Token导航 LogoToken导航

Agent Skill · 研究检索

regexguard(regexguard 分析)

regexguard 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 OpenClaw 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。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。

regexguard 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为操作浏览器;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 35,079。

总安装 2,140周安装 91GitHub Stars 公开资料未说明下载 750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
MIT-0
版本
1.0.2

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:regexguard(regexguard 分析)
来源仓库:https://github.com/suhteevah/regexguard
安装命令:
openclaw skills install regexguard
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install regexguard

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。

分析正则表达式的安全性和正确性,检测灾难性回溯等问题。识别可移植性错误和维护性问题,提升代码质量。适合代码审查阶段集成使用。regexguard 属于研究检索类 Skill,可作为该场景下的辅助能力补充。安装命令:openclaw skills install regexguard。

使用前建议确认权限范围和维护状态,避免触发未授权操作。

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 OpenClaw;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 openclaw skills install regexguard;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

    它需要操作浏览器,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

regexguard 怎么安装?

在终端执行 openclaw skills install regexguard。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

regexguard 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

regexguard 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

regexguard 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

regexguard 用的人多吗?

公开数据是累计安装 2,140 次,近一周安装 91 次,下载 750 次。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。

regexguard 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 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 OpenClaw,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

  • 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
regexguard

regexguard 分析 · 本页

2,140—操作浏览器MIT-0有提醒

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

name
RegexGuard
version
1.0.0
description
Regex safety & correctness analyzer -- detects catastrophic backtracking, portability errors, correctness bugs, maintainability issues, anchoring problems, and pattern injection risks
homepage
https://regexguard.pages.dev
metadata
user-invocable
true
disable-model-invocation
false

RegexGuard -- Regex Safety & Correctness Analyzer

RegexGuard scans codebases for regex anti-patterns: catastrophic backtracking (ReDoS), portability errors across engines, correctness bugs, maintainability issues, anchoring and boundary problems, and pattern injection risks. It uses regex-based pattern matching against 90 regex-specific patterns across 6 categories, lefthook for git hook integration, and produces markdown reports with actionable remediation guidance. 100% local. Zero telemetry.

Note: RegexGuard focuses on regex patterns found in source code (JavaScript, Python, Go, Java, Ruby, shell scripts, config files). It detects anti-patterns in how regexes are written, constructed, and used.

Commands

Free Tier (No license required)

regexguard scan [file|directory]

One-shot regex safety scan of files or directories.

How to execute:

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [target]

What it does:

  1. Accepts a file path or directory (defaults to current directory)
  2. Discovers all source files (skips .git, node_modules, binaries, images, .min.js)
  3. Runs 30 regex patterns against each file (free tier limit)
  4. Calculates a regex quality score (0-100) per file and overall
  5. Grades: A (90-100), B (80-89), C (70-79), D (60-69), F (<60)
  6. Outputs findings with: file, line number, check ID, severity, description, recommendation
  7. Exit code 0 if score >= 70, exit code 1 if regex quality is poor
  8. Free tier limited to first 30 patterns (CB + PE categories)

Example usage scenarios:

  • "Scan my code for regex issues" -> runs regexguard scan .
  • "Check this file for ReDoS vulnerabilities" -> runs regexguard scan src/validators.ts
  • "Find catastrophic backtracking patterns" -> runs regexguard scan src/
  • "Check for non-portable regex syntax" -> runs regexguard scan .
  • "Audit regex patterns for correctness" -> runs regexguard scan .

Pro Tier ($19/user/month -- requires REGEXGUARD_LICENSE_KEY)

regexguard scan --tier pro [file|directory]

Extended scan with 60 patterns covering backtracking, portability, correctness, and maintainability.

How to execute:

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [target] --tier pro

What it does:

  1. Validates Pro+ license
  2. Runs 60 regex patterns (CB, PE, CE, MA categories)
  3. Detects correctness bugs like unescaped dots, bad character class ranges
  4. Identifies maintainability issues: overly complex patterns, missing comments
  5. Full category breakdown reporting
regexguard scan --format json [directory]

Generate JSON output for CI/CD integration.

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [directory] --format json
regexguard scan --format html [directory]

Generate HTML report for browser viewing.

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [directory] --format html
regexguard scan --category CB [directory]

Filter scan to a specific check category (CB, PE, CE, MA, AN, PI).

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [directory] --category CB

Team Tier ($39/user/month -- requires REGEXGUARD_LICENSE_KEY with team tier)

regexguard scan --tier team [directory]

Full scan with all 90 patterns across all 6 categories including anchoring and injection.

How to execute:

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [directory] --tier team

What it does:

  1. Validates Team+ license
  2. Runs all 90 patterns across 6 categories
  3. Includes anchoring checks (missing ^/$, multiline flag gaps, \b misuse)
  4. Includes pattern injection checks (unsanitized user input, DoS vectors)
  5. Full category breakdown with per-file results
regexguard scan --verbose [directory]

Verbose output showing every matched line and pattern details.

bash "<SKILL_DIR>/scripts/dispatcher.sh" --path [directory] --verbose
regexguard status

Show license and configuration information.

bash "<SKILL_DIR>/scripts/dispatcher.sh" status
regexguard patterns

List all 90 detection patterns across all categories.

bash "<SKILL_DIR>/scripts/dispatcher.sh" patterns

Check Categories

RegexGuard detects 90 regex anti-patterns across 6 categories:

CategoryCodePatternsDescriptionSeverity Range
Catastrophic BacktrackingCB15Nested quantifiers, exponential patterns, ReDoS vectors, overlapping greedlow -- critical
Portability ErrorsPE15Non-POSIX features, engine-specific syntax, lookbehind gaps, Unicode escapeslow -- high
Correctness ErrorsCE15Unescaped dots, bad character class ranges, greedy vs lazy, redundant quantifierslow -- high
Maintainability IssuesMA15Overly complex patterns, missing comments, duplication, magic regex stringslow -- high
Anchoring & BoundariesAN15Missing ^/$, \b misuse, multiline flag gaps, validation anchor bypasslow -- critical
Pattern InjectionPI15Unsanitized user input in regex, string concat into RegExp, DoS vectorslow -- critical

Tier-Based Pattern Access

TierPatternsCategories
Free30CB, PE
Pro60CB, PE, CE, MA
Team90CB, PE, CE, MA, AN, PI
Enterprise90CB, PE, CE, MA, AN, PI + priority support

Scoring

RegexGuard uses a deductive scoring system starting at 100 (perfect):

SeverityPoint DeductionDescription
Critical-25 per findingSevere risk (ReDoS, injection, missing validation anchors)
High-15 per findingSignificant problem (portability bugs, correctness errors)
Medium-8 per findingModerate concern (engine-specific features, maintainability)
Low-3 per findingInformational / best practice suggestion

Grading Scale

GradeScore RangeMeaning
A90-100Excellent regex quality
B80-89Good patterns with minor issues
C70-79Acceptable but needs improvement
D60-69Poor regex quality
FBelow 60Critical regex problems
  • Pass threshold: 70 (Grade C or better)
  • Exit code 0 = pass (score >= 70)
  • Exit code 1 = fail (score < 70)

Configuration

Users can configure RegexGuard in ~/.openclaw/openclaw.json:

{
  "skills": {
    "entries": {
      "regexguard": {
        "enabled": true,
        "apiKey": "YOUR_LICENSE_KEY_HERE",
        "config": {
          "severityThreshold": "medium",
          "ignorePatterns": ["**/test/**", "**/fixtures/**", "**/*.test.*"],
          "ignoreChecks": [],
          "reportFormat": "text"
        }
      }
    }
  }
}

Important Notes

  • Free tier works immediately with no configuration
  • All scanning happens locally -- no code is sent to external servers
  • License validation is offline -- no phone-home or network calls
  • Pattern matching only -- no AST parsing, no external dependencies beyond bash
  • Supports scanning all file types in a single pass
  • Git hooks use lefthook which must be installed (see install metadata above)
  • Exit codes: 0 = pass (score >= 70), 1 = fail (for CI/CD integration)
  • Output formats: text (default), json, html

Error Handling

  • If lefthook is not installed and user tries hooks, prompt to install it
  • If license key is invalid or expired, show clear message with link to https://regexguard.pages.dev/renew
  • If a file is binary, skip it automatically with no warning
  • If no scannable files found in target, report clean scan with info message
  • If an invalid category is specified with --category, show available categories

When to Use RegexGuard

The user might say things like:

  • "Scan my code for regex issues"
  • "Check for catastrophic backtracking"
  • "Find ReDoS vulnerabilities in my patterns"
  • "Check for non-portable regex syntax"
  • "Audit regex correctness in my codebase"
  • "Find regex injection risks"
  • "Check if my validation regex has proper anchors"
  • "Detect overly complex regex patterns"
  • "Scan for regex portability problems"
  • "Find unsafe dynamic regex construction"
  • "Run a regex quality audit"
  • "Generate a regex health report"
  • "Check for unescaped dots in my patterns"
  • "Find missing anchors in validation regex"
  • "Check for user input in regex constructors"

平台分布

OpenClaw

70.41%
按下载量换算528

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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