OpenClaw Skill Lazy Loader

Stop loading every skill file at session start. Load what you need, when you need it — and cut your token usage by 40–70%.

The Problem

Most OpenClaw agents load their entire skill library at startup:

CODEBLOCK0

Each session burns 3,000–15,000 tokens just loading context that may never be used. At scale, this is your biggest cost.

The Solution: Lazy Loading

Instead of loading skills upfront, agents check a SKILLS catalog (a lightweight index) and load individual skill files only when a task requires them.

Before: Load 20 skill files = ~12,000 tokens/session
After: Load catalog (300 tokens) + 1–2 relevant skills (~800 tokens) = ~1,100 tokens/session

That's an 89% reduction on context loading alone.

Implementation Guide

Step 1: Create Your SKILLS Catalog

Create SKILLS.md in your agent workspace — a lightweight index of all available skills:

CODEBLOCK1

This catalog is the ONLY file loaded at session start. ~200–400 tokens instead of 10,000+.

See SKILLS.md.template for a complete starter template.

Step 2: Update Your AGENTS.md

Replace bulk loading with the catalog pattern:

CODEBLOCK2

See AGENTS.md.template for the full recommended AGENTS.md skills section.

Step 3: Use the Context Optimizer (Optional)

The included context_optimizer.py analyzes your task description and recommends which skills to load:

CODEBLOCK3

Step 4: Apply to Memory Files Too

The same pattern works for memory and context files:

CODEBLOCK4

Token Savings Calculator

Estimates based on average SKILL.md size of ~600 tokens. Catalog averages ~150 tokens.

Integration with Token Optimizer

This skill pairs directly with OpenClaw Token Optimizer. Lazy loading handles context loading costs; Token Optimizer handles model routing, heartbeat budgeting, and runtime costs. Together they cover the full token lifecycle.

Install both:

clawhub install openclaw-skill-lazy-loader
clawhub install openclaw-token-optimizer

Files in This Skill

Quick Start (5 minutes)

CODEBLOCK6