Token导航 LogoToken导航TokenDH.com
开发权限需确认github未标认证来源可访问许可证需确认审计未展示

ln-011-agent-installerln 011 Agent 安装程序

Agent Skill

ln-011-agent-installer 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

1,806

周安装

76

GitHub Stars

441

下载量

632
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-011-agent-installer(ln 011 Agent 安装程序)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-011-agent-installer
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-011-agent-installer
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-011-agent-installer

简介

ln-011-agent-installer 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 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。

SKILL.md

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

Agent Installer

Type: L3 Worker Category: 0XX Shared

Installs or updates the two supported CLI agents: Codex CLI and Claude Code. Single pass per agent: install then immediately verify.

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


Input / Output

DirectionContent
InputOS info, disabled flags per agent, dry_run flag, optional runId, optional summaryArtifactPath
OutputStructured summary envelope with payload.status = completed / skipped / error, plus per-agent install 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.

Runtime

Runtime family: environment-worker-runtime

Phase profile:

  1. PHASE_0_CONFIG
  2. PHASE_1_INSTALL_VERIFY
  3. PHASE_2_POST_CODEX_SANITY_CHECK
  4. PHASE_3_WRITE_SUMMARY
  5. PHASE_4_SELF_CHECK

Runtime rules:

  • emit summary_kind=env-agent-install
  • 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-agent-install summary envelope per:

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

Payload fields:

  • targets
  • agents_processed
  • agents_skipped
  • versions
  • codex_drift_detected
  • status

Agent Registry

AgentInstall CommandHealth CheckInteractive
Codexnpm i -g @openai/codexcodex --versioncodex or codex "prompt"
Claudenpm i -g @anthropic-ai/claude-code or claude updateclaude --versionclaude or claude "prompt"

Automation uses:

  • Codex: codex exec...
  • Claude: claude -p...

Note: codex / codex "prompt" are interactive TTY entrypoints. Non-interactive validation and review automation must use codex exec..., because Codex rejects direct interactive mode when stdin is not a terminal.


Workflow

For each enabled agent: Install or Update -> Verify -> Record

Phase 1: Install & Verify

For each agent in registry, apply first matching rule:

ConditionActionReport
disabled: trueSKIPdisabled by user
dry_run: trueShow planned commanddry run
Codexnpm install -g @openai/codex then codex --versionversion or error
Claude installedclaude update then claude --versionversion or error
Claude missingnpm install -g @anthropic-ai/claude-code then claude --versionversion or error

Single pass: install and verify happen atomically per agent. No separate scan phase; the install result is the state.

Error handling:

ErrorDetectionResponse
npm not in PATHnpm --version failsFAIL gracefully, report npm not found in PATH
Permission deniedstderr contains EACCESFAIL, suggest npm install -g --prefix ~/.local {pkg}
Network errorstderr contains ETIMEDOUT or ENETUNREACHFAIL, report network error
Unknown errorAny other non-zero exitFAIL, include stderr

Output table:

Agent Installation:
| Agent  | Action    | Version  | Status |
|--------|-----------|----------|--------|
| Codex  | installed | 0.124.0  | ok     |
| Claude | updated   | 2.1.119  | ok     |

Phase 2: Post-Install Codex Sanity Check

After successful Codex install/update:

  1. Check ~/.codex/config.toml top-level approval_policy and sandbox_mode.
  2. Check configured Codex marketplaces for duplicate active paths to this repo.
  3. If drift is found, report a WARN and defer remediation to ln-013-config-syncer.

This installer does not install marketplace plugins, rewrite Codex marketplace layout, or manage Codex execution defaults. It only reports drift so install success is not mistaken for a healthy two-agent environment.


Critical Rules

  1. Never modify disabled flags. Respect them, never change them.
  2. Fail gracefully. One agent failure does not block the other.
  3. Global install only. CLI tools must be in PATH.
  4. Report all changes. Include config observations in the final summary table.
  5. Idempotent. Safe to run multiple times.
  6. Claude and Codex only. Do not add unrelated agent branches.
  7. Codex marketplace/plugin and execution-default remediation belongs to ln-013. This skill may detect drift, but must not rewrite marketplace/cache layout or Codex top-level permission defaults itself.

Anti-Patterns

DON'TDO
Separate check/install/verify phasesSingle pass: install then verify
Retry failed installs automaticallyOne attempt, report failure
Use sudo npm installSuggest --prefix for permission issues
Install agents marked disabledSkip with clear report
Configure MCP settings or marketplace plugins hereRoute environment alignment to ln-013-config-syncer

Definition of Done

  • Codex and Claude processed in single pass (install + verify)
  • Disabled agents skipped with report
  • Version verified immediately after each install
  • Codex marketplace/plugin and execution-default sanity checked or explicitly reported for ln-013 follow-up
  • Status table displayed
  • Structured summary returned
  • Summary artifact written to the managed or standalone runtime path

Version: 1.1.0 Last Updated: 2026-03-23

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

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

36.4%
按下载量换算230

Claude

30.48%
按下载量换算193

Cursor

18.89%
按下载量换算119

Gemini CLI

7.85%
按下载量换算50

安全审计

暂无安全审计结果可展示。

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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。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