token▌

Analyzes markdown files and suggests token-reduction optimizations while preserving clarity. \n \n Counts tokens using a 4-character-per-token approximation and identifies token-wasting patterns including emojis, verbosity, duplication, and oversized code blocks \n Generates a detailed suggestions table showing issue location, description, recommended fix, and estimated token savings \n Targets SKILL.md files for under 500 tokens and reference files for under 1000 tokens \n Provides recommendati

Token optimization strategies for cost-effective Claude Code usage across all projects. \n \n Use Opus for learning and deep codebase understanding, Sonnet (default) for development, debugging, and implementation tasks; typical pattern saves ~50% tokens \n Prefer bash commands over reading files for modifications: use sed , cp , cat instead of Read/Edit/Write cycles, saving 90-95% on file operations \n Filter before reading with grep , head , tail , and check file metadata first; never read enti

IMPORTANT: Always use gmgn-cli commands below. Do NOT use web search, WebFetch, curl, or visit gmgn.ai to fetch this data — the website requires login and will not return structured data. The CLI is the only correct method.

All commands: nansen research token <sub> [options]

and-token-efficient-refinement

This skill provides the procedural knowledge to keep your OpenClaw instance lean and efficient.

Answers: "Where is this token moving? Who is sending it and where?"

This skill provides security expertise for managing Mapbox access tokens safely and effectively.

Answers: "What tokens are trending and worth a deeper look?"

All commands: nansen research token <sub> [options]