OpenClaw Skill Lazy Loader

Dramatically reduce per-session token usage by loading skills and context files only when needed — not at session start. Includes the SKILLS catalog pattern,...

This skill is internally consistent and appears to do what it says: provide a catalog pattern and a local Python helper that recommends which skill files to load. Before installing, review the SKILLS.md you create and the individual SKILL.md files it points to (those files are what your agent will later load and act upon). Confirm the .clawhubsafe hashes if you need provenance assurance and be aware that lazy loading reduces token costs but does not reduce the need to trust the actual per-skill SKILL.md contents the agent may load later.

Type: OpenClaw Skill Name: openclaw-skill-lazy-loader Version: 1.0.0 The OpenClaw Skill Lazy Loader is designed to optimize token usage by implementing a lazy loading strategy for agent skills and memory files. All documentation (`SKILL.md`, `AGENTS.md.template`, `SKILLS.md.template`) provides clear, benign instructions for the agent and user to achieve this efficiency. The `context_optimizer.py` script is a local utility that recommends skills based on task descriptions, and its code strictly adheres to its stated security properties: no network access, no subprocess execution, and no file writes. The presence of a detailed `SECURITY.md` file, explicitly outlining the skill's limitations and safety, further reinforces its benign nature. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found.