token-optimization
Skill2 starsChanged 6 months agoMITView on GitHub
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
10 other projects use a version of this.
Adopted by
Most recently taken up by
- QSOLKCB/CLAUDE-SKILLS-AGItheir own version, first seen Nov 8, 2026
- OpenxIntelligence/Coding-Agent-Skillstheir own version, first seen Nov 1, 2026
- okfriansyah-moh/agentic-workflowtheir own version, first seen Oct 25, 2026
- I-Onlabs/claude-code-skillstheir own version, first seen Oct 25, 2026
- andrewalhaj/custom-hermesagenttheir own version, first seen Oct 20, 2026
- bm629/agent-skillstheir own version, first seen Aug 21, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- cwinvestments/memstack★ 433same name
- Hassaan146/claude-skills★ 18same name
- I-Onlabs/claude-code-skills★ 4same name
- OpenxIntelligence/Coding-Agent-Skills★ 4same name
- bm629/agent-skills★ 2same name
- QSOLKCB/CLAUDE-SKILLS-AGI★ 1same name
- andrewalhaj/custom-hermesagent★ 0same name
- ESUnternehmensberatung/ClaudeCode★ 0same name
- muxammadmamajonov/dot-claude★ 0same name
- okfriansyah-moh/agentic-workflow★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analysis-frameworkSkill
- architecture-overviewSkill
- audit-boundariesSkill
- biannianSkill
- communication-protocolsSkill
- dispatch-rulesSkill
- fault-toleranceSkill
- governance-coreSkill
- hanlinSkill
- intent-classificationSkill
- kejuSkill
- morning-courtSkill
- parallel-executionSkill
- permission-matrixSkill
- qijuzhuSkill
- redline-referenceSkill
- report-formatSkill
- review-coverageSkill
- shengzhiSkill
- special-directivesSkill
- team-bootstrapSkill
- ticket-formatSkill
- tuichaoSkill
- veto-mechanismSkill
- zouzheSkill
The file
Files
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
- 会话复用仅限同一
plan_id - 摘要由 Agent 自身生成
- 异常时回退为独立会话模式
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

