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通过

ln-014-agent-instructions-auditorln 014 Agent 指令审核员

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

196

周安装

8

GitHub Stars

441

下载量

63
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-014-agent-instructions-auditor(ln 014 Agent 指令审核员)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-014-agent-instructions-auditor
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-014-agent-instructions-auditor
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-014-agent-instructions-auditor

简介

用于辅助安全审计、权限检查和认证流程排查。

  • 适合梳理敏感配置、ln-014-agent-instructions-auditor 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 检查依赖风险或生成安全复核清单。
  • 使用时不能把工具输出直接当最终结论, 涉及密钥或生产系统时应先确认最小权限和操作边界。

SKILL.md

Paths: All file refs relative to skills repo root.

Agent Instructions Auditor

Type: L3 Worker Category: 0XX Shared

Audits instruction files (CLAUDE.md, AGENTS.md, GEMINI.md) across all three agents for quality, consistency, and best practices.

When to Use

  • After editing any instruction file
  • After adding/removing MCP servers or hooks
  • Before release or publishing
  • When sessions degrade (context bloat symptoms)

Phase 1: Discover Files

Locate instruction files in target project:

AgentPrimaryFallback
ClaudeCLAUDE.md.claude/settings.local.json
CodexAGENTS.md.codex/instructions.md
GeminiGEMINI.mdAGENTS.md (shared with Codex)

Report: which files exist, which agents share files.

Phase 2: Token Budget Audit

For each instruction file:

CheckPassWarnFail
Line count≤100 lines101-150 lines>150 lines
Estimated tokens≤2,500 tokens2,501-3,500>3,500
Sections count≤8 sections9-12>12

Token estimation: wc -w {file} × 1.3 (English average tokens/word ratio).

Report table per file with line count, word count, estimated tokens.

Phase 3: Prompt Cache Safety

Check each file for content that breaks prefix-based prompt caching:

#CheckPatternSeverity
1No timestampsgrep -E '\d{4}-\d{2}-\d{2}.\d{2}:\d{2}'WARN
2No dates in content`grep -E '(JanuaryFebruary
3No dynamic counts`grep -E '\d+ skills\\d+ tools\\d+ servers'` (hardcoded counts change)WARN
4No absolute paths`grep -E '[A-Z]:\/home/
5Stable structureNo conditional sections (if X then include Y)INFO

Phase 4: Content Quality

#CheckPassFail
1Has build/test commandsFound `npm\cargo\pytest\dotnet` commandsMissing — add essential commands
2No abstract principlesNo "write quality code", "follow best practices"Found vague instructions
3No redundant docsNo API docs, no full architecture descriptionFound content discoverable from code
4Has hard boundariesFound `NEVER\ALWAYS\MUST\DO NOT` rulesMissing explicit prohibitions
5Compact Instructions section## Compact Instructions present with preservation prioritiesMissing — sessions lose decisions on /compact
6MCP Tool PreferencesTable mapping built-in → MCP toolsMissing — agents use suboptimal tools
7No tool output examplesNo large code blocks or command outputsFound — bloats every turn

Phase 5: Cross-Agent Consistency

Compare content across all found instruction files:

CheckPassFail
MCP Tool PreferencesSame table in all filesMissing in some files
Critical RulesSame core rulesDivergent rules
Build/test commandsSame commandsDifferent or missing
Structural sectionsSame section orderInconsistent structure

Sync action: For each inconsistency, show diff and suggest which file is source of truth (usually CLAUDE.md).

Phase 6: Report

Agent Instructions Audit:
| File       | Lines | ~Tokens | Cache-safe | Quality | Issues |
|------------|-------|---------|------------|---------|--------|
| CLAUDE.md  | 80    | 2,100   | ✅          | 6/7     | Missing Compact Instructions |
| AGENTS.md  | 77    | 2,000   | ✅          | 7/7     | OK |
| GEMINI.md  | —     | —       | —          | —       | File not found |

Cross-agent: 1 inconsistency (GEMINI.md missing)

Recommendations:
1. Create GEMINI.md (copy from AGENTS.md, adjust agent-specific sections)
2. Add ## Compact Instructions to CLAUDE.md

Definition of Done

  • All instruction files discovered and audited
  • Token budget within limits (≤2,500 tokens each)
  • No prompt cache breakers found (or reported as WARN)
  • Content quality checks passed (or issues reported)
  • Cross-agent consistency verified
  • Report generated with actionable recommendations

Version: 1.0.0 Last Updated: 2026-03-20

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

31.37%
按下载量换算20

Claude

30.8%
按下载量换算19

Cursor

18.92%
按下载量换算12

Gemini CLI

9.22%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。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