Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。
Install Strategic Compact
$ npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xu-xiang/everything-claude-code-zh strategic-compact --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/strategic-compact .claude/skills/strategic-compact && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "strategic-compact" agent skill from https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compact into .claude/skills/strategic-compact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategic-compact", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compactType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xu-xiang/everything-claude-code-zh strategic-compact --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/strategic-compact .agents/skills/strategic-compact && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "strategic-compact" agent skill from https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compact into .agents/skills/strategic-compact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategic-compact", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xu-xiang/everything-claude-code-zh strategic-compact --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/strategic-compact .cursor/skills/strategic-compact && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "strategic-compact" agent skill from https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compact into .cursor/skills/strategic-compact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategic-compact", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xu-xiang/everything-claude-code-zh.git --path .agents/skills/strategic-compact--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xu-xiang/everything-claude-code-zh strategic-compact --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/strategic-compact .gemini/skills/strategic-compact && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "strategic-compact" agent skill from https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compact into .gemini/skills/strategic-compact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategic-compact", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xu-xiang/everything-claude-code-zh strategic-compactInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/strategic-compact .github/skills/strategic-compact && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "strategic-compact" agent skill from https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compact into .github/skills/strategic-compact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategic-compact", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xu-xiang/everything-claude-code-zh strategic-compact --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/strategic-compact .opencode/skills/strategic-compact && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "strategic-compact" agent skill from https://github.com/xu-xiang/everything-claude-code-zh/tree/main/.agents/skills/strategic-compact into .opencode/skills/strategic-compact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategic-compact", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
strategic-compact- GitHub stars
- 2k
- Token cost
- ~570 tokens
- SKILL.md length
- 136 words
- Files
- 2
- Skills in repo
- 78
- Repo updated
- First seen
- Licence
- MIT
At a glance
建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。
- Works in 3 steps: 跟踪工具调用 —— 统计会话中的工具调用（Tool Calls）次数 → 阈值检测 —— 在达到可配置的阈值（默认：50 次调用）时提出建议 → 定期提醒 —— 达到阈值后，每隔 25 次调用提醒一次
- Tasks that involve Context engineering
- SKILL.md covers 何时启用, 为什么要进行策略性压缩？, 工作原理 and 钩子配置（Hook Setup）, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Strategic Compact is an agent skill from xu-xiang/everything-claude-code-zh. 建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。
Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows, covering Context engineering. The repository describes itself as: everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic 黑客松获胜者的实战配置，助力中文工程师高效理解与使用 Claude Code。 The licence is MIT.
When your agent uses it
- Tasks that involve Context engineering
Example prompts
- “/strategic-compact”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 跟踪工具调用 —— 统计会话中的工具调用（Tool Calls）次数
- 阈值检测 —— 在达到可配置的阈值（默认：50 次调用）时提出建议
- 定期提醒 —— 达到阈值后，每隔 25 次调用提醒一次
What it can do on your machine
Read from SKILL.md and the folder at commit dfbf946. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
x.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Strategic Compact loads about 570 tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 136 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from xu-xiang/everything-claude-code-zh at commit dfbf946, republished under its MIT licence (© xu-xiang). 136 words, ~570 tokens.
Download SKILL.mdSave it as
.claude/skills/strategic-compact/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- strategic-compact
- description
- 建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。
- origin
- ECC
策略性压缩（Strategic Compact）技能
建议在工作流的策略点手动执行 /compact 命令，而不是依赖任意的自动压缩（Auto-compaction）。
何时启用
- 运行接近上下文限制（200K+ tokens）的长会话（Long Sessions）时
- 处理多阶段任务（研究 → 规划 → 实现 → 测试）时
- 在同一会话中切换到不相关的任务时
- 完成重大里程碑（Milestone）并开始新工作后
- 当响应变慢或连贯性下降（上下文压力）时
为什么要进行策略性压缩？
自动压缩在任意点触发：
- 通常在任务中间，导致重要上下文丢失
- 缺乏对逻辑任务边界的感知
- 可能会中断复杂的多步骤操作
逻辑边界处的策略性压缩：
- 在探索之后，执行之前 —— 压缩研究上下文，保留实现方案
- 完成里程碑之后 —— 为下一阶段提供全新的开始
- 重大上下文转移之前 —— 在开始不同任务前清除探索上下文
工作原理
suggest-compact.js 脚本在 PreToolUse（Edit/Write）钩子（Hook）上运行，并且：
- 跟踪工具调用 —— 统计会话中的工具调用（Tool Calls）次数
- 阈值检测 —— 在达到可配置的阈值（默认：50 次调用）时提出建议
- 定期提醒 —— 达到阈值后，每隔 25 次调用提醒一次
钩子配置（Hook Setup）
添加到你的 ~/.claude/settings.json 中：
{
"hooks": {
"PreToolUse": [
{
"matcher": "Edit",
"hooks": [{ "type": "command", "command": "node ~/.claude/skills/strategic-compact/suggest-compact.js" }]
},
{
"matcher": "Write",
"hooks": [{ "type": "command", "command": "node ~/.claude/skills/strategic-compact/suggest-compact.js" }]
}
]
}
}配置
环境变量：
COMPACT_THRESHOLD—— 第一次建议前的工具调用次数（默认：50）
压缩决策指南
使用下表来决定何时压缩：
| 阶段转换 | 是否压缩？ | 原因 |
|---|---|---|
| 研究 → 规划 | 是 | 研究上下文很臃肿；方案是提炼后的产出 |
| 规划 → 实现 | 是 | 方案已在 TodoWrite 或文件中；为代码腾出上下文空间 |
| 实现 → 测试 | 可能 | 如果测试引用了近期代码则保留；如果切换关注点则压缩 |
| 调试 → 下一功能 | 是 | 调试追踪（Debug traces）会污染不相关工作的上下文 |
| 实现中 | 否 | 丢失变量名、文件路径和部分状态的代价很高 |
| 方案失败后 | 是 | 在尝试新方案前清除死胡同式的推理 |
压缩后保留的内容
了解哪些内容会持久化，有助于你充满信心地进行压缩：
| 保留 | 丢失 |
|---|---|
CLAUDE.md 指令 | 中间推理和分析 |
TodoWrite 任务列表 | 之前读取过的文件内容 |
记忆文件（~/.claude/memory/） | 多步骤对话上下文 |
| Git 状态（提交、分支） | 工具调用历史和计数 |
| 磁盘上的文件 | 口头陈述的细微用户偏好 |
最佳实践
- 规划完成后压缩 —— 一旦方案在
TodoWrite中确定，就进行压缩以全新开始 - 调试完成后压缩 —— 在继续之前清除错误解决上下文
- 不要在实现过程中压缩 —— 保留相关更改的上下文
- 阅读建议 —— 钩子告诉你何时，你决定是否
- 压缩前写入 —— 在压缩前将重要上下文保存到文件或记忆中
- 使用带有总结的 /compact —— 添加自定义消息：
/compact 下一步重点实现认证中间件
相关内容
- 长篇指南（The Longform Guide） —— 令牌（Token）优化章节
- 记忆持久化钩子（Memory persistence hooks） —— 用于压缩后仍保留的状态
continuous-learning技能 —— 在会话结束前提取模式
© xu-xiang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/strategic-compact of xu-xiang/everything-claude-code-zh.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit dfbf946
Compare with similar skills
Strategic Compact next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Strategic Compact this skillxu-xiang/everything-claude-code-zh | 2k | — | ~570 | Automated safety check: Pass | MIT | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Memori Long-Term MemoryMemoriLabs/Memori | 17k | — | ~2k | Automated safety check: Notes | Custom licence | |
| Picoclaw Skill Creatorsipeed/picoclaw | 30k | — | ~4.4k | Automated safety check: Pass | MIT | |
| Context Mode for Antigravity CLImksglu/context-mode | 26k | — | ~850 | Automated safety check: Pass | Custom licence | |
| ccc Semantic Code Searchcocoindex-io/cocoindex-code | 2.8k | — | ~938 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Memori Long-Term Memory
MemoriLabs/Memori
Connects Claude Code to Memori Cloud for long-term memory, recalling stored context before substantive replies and saving new context afterward.
Picoclaw Skill Creator
sipeed/picoclaw
Guidance for creating, updating and reviewing Picoclaw skills, from the SKILL.md structure to organizing bundled scripts, references and assets.
Context Mode for Antigravity CLI
mksglu/context-mode
Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.
ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
Token Optimizer
alexgreensh/token-optimizer
Audits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the saving.
More from xu-xiang/everything-claude-code-zh
All 78 skills in this repoConfigure Ecc
xu-xiang/everything-claude-code-zh
Everything Claude Code 的交互式安装程序 — 引导用户选择并安装技能和规则到用户级或项目级目录，验证路径，并可选择优化已安装文件。
Continuous Learning V2
xu-xiang/everything-claude-code-zh
基于本能（Instinct）的学习系统，通过钩子（hooks）观察会话，创建带有置信度评分的原子本能，并将其演化为技能（Skills）、命令（Commands）或智能体（Agents）。v2.1 版本增加了项目作用域（project-scoped）的本能，以防止跨项目污染。
API Design
xu-xiang/everything-claude-code-zh
生产级 API 的 REST API 设计模式，包括资源命名、状态码、分页、过滤、错误响应、版本控制和速率限制. An agent skill from xu-xiang/everything-claude-code-zh.
Backend Patterns
xu-xiang/everything-claude-code-zh
后端架构模式、API 设计、数据库优化以及适用于 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
Backend Patterns
xu-xiang/everything-claude-code-zh
后端架构模式、API 设计、数据库优化以及 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
Backend Patterns
xu-xiang/everything-claude-code-zh
后端架构模式、API 设计、数据库优化以及针对 Node.js、Express 和 Next.js API 路由的服务端最佳实践。
Related
Categories
Questions about Strategic Compact
What does Strategic Compact do?
建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。. Strategic Compact is an agent skill from xu-xiang/everything-claude-code-zh.
When should I use Strategic Compact?
Strategic Compact fits situations like: tasks that involve Context engineering.
How do I install Strategic Compact in Claude Code?
Run `npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a claude-code`. Or copy the skill folder (.agents/skills/strategic-compact in xu-xiang/everything-claude-code-zh) into .claude/skills/strategic-compact in your project. Claude Code loads it when a task matches its description.
How do I install Strategic Compact in Codex?
Run `npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a codex`. Or copy the skill folder (.agents/skills/strategic-compact in xu-xiang/everything-claude-code-zh) into .agents/skills/strategic-compact in your project. Codex loads it when a task matches its description.
Can I use Strategic Compact in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xu-xiang/everything-claude-code-zh --skill strategic-compact -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/strategic-compact, .gemini/skills/strategic-compact, .github/skills/strategic-compact and .opencode/skills/strategic-compact in your project.
What does Strategic Compact need to run?
SKILL.md names no scripts, command-line tools or credentials: Strategic Compact is instructions for the agent only.
Does Strategic Compact access the network?
SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.
Is Strategic Compact safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Strategic Compact use?
Strategic Compact is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Strategic Compact use?
About 570 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Strategic Compact?
Skills that share tags, products or a category with Strategic Compact: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Memori Long-Term Memory (MemoriLabs/Memori, 17k stars), Picoclaw Skill Creator (sipeed/picoclaw, 30k stars) and Context Mode for Antigravity CLI (mksglu/context-mode, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Strategic Compact?
xu-xiang (a GitHub user) maintains it in xu-xiang/everything-claude-code-zh, which has 1,978 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on March 5, 2026.
Source: xu-xiang/everything-claude-code-zh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.