Save Token

save-token 1.0.1 Changelog - Clarified that this is a guiding skill; it offers advice and strategies but does not modify agent runtime context directly. - Added detailed explanations and examples of token-saving strategies for agents to follow. - Improved documentation for both English and Chinese readers. - Removed references to direct automated deduplication; agents are now expected to apply guidance themselves. - Deleted the scripts/dedupe.js file as code-based deduplication is no longer part of the skill.

Initial release of save-token skill. - Automatically deduplicates repeated content in conversation context before each task, reducing token consumption. - Removes duplicate blocks (≥100 characters) and keeps only the first occurrence. - Supports deduplication for user messages, assistant responses, tool outputs, and file contents (not system prompts). - Reports the amount of tokens saved after optimization. - Triggers automatically under high token cost, long conversations, repeated file reads, or before complex tasks; can also be called manually. 在每次任务执行前自动去重上下文中的重复内容。 通过删除重复文本块（仅保留一份），在保证上下文完整性的同时降低 Token 消耗。