Install
openclaw skills install save-token💰 Save Token | Token 节省器 TRIGGERS: Use when token cost is high, conversation is long, files read multiple times, or before complex tasks. Guiding skill that...
openclaw skills install save-tokenA guiding skill that teaches agents how to save tokens by avoiding duplicate context.
指导 Agent 如何通过避免重复上下文来节省 Token 的技能。
| Clarification | 说明 |
|---|---|
| This is a guiding skill | Skill itself cannot modify agent's runtime context |
| Agent performs the action | Agent follows the guidance to optimize context |
| 这是一个指导性 Skill | Skill 本身不能修改 Agent 的运行时上下文 |
| 由 Agent 执行操作 | Agent 遵循指导来优化上下文 |
Agent 自动触发条件(满足任一即应调用):
| Situation | Action | 场景 | 操作 |
|---|---|---|---|
| User mentions "token" or "cost" | Apply save-token strategies | 用户提到 token 或成本 | 应用 save-token 策略 |
| Long conversation (>10 turns) | Summarize old context | 长对话(>10轮) | 摘要旧上下文 |
| File read multiple times | Reference previous read, don't re-read | 文件被多次读取 | 引用之前的读取,不重复读取 |
| Repeated error messages | Summarize error pattern, don't repeat full error | 重复错误消息 | 摘要错误模式,不重复完整错误 |
When: Old conversation context is no longer directly relevant 当:旧对话上下文不再直接相关时
Do:
做法:
Example:
❌ Bad: Re-sending 50 turns of conversation (10,000+ tokens)
✅ Good: "Previous context: User was analyzing stock investment strategies.
Key decisions made: prioritize low P/E, check cash flow.
Now focusing on: specific company analysis."
When: Same file/content needs to be referenced again 当:需要再次引用同一文件/内容时
Do:
做法:
Example:
❌ Bad: Reading the same 200KB file again
✅ Good: "As we found earlier in the file, the revenue is $50M..."
When: Identical text appears multiple times in context 当:相同文本在上下文中多次出现时
Do:
做法:
Example:
❌ Bad: Same error message appears 5 times (500 chars × 5 = 2500 chars)
✅ Good: "[Error message appeared 5 times, showing once]: Connection timeout..."
When: Tool output or file content is very long 当:工具输出或文件内容很长时
Do:
做法:
Example:
❌ Bad: Including full 1000-line log file
✅ Good: "Log file (1000 lines): Key errors on lines 45, 78, 234.
Pattern: Connection drops every 5 minutes. Full log available if needed."
1. Agent receives task
2. Agent checks context size and duplicate content
3. If context > threshold OR duplicates found:
a. Apply appropriate strategy from above
b. Report token savings to user
4. Proceed with optimized context
When applying token-saving strategies, inform the user:
💡 Token Optimization Applied:
- Strategy: [Strategy Name]
- Context before: X tokens
- Context after: Y tokens
- Saved: Z tokens (P%)
| Cannot Do | Reason | 不能做 | 原因 |
|---|---|---|---|
| Directly modify context | Skill is guidance, not execution | 直接修改上下文 | Skill 是指导,不是执行 |
| Automatically delete content | Agent must decide what to keep | 自动删除内容 | Agent 必须决定保留什么 |
| Guarantee exact savings | Depends on implementation | 保证精确节省量 | 取决于实现方式 |
| Does | Description | 能做 | 描述 |
|---|---|---|---|
| Provide strategies | Teaches how to save tokens | 提供策略 | 教如何节省 Token |
| Identify opportunities | Helps recognize when to apply | 识别机会 | 帮助识别何时应用 |
| Guide implementation | Shows best practices | 指导实现 | 展示最佳实践 |