Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问许可证需确认审计提醒

maintain-plugins维护插件

Agent Skill

maintain-plugins 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

235

周安装

10

GitHub Stars

2

下载量

82
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:maintain-plugins(维护插件)
来源仓库:https://github.com/richfrem/agent-plugins-skills
仓库路径:skills/maintain-plugins
安装命令:
npx skills add https://github.com/richfrem/agent-plugins-skills --skill maintain-plugins
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/richfrem/agent-plugins-skills --skill maintain-plugins

简介

maintain-plugins 用于查找和筛选相关信息。

  • 适合在关键词搜索或任务场景中快速定位候选结果。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装前应确认权限范围、维护状态及是否触发联网或文件读写。
  • 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

Dependencies

This skill requires Python 3.8+ and standard library only. No external packages needed.

To install this skill's dependencies:

pip-compile ./requirements.in
pip install -r ./requirements.txt

See ../../requirements.txt for the dependency lockfile (currently empty — standard library only).


Plugin Maintenance

Overview

This skill is the ecosystem health hub. It covers three operations:

  • Audit — structural compliance checking against Open Standards
  • Sync — keep agent environments in sync with plugins/, cleaning up orphaned artifacts
  • README — scaffold missing documentation

Core constraint: Custom, project-specific plugins are NEVER deleted during sync. Only vendor-managed plugins that have been locally removed are cleaned up.

References

  • Sync process guide: cleanup_process.md
  • Sync flow diagram: cleanup_flow.mmd

Execution Protocol

CRITICAL: Do not immediately generate bash commands. Operate as an interactive assistant.

Phase 1: Guided Discovery

When invoked, ask what operation the user needs:

Which maintenance operation?
1. [Audit]  — Check plugin(s) against structural Open Standards
2. [Sync]   — Sync plugins/ to all agent environments (install + cleanup orphans)
3. [README] — Scaffold missing README.md files from plugin metadata

Phase 2: Recap-Before-Execute

State exactly what you are about to do and ask for confirmation:

### Proposed Maintenance Task
- **Operation**: [Audit / Sync (Dry Run) / Sync (Apply) / README Generation]
- **Target**: [All plugins / Specific plugin: name]
- **Impact**: [Read-only / Modifies agent config directories]

> Does this look correct? I will generate the commands once you confirm.

For Sync: Always propose a Dry Run first before offering to Apply.

Phase 3: Command Execution

Wait for explicit confirmation (yes, looks good, ok).


[Audit] Structural Compliance Check

Step 1: Run Deterministic Scanner

python3 .agents/skills/maintain-plugins/scripts/audit_structure.py
For deeper semantic + security checks, invoke analyze-plugin from agent-plugin-analyzer.

Step 2: Manual Audit Checklist (if script unavailable)

For each plugin being audited, classify every file by type and check against Open Standards:

File Type Classification:

TypePath PatternNotes
Skill definitionskills/*/SKILL.mdOne per skill dir
Commandcommands/*.mdSlash-command instructions
Referenceskills/*/references/*.mdProgressive disclosure content
Scriptscripts/*.pyPython only — no.sh/.ps1
Manifest../../../.claude-plugin/plugin.jsonRequired
ConnectorsCONNECTORS.mdRequired if Supercharged/Integration-Dependent
Diagram*.mmdArchitecture diagrams
READMEREADME.mdRequired

7 Structural Dimensions:

DimensionPass Condition
LayoutEach skill has its own directory. No flat file mixing.
Progressive DisclosureEvery SKILL.md is under 500 lines. Deep content is in references/.
NamingPlugin name: kebab-case, lowercase. Skill names: same convention, matching directory.
README QualityHas directory tree, usage examples, skill table.
CONNECTORS.mdPresent if plugin uses external tools. Uses ~~category abstraction.
Architecture fitIs Standalone / Supercharged / Integration-Dependent clearly declared?
././././plugin.jsonHas unique name, version, description, author.url, repository.

SKILL.md Frontmatter Quality Checks:

  • description written in third person
  • Includes specific trigger phrases ("Trigger when...")
  • Under 1024 characters
  • name matches directory name (kebab-case, lowercase)

SKILL.md Body Structure Checks:

  • Clear numbered phases or execution steps
  • Uses Recap-Before-Execute for destructive operations
  • Tables used for structured comparisons
  • Links to references/ for deep content (not inline)
  • allowed-tools declared if tool-restricted

Three Compliance Absolutes (from Open Standards):

  1. All skills MUST end with a Source Transparency Declaration if querying external sources
  2. If plugin generates .html, .svg, or .js artifacts, MUST implement Client-Side Compute Sandbox (hardcoded loop bounds) + XSS Compliance Gate (no external script tags)
  3. Sub-agents MUST have an explicit tools: allowlist

Step 3: Flag and Report

For each violation found, report with severity:

  • CRITICAL — Missing ../../../.claude-plugin/plugin.json, shell=True in scripts, hardcoded credentials
  • HIGH — SKILL.md over 500 lines, name convention violations, missing allowed-tools
  • MEDIUM — Missing CONNECTORS.md for tool-using plugin, missing fallback-tree
  • LOW — Missing README, no repository in././././plugin.json
For L5 maturity scoring, invoke the l5-red-team-auditor agent from agent-plugin-analyzer.

[Sync] Agent Environment Synchronization

Preview Changes (Always Run First)

python3 .agents/skills/maintain-plugins/scripts/sync_with_inventory.py --dry-run

Apply Changes

python3 .agents/skills/maintain-plugins/scripts/sync_with_inventory.py

Post-Sync Verification

  1. Check local-plugins-inventory.json (generated in project root) for current state.
  2. Confirm custom plugins (not in vendor list) still present in plugins/.
  3. Confirm artifacts for removed vendor plugins are gone from .agent, .gemini, etc.

[README] Generate Missing Documentation

python3 .agents/skills/maintain-plugins/scripts/generate_readmes.py --apply

Escalation Taxonomy

ConditionResponse
"Vendor directory not found"Clone vendor: git clone https://github.com/richfrem/agent-plugins-skills.git.vendor/agent-plugins-skills
shell=True detected in any scriptSTOP — CRITICAL: Command Injection Vector. Report before proceeding.
Custom plugin accidentally cleanedSTOP. Restore via git checkout -- plugins/<name>/. Never re-run until cause identified.
SKILL.md exceeds 500 linesFLAG HIGH: Progressive Disclosure Violation. Suggest extracting to references/.

When to Use

  • After adding a new plugin — run Audit to verify correct structure
  • After removing a vendor plugin — run Sync to clean orphaned agent artifacts
  • Periodically — to catch drift or accidental file placements
  • Before a release — to ensure clean distribution state

Next Actions

  • Run plugin-installer from plugin-manager to deploy updated plugins to agent environments.
  • Run l5-red-team-auditor from agent-plugin-analyzer for full L5 maturity assessment.
  • Run create-skill from agent-scaffolders to fix scaffolding gaps in audited plugins.

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

37.43%
按下载量换算31

Claude

29.59%
按下载量换算24

Cursor

17.34%
按下载量换算14

Gemini CLI

9.55%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

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/richfrem/agent-plugins-skills --skill maintain-plugins 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 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