Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计异常

ln-004-agent-syncln 004 Agent 同步

Agent Skill

ln-004-agent-sync 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,014

周安装

41

GitHub Stars

441

下载量

318
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ln-004-agent-sync(ln 004 Agent 同步)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-004-agent-sync
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-004-agent-sync
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-004-agent-sync

简介

用于查找和筛选与 ln-004 Agent 同步相关的信息。

  • 适合根据关键词快速定位多 Agent 协作模式。
  • 通过 GitHub 安装,需结合项目文档验证适用性。
  • 建议在使用前评估对系统负载的影响。ln-004-agent-sync 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 注意同步延迟,避免依赖实时状态做关键决策。

SKILL.md

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

Agent Sync (Standalone Utility)

Type: Standalone Utility Category: 0XX Shared

Synchronizes skills and MCP server configurations from Claude Code (source of truth) to Gemini CLI and Codex CLI. Creates symlinks for skills, copies/converts MCP settings.


When to Use This Skill

  • After adding/removing MCP servers in Claude Code settings
  • After installing new plugins in Claude Code
  • First-time setup of Gemini CLI or Codex CLI alongside Claude Code
  • Periodic sync to keep all agents aligned

Input Parameters

ParameterRequiredDefaultDescription
targetsNobothgemini, codex, or both
modeNofullskills (symlinks only), mcp (MCP only), or full (both)
dry_runNofalseShow planned actions without executing

Workflow

Detect OS → Discover Configs → Sync Skills → Sync MCP → Report

Phase 0: OS Detection

CheckResultImpact
uname or platformwin32 / darwin / linuxJunction vs symlink
Home directory$HOME or $USERPROFILEConfig paths

Paths by OS:

AgentWindowsmacOS / Linux
Claude%USERPROFILE%\.claude\settings.json~/.claude/settings.json
Gemini%USERPROFILE%\.gemini\settings.json~/.gemini/settings.json
Codex%USERPROFILE%\.codex\config.toml~/.codex/config.toml

Phase 1: Discover Current State

  1. Read Claude settings:

- Parse ~/.claude/settings.json → extract mcpServers block - If no mcpServers → WARN "No MCP servers configured in Claude", skip MCP sync

  1. Read target configs (if exist):

- Gemini: Parse ~/.gemini/settings.json → extract existing mcpServers - Codex: Parse ~/.codex/config.toml → extract existing [mcp_servers.*]

  1. Detect installed plugins:

- Glob ~/.claude/plugins/*/plugin.json → list plugin directories - Also check if skills repo itself is a plugin source

  1. Check existing symlinks:

- ~/.gemini/skills → exists? points where? - ~/.codex/skills → exists? points where?

  1. Show current state: Current State: | Agent | Skills | MCP Servers | Config Exists | |-------|--------|-------------|---------------| | Claude (source) | 2 plugins | 4 servers | yes | | Gemini | no link | 2 servers | yes | | Codex | → ~/.claude/plugins | 4 servers | yes |

Phase 2: Sync Skills (symlinks/junctions)

FOR EACH target IN (gemini, codex) WHERE target in targets:

  1. Determine link path:

- Gemini: ~/.gemini/skills - Codex: ~/.codex/skills

  1. Check if already linked correctly:

- IF link exists AND points to correct source → SKIP (already synced) - IF link exists AND points to wrong source → WARN, ask user before replacing - IF regular directory (not link) exists → WARN "Target is a real directory, not a link. Skip to avoid data loss."

  1. Determine source:

- IF single plugin: link directly to plugin dir - IF multiple plugins: ask user which plugin to share

  1. Create link: OS Command Windows cmd /c mklink /J "{target_path}" "{source_path}" macOS / Linux ln -s "{source_path}" "{target_path}"
  2. Verify: Check link exists and resolves correctly

Phase 3: Sync MCP Settings

Source: ~/.claude/settings.jsonmcpServers block

3a: Claude → Gemini (JSON → JSON)

  1. Read Claude mcpServers as JSON object
  2. Read Gemini settings.json (or create {} if missing)
  3. Merge strategy: Claude servers override Gemini servers by key name. Gemini-only servers preserved.
  4. Write updated settings.json

Conversion: None needed — identical format.

3b: Claude → Codex (JSON → TOML)

  1. Read Claude mcpServers as JSON object
  2. Read Codex config.toml (or create empty if missing)
  3. Convert each server: Claude JSON field Codex TOML field Notes command command Same args args JSON array → TOML array env [mcp_servers.{name}.env] Nested table type: "http" + url url HTTP transport type: "sse" + url url SSE transport Example conversion: "context7": {"command": "npx", "args": ["-y", "@upstash/context7-mcp"]} [mcp_servers.context7] command = "npx" args = ["-y", "@upstash/context7-mcp"]
  4. Merge strategy: Claude servers override. Codex-only servers preserved.
  5. Write updated config.toml

Unsupported conversions (preserve as-is in Codex):

  • bearer_token_env_var — no Claude equivalent
  • enabled_tools / disabled_tools — no Claude equivalent

Phase 4: Report

Sync Complete:
| Action | Target | Status |
|--------|--------|--------|
| Skills symlink | Gemini | Created → ~/.claude/plugins/... |
| Skills symlink | Codex | Already linked |
| MCP sync | Gemini | 4 servers synced (2 new, 2 updated) |
| MCP sync | Codex | 4 servers synced (1 new, 3 updated) |

Critical Rules

  1. Claude = source of truth. Never write TO Claude settings. Read-only source.
  2. Non-destructive merge. Target-only servers/settings preserved. Only Claude servers added/updated.
  3. No data loss. If target is a real directory (not symlink) — warn and skip, never delete.
  4. Backup before write. Before modifying any config file, create .bak copy.
  5. Dry run first. If dry_run=true, show all planned actions without executing.
  6. Ask on conflict. If symlink points to different source — ask user, don't auto-replace.

Anti-Patterns

  • Writing TO Claude settings from Gemini/Codex (reverse sync)
  • Deleting target-only MCP servers during sync
  • Creating symlinks inside symlinks (circular)
  • Modifying config files without backup

Definition of Done

#Criterion
1Claude settings read successfully
2Skills symlinks created/verified for each target
3MCP settings synced with format conversion (JSON→TOML for Codex)
4Backup files created before any config modification
5Report shown with all actions and warnings

Version: 1.0.0 Last Updated: 2026-02-15

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.08%
按下载量换算115

Claude

32.22%
按下载量换算102

Cursor

21.01%
按下载量换算67

Gemini CLI

8.61%
按下载量换算27

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

未通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills