尚书省首次调用时加载的 Token 优化策略,定义运行模式拆分、会话复用与上下文管理
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill token-optimization-cheukswiss-etdxm --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Token Optimization Cheukswiss Etdxm?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-token-optimization-cheukswiss-etdxm-claude-skill-registry)More formats (shields.io, HTML) on the badges page.
---
name: token-optimization
description: 尚书省首次调用时加载的 Token 优化策略,定义运行模式拆分、会话复用与上下文管理
---
# Skill: Token 优化策略
> **适用 Agent**:尚书省、系统层
> **加载时机**:尚书省首次调用时(了解自身运行模式)
## 尚书省运行模式
尚书省按职责阶段切换运行模式,每种模式仅加载当前阶段所需的系统提示:
| 运行模式 | 触发条件 | 加载内容 |
|---------|---------|---------|
| **dispatch** | 收到 `approved_plan` | 核心身份 + Skill `dispatch_rules` |
| **coordinate** | 六部执行中,需协调或汇总 | 核心身份 + Skill `communication_protocols` + Skill `fault_tolerance` |
| **report** | 门下覆奏通过 | 核心身份 + Skill `report_format` |
## 会话复用
同一 `plan_id` 生命周期内,Agent 多次调用复用同一会话,后续调用以追加消息继续对话。
## 上下文摘要
会话上下文 ≥ 模型窗口 70% 时,Agent 自动生成摘要,以「核心身份 + 摘要」开启新会话。摘要须包含:当前阶段、关键决策、待办事项、阻塞项、各子任务状态。
## 约束
1. 会话复用仅限同一 `plan_id`
2. 摘要由 Agent 自身生成
3. 异常时回退为独立会话模式
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...