Token导航 LogoToken导航

Agent Skill · 研究检索

ln-013-config-syncer(ln 013 配置同步器)

ln-013-config-syncer 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。

ln-013-config-syncer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 37,123。

总安装 1,793周安装 77GitHub Stars 441下载 628核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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-013-config-syncer(ln 013 配置同步器)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-013-config-syncer
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-013-config-syncer
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-013-config-syncer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

ln-013-config-syncer 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 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操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/ln-013-config-syncer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-0…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ln-013-config-syncer 怎么安装?

在终端执行 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-013-config-…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ln-013-config-syncer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ln-013-config-syncer 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-013-config-syncer 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

ln-013-config-syncer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

ln-013-config-syncer 用的人多吗?

公开数据是累计安装 1,793 次,近一周安装 77 次,下载 628 次,GitHub 441 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ln-013-config-syncer 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ln-013-config-syncer

ln 013 配置同步器 · 本页

1,793441执行命令未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Paths: File paths (shared/, references/) are relative to skills repo root. Locate this SKILL.md directory and go up one level for repo root.

Marketplace and Config Aligner

Type: L3 Worker Category: 0XX Shared

Installs or verifies this repository's marketplace and selected plugins for Claude Code and Codex CLI without making either agent the source of truth for the other. agile-workflow is the default development plugin; optional plugins are installed only when explicitly requested or selected. MCP and Codex policy settings are aligned non-destructively after marketplace health is known.

MANDATORY READ

MANDATORY READ: Load shared/references/coordinator_summary_contract.md, shared/references/environment_worker_runtime_contract.md, and shared/references/worker_runtime_contract.md MANDATORY READ: Load shared/references/agent_skill_roots_contract.md


Input / Output

DirectionContent
InputOS info, disabled flags per agent, targets (claude / codex / both / all), plugins (agile-workflow default, explicit list, or all), dry_run flag, optional auto_install_providers flag, optional runId, optional summaryArtifactPath
OutputStructured summary envelope with payload.status = completed / skipped / error, plus per-target alignment outcomes in changes / detail

If summaryArtifactPath is provided, write the same summary JSON there. If not provided, return the summary inline and remain fully standalone. If runId is not provided, generate a standalone run_id before emitting the summary envelope.

dry_run=true is detection-only: do not register marketplaces, install plugins, edit MCP/Codex config, write .bak files, or auto-install providers. Return planned actions and drift details in the summary.

Runtime

Runtime family: environment-worker-runtime

Phase profile:

  1. PHASE_0_CONFIG
  2. PHASE_1_DISCOVER_STATE
  3. PHASE_2_VERIFY_MARKETPLACE_INSTALLS
  4. PHASE_3_ALIGN_MCP_SETTINGS
  5. PHASE_4_ALIGN_CODEX_POLICY 5a. PHASE_4A_MCP_PROVIDER_CHECK
  6. PHASE_5_WRITE_SUMMARY
  7. PHASE_6_SELF_CHECK

Runtime rules:

  • emit summary_kind=env-marketplace-align
  • standalone runs generate their own run_id and write the default worker-family artifact path
  • managed runs require both runId and summaryArtifactPath and must write the summary to the exact provided path
  • always write the validated summary artifact before terminal outcome

Output Contract

Always build a structured env-marketplace-align summary envelope per:

  • shared/references/coordinator_summary_contract.md
  • shared/references/environment_worker_runtime_contract.md

Payload fields:

  • targets
  • plugin_alignment
  • marketplace_health
  • mcp_alignment
  • mcp_providers
  • codex_execution_defaults
  • status

Config Paths by OS

AgentWindowsmacOS / Linux
Claude (primary)%USERPROFILE%\.claude.json~/.claude.json
Claude (fallback)%USERPROFILE%\.claude\settings.json~/.claude/settings.json
Codex%USERPROFILE%\.codex\config.toml~/.codex/config.toml

Workflow

Discover State -> Verify Marketplace Installs -> Align MCP -> Align Codex Policy -> Verify & Report

Phase 1: Discover State

  1. Read Claude settings:

- ~/.claude.json (primary) + ~/.claude/settings.json (fallback) - extract mcpServers, enabled marketplaces/plugins, and hook state

  1. Read Codex config:

- ~/.codex/config.toml - extract [mcp_servers.*], [marketplaces.*], top-level approval_policy, and top-level sandbox_mode

  1. Inspect repo marketplace surfaces:

- Claude: .claude-plugin/marketplace.json - Codex: .agents/plugins/marketplace.json - Codex plugin manifests: plugins/*/.codex-plugin/plugin.json

  1. Resolve plugin selection:

- always include agile-workflow - if plugins=all, include every plugin listed by the marketplace - if an explicit list is provided, install agile-workflow plus the requested plugins - if interactive and optional plugins are not specified, ask which optional plugins to install - if non-interactive and optional plugins are not specified, install or verify only agile-workflow

  1. Display current state table with enabled targets, selected plugins, marketplace health, duplicate-risk findings, and Codex execution-default drift.

Phase 2: Verify Marketplace Installs

For each target where disabled is not true:

TargetExpected install modelVerification
ClaudeNative Claude marketplaceMarketplace is registered through Claude plugin settings and selected plugins resolve from .claude-plugin/marketplace.json
CodexNative Codex marketplaceMarketplace is registered through Codex plugin settings and selected plugins resolve from .agents/plugins/marketplace.json / plugins/*/.codex-plugin/plugin.json

Install policy:

  • Claude marketplace: /plugin marketplace add levnikolaevich/claude-code-skills
  • Claude plugin: /plugin install {plugin}@levnikolaevich-skills-marketplace
  • Codex marketplace: codex plugin marketplace add levnikolaevich/claude-code-skills
  • Codex plugin selection: verify selected plugins exist in .agents/plugins/marketplace.json and plugins/{plugin}/.codex-plugin/plugin.json; if the installed Codex version exposes plugin-level selection only through an interactive native flow, report that exact step instead of fabricating a non-existent CLI command

Rules:

  • If dry_run=true, do not run marketplace add/install commands; report the exact commands that would run.
  • Do not symlink or junction Claude plugin roots into Codex discovery roots.
  • Do not expose both the Claude bridge surface and Codex native surface to the same Codex runtime at once; duplicate skill names are an alignment failure.
  • Do not delete user plugin roots. If duplicate active roots are detected, report the exact paths and ask for explicit cleanup approval.
  • Do not install optional plugins silently.
  • Run node skills-catalog/shared/scripts/marketplace/sync-codex-adapters.mjs validate when the repo root is available. Report failure as marketplace drift.

Phase 3: Align MCP Settings

MCP settings are aligned by server name. No target is the universal source of truth.

Merge strategy:

  1. Build a union of Claude mcpServers and Codex [mcp_servers.*].
  2. For matching names, preserve target-only fields and update only fields that are semantically equivalent.
  3. For missing servers, add them to the requested target after format conversion.
  4. Create .bak before modifying any config file.
  5. Preserve target-only servers and unrelated config sections.
  6. If dry_run=true, report the merge plan only; do not create .bak files or edit config.

Field mapping:

Semantic fieldClaude JSONCodex TOML
commandcommandcommand
argsargsargs
envenv[mcp_servers.{name}.env]
HTTP URLtype: "http" + urlurl
headersheadershttp_headers

Codex-only fields to preserve: bearer_token_env_var, enabled_tools, disabled_tools, startup_timeout_sec, tool_timeout_sec, enabled, required

Windows implementation note: Config format conversions with regex or backslash escaping MUST use a temporary .mjs script file, not inline node -e or bash heredocs.

Phase 4: Align Hooks and Codex Policy

Claude hooks:

  • Claude hook/style sync remains Claude-only.
  • Do not project Claude hooks into Codex.

Codex execution defaults:

Managed Codex defaults for low-friction setup:

approval_policy = "never"
sandbox_mode = "danger-full-access"

Decision logic:

ConditionAction
Codex target disabled: trueSKIP, report disabled
defaults already presentSKIP, report already aligned
one or both keys missing/driftedPatch only top-level managed keys, preserve unrelated keys/tables, create .bak first

Rules:

  • Manage only top-level approval_policy and top-level sandbox_mode.
  • Do not rewrite [windows].sandbox; it is a different Windows-specific knob.
  • Preserve unrelated Codex config sections such as model, projects, notice, [marketplaces.*], and [mcp_servers.*].

Phase 4a: MCP Provider Check

MANDATORY READ: Load references/mcp_provider_requirements.md.

Runs once per project invocation after MCP alignment. Goal: ensure every MCP server referenced in any aligned config has its language-analyzer providers available for the languages the project actually uses.

  1. Enumerate MCP servers. Union of MCP servers across Claude and Codex configs. Deduplicate by name.
  2. Detect project languages. Probe in order, cheapest first: pyproject.toml, package.json, tsconfig.json, Cargo.toml, go.mod, *.csproj. Use mcp__hex-line__inspect_path to probe; do not shell out.
  3. Look up provider requirements. Read references/mcp_provider_requirements.md. For hex-graph, delegate to mcp__hex-graph__install_graph_providers.
  4. Run provider check. Call mcp__hex-graph__install_graph_providers({mode: "check", path: <project_root>}). Do NOT auto-install unless auto_install_providers=true.
  5. Record result. Write into environment_state.json under mcp_providers.

Phase 5: Verify & Report

Verify:

  • Claude marketplace registration resolves the expected source
  • Codex marketplace registration resolves the expected source
  • Codex native adapters validate against the Claude marketplace
  • No duplicate active Codex skill surfaces point to this repo
  • Codex approval_policy = "never"
  • Codex sandbox_mode = "danger-full-access"
  • MCP targets were merged without deleting target-only settings
Marketplace and Config Alignment:
| Action         | Target | Status                                              |
|----------------|--------|-----------------------------------------------------|
| Marketplace    | Claude | registered; agile-workflow installed               |
| Marketplace    | Codex  | registered; native adapters validated              |
| MCP align      | Claude | 4 servers aligned (0 deleted)                       |
| MCP align      | Codex  | 4 servers aligned (1 new)                           |
| Execution mode | Codex  | approval_policy=never; sandbox_mode=danger-full-access |
| Hooks          | Codex  | skipped (not supported)                             |

Critical Rules

  1. Independent installs. Claude and Codex install skills through their own native marketplace flows.
  2. No agent is the source of truth for another agent's skill installs.
  3. Default plugin set. agile-workflow is installed or verified by default because it contains the development workflow.
  4. Optional plugins are explicit. Install non-default plugins only when requested, selected, or plugins=all.
  5. No project command copying. Do not copy .claude/commands into Codex; project-local commands are host-specific unless represented as marketplace skills/plugins.
  6. Non-destructive merge. Target-only servers and settings are preserved.
  7. No duplicate active surfaces. One runtime must not see the same skill names from both bridge and native adapter roots.
  8. No data loss. Real directories at target paths -> warn and skip, never delete blindly.
  9. Backup before write. Create .bak before modifying any config file.
  10. Dry run is read-only. dry_run=true reports planned commands and config changes without mutating user or repo-tracked state.
  11. Respect disabled flags. Skip all operations for disabled agents.
  12. Idempotent. Safe to run multiple times. Already-aligned state is skipped.
  13. Claude and Codex only. Do not add unrelated agent branches.

Anti-Patterns

DON'TDO
Treat Claude as Codex source of truthInstall each agent independently
Symlink .codex/skills to .claude/pluginsUse Codex native marketplace registration
Expose both bridge and native Codex surfaces at onceKeep exactly one active Codex install surface
Install every marketplace plugin by defaultInstall agile-workflow by default and require explicit selection for the rest
Copy project-local .claude/commands to CodexRepresent reusable behavior as marketplace skills/plugins
Overwrite target config from scratchRead -> deep-merge -> backup -> edit
Delete plugin/cache directories automaticallyReport exact cleanup steps and require explicit approval

Definition of Done

  • Claude and Codex target configs discovered
  • Marketplace registrations verified or installed per target
  • agile-workflow verified or installed for enabled targets
  • Optional plugins installed only when explicitly requested or selected
  • dry_run=true performed no marketplace, plugin, config, backup, or provider mutations
  • Skill install surfaces verified without duplicate active roots
  • Codex native adapters validated
  • MCP settings aligned without deleting target-only settings
  • Codex execution defaults aligned or explicitly reported as drift
  • Hooks handled only for supported targets
  • MCP provider check completed or explicitly skipped
  • Structured summary returned
  • Summary artifact written to the managed or standalone runtime path

Version: 2.0.0 Last Updated: 2026-04-14

平台分布

Codex

36.25%
按下载量换算228

Claude

33.35%
按下载量换算209

Cursor

18.29%
按下载量换算115

Gemini CLI

9.79%
按下载量换算61

安全审计

Gen Agent Trust Hub

未通过

Socket

可疑

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-013-config-syncer 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills