New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hitmux Context Engine

by hitmux in hitmux/hitmux-context-engine

使用 Hitmux Context Engine 的 hitmux-context-engine CLI 为当前代码仓库建立索引、检查索引状态并进行语义代码搜索。用户要求查找实现、定位 workflow、理解项目结构或检查索引时使用；优先走 CLI，不需要启动 MCP server。

MITAuto-check passedAgent Workflows

Install Hitmux Context Engine

skills CLI
$ npx skills add hitmux/hitmux-context-engine --skill hitmux-context-engine -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hitmux/hitmux-context-engine hitmux-context-engine --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hitmux/hitmux-context-engine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/hitmux-context-engine .claude/skills/hitmux-context-engine && rm -rf skills-src

Use ~/.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/

Facts

Skill name
hitmux-context-engine
GitHub stars
402
Token cost
~736 tokens
SKILL.md length
159 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

使用 Hitmux Context Engine 的 hitmux-context-engine CLI 为当前代码仓库建立索引、检查索引状态并进行语义代码搜索。用户要求查找实现、定位 workflow、理解项目结构或检查索引时使用；优先走 CLI，不需要启动 MCP server。

  • Works in 5 steps: 先确认 CLI 可用 → 首次使用或配置变更后先运行本地诊断 → 在目标仓库根目录检查索引 → …
  • Agent Workflows work in your project
  • SKILL.md covers 工作流, 输出格式与 JSON and 约束
  • Calls jq

What it does

Hitmux Context Engine is an agent skill from hitmux/hitmux-context-engine. 使用 Hitmux Context Engine 的 hitmux-context-engine CLI 为当前代码仓库建立索引、检查索引状态并进行语义代码搜索。用户要求查找实现、定位 workflow、理解项目结构或检查索引时使用；优先走 CLI，不需要启动 MCP server。

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: Semantic code search and context engine for AI coding agents. The licence is MIT.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/hitmux-context-engine”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 先确认 CLI 可用
  2. 首次使用或配置变更后先运行本地诊断
  3. 在目标仓库根目录检查索引
  4. 用自然语言和标识符组合查询
  5. 代码发生变化后，先检查状态；需要立即读取远程状态时加 --refresh

What it can do on your machine

Read from SKILL.md and the folder at commit 82fd8ea. 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

    Shell commands in SKILL.md call:

    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Hitmux Context Engine loads about 736 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~736

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 hitmux/hitmux-context-engine at commit 82fd8ea, republished under its MIT licence (© hitmux). 159 words, ~736 tokens.

Download SKILL.mdSave it as .claude/skills/hitmux-context-engine/SKILL.md (or your agent's skills folder).
name
hitmux-context-engine
description
使用 Hitmux Context Engine 的 hitmux-context-engine CLI 为当前代码仓库建立索引、检查索引状态并进行语义代码搜索。用户要求查找实现、定位 workflow、理解项目结构或检查索引时使用；优先走 CLI，不需要启动 MCP server。

Hitmux Context Engine

使用 hitmux-context-engine CLI 查询仓库上下文。hce 只是可选 alias，不应假定已经安装。这个 Skill 面向 shell 调用，适用于没有 MCP 或希望把搜索结果交给脚本继续处理的 agent。所有由 Agent 执行的命令都显式使用 --json，避免 PTY 环境被识别为交互终端。

工作流

  1. 先确认 CLI 可用：

    bash
    hitmux-context-engine --json --version

  2. 首次使用或配置变更后先运行本地诊断：

    bash
    hitmux-context-engine --json doctor --no-connectivity

    需要访问 embedding provider 或 Milvus 时再运行 hitmux-context-engine doctor。不要把 provider key、Milvus token 或完整 config.conf 内容写入对话或日志。

  3. 在目标仓库根目录检查索引：

    bash
    hitmux-context-engine --json status "$PWD"

    如果返回 not indexed，先运行：

    bash
    hitmux-context-engine --json index "$PWD"

    索引是远程 embedding 和 vector database 操作，开始前确认目标路径正确。索引完成后再次运行 hitmux-context-engine --json status "$PWD"。

  4. 用自然语言和标识符组合查询：

    bash
    hitmux-context-engine --json search "handler that validates MCP tool arguments" "$PWD" --scope code --limit 8

    --scope 可选 all、docs、code。省略 --limit 时使用自动 TopK；需要脚本稳定处理结果时传入正整数。

  5. 代码发生变化后，先检查状态；需要立即读取远程状态时加 --refresh：

    bash
    hitmux-context-engine --json status "$PWD" --refresh

输出格式与 JSON

CLI 的自动模式会在非 TTY stdout 输出 JSON，在交互终端输出文本。Skill 和脚本必须显式传 --json；需要强制人类可读文本时传 --text：

json
{"ok":true,"command":"search","exitCode":0,"output":"...","data":{"pagination":{"truncated":true,"continuationToken":"..."}}}

失败时 ok 为 false，错误位于 error，进程也会返回非零 exit code。脚本应先检查 ok 或 exit code。output 是可读文本，不能依赖其排版；handler 返回的机器可读内容位于 data。搜索存在下一页时读取 .data.pagination.continuationToken，并使用同一个 query、path 和 scope 继续查询：

bash
hitmux-context-engine --json search "handler that validates MCP tool arguments" "$PWD" --scope code --continuation-token "$TOKEN"

也可以使用 --format json|text，或设置 HCE_OUTPUT_FORMAT=json|text。

常用命令：

bash
hitmux-context-engine status [path] [--refresh] [--details]
hitmux-context-engine search <query> [path] [--limit n] [--scope all|docs|code] [--continuation-token token]
hitmux-context-engine list [collection-name|repo-path]
hitmux-context-engine index [path]
hitmux-context-engine doctor [--no-connectivity]

需要提取文本时可使用 jq -r '.output // .error'，提取下一页 token 时可使用 jq -r '.data.pagination.continuationToken // empty'。索引进度等 stderr 诊断会收集到 error 字段，即使命令成功也可能存在；它们不会污染 stdout 的 JSON envelope。--json 可以放在 command 前或后。

约束

  • 不要直接运行不带参数的 hitmux-context-engine；它会进入 MCP stdio server 模式并保持进程运行。
  • 不要为了普通搜索使用 clear、rm 或 index --force。这些命令会删除数据或重建索引，只有用户明确要求时才执行。
  • hitmux-context-engine init 会创建全局配置，并安装或更新 collection lease reaper user service；执行前确认这是期望的安装行为。
  • status、search 和 index 省略路径时默认当前工作目录；clear 和 repair 仍要求显式路径。Skill 应优先传入仓库根目录的绝对路径，避免在不同工作目录下命中错误的 collection。
  • 退出码 0 表示成功，1 表示运行或配置失败，2 表示参数错误。

© hitmux, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/hitmux-context-engine of hitmux/hitmux-context-engine.

Open the folder on GitHubat commit 82fd8ea

Compare with similar skills

Hitmux Context Engine 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.

Hitmux Context Engine compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hitmux Context Engine this skillhitmux/hitmux-context-engine402—~736Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace60k—~1.4kAutomated safety check: PassMIT
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    60k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • 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.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

Works with

Categories

Questions about Hitmux Context Engine

What does Hitmux Context Engine do?

使用 Hitmux Context Engine 的 hitmux-context-engine CLI 为当前代码仓库建立索引、检查索引状态并进行语义代码搜索。用户要求查找实现、定位 workflow、理解项目结构或检查索引时使用；优先走 CLI，不需要启动 MCP server。. Hitmux Context Engine is an agent skill from hitmux/hitmux-context-engine.

When should I use Hitmux Context Engine?

Hitmux Context Engine fits situations like: agent Workflows work in your project.

How do I install Hitmux Context Engine in Claude Code?

Run `npx skills add hitmux/hitmux-context-engine --skill hitmux-context-engine -a claude-code`. Or copy the skill folder (.agents/skills/hitmux-context-engine in hitmux/hitmux-context-engine) into .claude/skills/hitmux-context-engine in your project. Claude Code loads it when a task matches its description.

How do I install Hitmux Context Engine in Codex?

Run `npx skills add hitmux/hitmux-context-engine --skill hitmux-context-engine -a codex`. Or copy the skill folder (.agents/skills/hitmux-context-engine in hitmux/hitmux-context-engine) into .agents/skills/hitmux-context-engine in your project. Codex loads it when a task matches its description.

Can I use Hitmux Context Engine 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 hitmux/hitmux-context-engine --skill hitmux-context-engine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hitmux-context-engine, .gemini/skills/hitmux-context-engine, .github/skills/hitmux-context-engine and .opencode/skills/hitmux-context-engine in your project.

What does Hitmux Context Engine need to run?

Going by SKILL.md and its folder, Hitmux Context Engine needs the command-line tools its instructions call (jq).

Does Hitmux Context Engine access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hitmux Context Engine 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 Hitmux Context Engine use?

Hitmux Context Engine 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 Hitmux Context Engine use?

About 736 tokens (SKILL.md is roughly 2.9k 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 Hitmux Context Engine?

Skills that share tags, products or a category with Hitmux Context Engine: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and MemPalace Memory Search (MemPalace/mempalace, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hitmux Context Engine?

hitmux (a GitHub organization) maintains it in hitmux/hitmux-context-engine, which has 402 GitHub stars. The repository was last updated on September 29, 2026.

Source: hitmux/hitmux-context-engine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.