Moonshot/Kimi, Kimi Coding, KiloCode, Groq, xAI, OpenRouter, Bedrock, Together AI, Cerebras, Hugging Face, Ollama, vLLM, MiniMax, Venice, Z.AI, Synthetic, OpenCode Zen, OpenCode Go, and more. Each with the exact CLI commands to authenticate, configure, and add to your fallback chain. Includes provider ban warnings for Google (AntiGravity/Gemini CLI) and Anthropic (Claude Code tokens).