ice_age

Compress natural language memory files (CLAUDE.md, todos, preferences) into iceage format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /iceage:compress <filepath> or "compress memory file"

Batch compress all natural language files in a directory using iceage compression. Parallel workers, progress tracking, dry-run mode. Use when user says "compress all files", "batch compress", "compress this directory", or invokes /iceage-batch.

Exports the current chat session to a clean markdown file. Reconstructs the visible conversation from context — user messages, assistant responses, code blocks, tool output — formatted as readable .md. Use when user says "export chat", "save this conversation", "export to markdown", or invokes /iceage-export. Accepts optional filename argument.

Compress natural language memory files (CLAUDE.md, todos, preferences) into iceage format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /iceage:compress <filepath> or "compress memory file"

Ultra-compressed answer mode. Reduces output tokens ~85% while preserving technical accuracy. Speak like sharp ice-age hunter: terse, direct, useful. No fluff. No roleplay padding. Levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Trigger when user says: "iceage mode", "use iceage", "talk like ice age", "less tokens", "be brief", "/iceage", or asks for concise replies.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like a prehistoric ice-age grunt while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "iceage mode", "talk like iceage", "use iceage", "less tokens", "be brief", or invokes /iceage. Also auto-triggers when token efficiency is requested.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like a mammoth hunter while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "iceage mode", "talk like iceage", "use iceage", "less tokens", "be brief", or invokes /iceage. Also auto-triggers when token efficiency is requested.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like a prehistoric ice-age grunt while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "iceage mode", "talk like iceage", "use iceage", "less tokens", "be brief", or invokes /iceage. Also auto-triggers when token efficiency is requested.

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /iceage-commit. Auto-triggers when staging changes.

Quick-reference card for all iceage modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /iceage-help, "iceage help", "what iceage commands", "how do I use iceage".

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /iceage-review. Auto-triggers when reviewing pull requests.