openclaw-agent-optimize
Use when: you want to optimize an OpenClaw setup (cost/quality tradeoffs, model routing, context discipline, delegation, reliability) and you’re okay with a structured audit → options → recommended plan. Don’t use when: you want immediate config mutations without review, or the question is unrelated to OpenClaw operations. Output: a prioritized plan + exact change proposals (with rollback) if approved.
Why use this skill?
Audit your OpenClaw setup for cost-aware routing and context bloat. Get prioritized improvement plans, exact change proposals, and rollbacks.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/phenomenoner/openclaw-agent-optimizeWhat This Skill Does
The openclaw-agent-optimize skill acts as an architectural consultant for your OpenClaw environment. Rather than performing blind operations, it audits your existing configuration, skill set, and context usage to identify inefficiencies. It evaluates your current setup against industry best practices for cost, model selection, and context management. The skill provides a structured decision-making framework, delivering a prioritized list of proposed changes alongside concrete patch snippets and, crucially, specific rollback instructions. It ensures your agent workspace remains performant without sacrificing reliability.
Installation
You can integrate this skill into your environment by running the following command in your terminal:
clawhub install openclaw/skills/skills/phenomenoner/openclaw-agent-optimize
Ensure you restart your session or trigger a watcher refresh to load the skill metadata correctly. It is designed to work seamlessly with OpenClaw 2.9+.
Use Cases
- Cost Control: Reducing token usage by identifying heavy models and routing non-critical tasks to smaller, more efficient LLMs.
- Context Cleanup: Analyzing long-running sessions that suffer from degradation due to excessive transcript history, file bloat, or recurring cron logs.
- Operational Efficiency: Transforming chatty automation loops into silent-on-success processes to keep your human-facing interface clean.
- Delegation Strategy: Establishing clear protocols for when the agent should handle tasks autonomously versus when it should delegate to specific sub-skills.
Example Prompts
- "Audit my OpenClaw setup for cost, reliability, and context bloat. Output a prioritized plan with rollback notes. Do NOT apply changes."
- "My OpenClaw context is bloating. Identify the top offenders among my current tools and bootstrap files and propose the smallest reversible fixes first."
- "Propose a model routing plan for (a) coding/engineering tasks, (b) short notifications, and (c) research writing. Include an exact config patch."
Tips & Limitations
This skill is advisory. It does not execute modifications to your production environment autonomously. You must review the change proposal and explicitly approve any patch. For high-ROI, focus on implementing 'silent-on-success' outputs for cron jobs. If you are handling sensitive environment variables, ensure you have correctly configured the sandbox environment, as this skill does not mirror host-level secrets automatically. Always verify the rollback steps provided before applying any persistent configuration patch.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-phenomenoner-openclaw-agent-optimize": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read
Related Skills
context-scope-tags
Use when: you need strict context boundaries in chat (Telegram/Discord/Slack/etc.) and want to prevent topic bleed using explicit tags like [ISO], [SCOPE], [GLOBAL], [NOMEM], [REM]. Don’t use when: you want normal free-form conversation with automatic carry-over. Output: a copy/paste tag cheat sheet + routing rules.
openclaw-agent-token-optimizer
DEPRECATED — duplicate listing. Please use the canonical "openclaw-agent-optimize" skill instead.
cron-worker-guardrails
Use when hardening OpenClaw cron workers (especially isolated agentTurn jobs) against quoting failures, brittle shell patterns, SIGPIPE false failures, and cwd/env drift. Output: a scripts-first hardening checklist + portable patterns.
context-clean-up
Use when: you suspect OpenClaw prompt context is bloating (slow replies, high cost, repeated transcript noise) and you want a ranked offender list + a reversible clean-up plan. Don’t use when: you want the assistant to apply fixes automatically, or you’re asking for unrelated troubleshooting. Output: an audit summary + 3–8 concrete fix steps + rollback notes (no automatic changes).
openclaw-agent-optimize-skill
DEPRECATED — duplicate listing. Please use the canonical "openclaw-agent-optimize" skill instead.