Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Updated description to highlight up to 70% savings and that no coding is required. - No code or file changes; documentation improvements only. - Clarified value proposition in the skill summary for better user visibility.
What This Skill Does
Manifest is an OpenClaw plugin that routes each LLM request to the most cost-effective model using a 23-dimension scoring algorithm with under 2ms added latency. It tracks spend, token usage, and agent activity in a real-time dashboard, and supports hard spending caps with email alerts.
Routing and cost tracking would otherwise require custom code and separate dashboards; Manifest adds both as a no-config plugin with 300+ model coverage.
When to use it
- Cutting monthly LLM costs by routing simple queries to cheaper models
- Checking which model is consuming the most budget this week
- Setting a hard spending cap before a client project starts
- Asking the agent mid-conversation how many tokens it has used today
- Diagnosing rate limit errors through the message log and error filters
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: how much have I spent this week and which model cost the most?
- 1Invokes manifest_costs tool with period set to "week"
- 2Retrieves cost breakdown by model in USD
- 3Identifies the highest-cost model from the returned data
- 4Summarizes total spend and top model for the user
A cost breakdown listing total weekly spend and the most expensive model, pulled from the agent's own usage data
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.