Hol Guard

Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, or scanning agent plugins, skills, MCP servers, and marketplace packages before use.

197 stars 47 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add nextlevelbuilder/skillx

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add nextlevelbuilder/skillx --skill hol-guard
Manual install
git clone --depth 1 https://github.com/nextlevelbuilder/skillx.git /tmp/skillx
mkdir -p ~/.claude/skills
cp -r /tmp/skillx/.claude/skills/hol-guard ~/.claude/skills/hol-guard

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# HOL Guard

HOL Guard protects local AI harnesses before tools run. Use it for runtime safety, approval review, package verification, and auditable evidence around agent actions.

## Safety Rules

- Never read `.env` files.
- Never bypass Guard approvals.
- Do not claim a workspace is protected until a Guard command proves it.
- Prefer reversible Guard commands over manual harness configuration edits.
- Treat scanner failures as real until inspected.
- Preserve user changes and inspect `git status --short` before editing a repository.

## Install Check

Probe the CLIs directly so the check works across shells:

```bash
hol-guard --version
plugin-scanner --version
```

If `hol-guard` is missing and the user asked for runtime setup, prefer an isolated install:

```bash
pipx install hol-guard
```

If `plugin-scanner` is missing and scanning was requested, install its separate distribution:

```bash
pipx install plugin-scanner
```

Do not assume the `hol-guard` distribution provides the `plugin-scanner` command. If `pipx` is unavailable, explain that isolated CLI installation is recommended rather than silently modifying the user's Python environment.

After installing HOL Guard:

```bash
hol-guard status
hol-guard detect --json
```

## Protect a Local Harness

First detect the exact supported harness, then use Guard-owned setup:
Read the full skill on GitHub

Details

Skill name
hol-guard
Path
.claude/skills/hol-guard/SKILL.md
Repo updated
8 November 2026

FAQ

What does the Hol Guard skill do?

Use when setting up HOL Guard, protecting local AI harnesses, reviewing Guard approvals or receipts, or scanning agent plugins, skills, MCP servers, and marketplace packages before use.

How do I install the Hol Guard skill?

Claude Code plugin: /plugin marketplace add nextlevelbuilder/skillx. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Hol Guard popular?

It lives in nextlevelbuilder/skillx, which has 197 GitHub stars and 47 forks.

Related skills

Skill Creator

197

nextlevelbuilder/skillx

Create or update Claude skills optimized for Skillmark benchmarks. Use for new skills, skill scripts, references, benchmark optimization, extending Claude's capabilities.

Skill & Plugin Authoring47

Marketing Mindset

197

nextlevelbuilder/skillx

Use when the user needs a professional marketer's operating mindset for any marketing, growth, or client-acquisition task — finding first customers, writing an ad or landing page, designing ad creatives and visuals (how the eye works: background, scene, hero, movement), evaluating an idea, deciding whether to do X to get Y, positioning or launching a B2B or SaaS product, running cold outreach, setting up ads, or writing copy — not a tactical template.

Marketing, Sales & Business47

Skillx

197

nextlevelbuilder/skillx

Find, compare, vet and use AI agent skills from the SkillX.sh catalog. Use when the user asks to discover, search, compare, evaluate, install or run an agent skill (a SKILL.md package) for a task, or asks whether a skill exists for something. Do not use for ordinary coding, writing or research tasks that do not involve finding or managing agent skills.

AI, LLMs & Agents47

China AI Compliance Audit

139

jnMetaCode/shellward

按中国法规(网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识)审计一个 AI 项目的代码仓库,产出每条都带 文件:行 取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's codebase against China's regulations (CSL, PIPL, MLPS 2.0, cross-border data transfer, AI content labeling) with file:line evidence, independent verification and a deterministic validator.

AI, LLMs & AgentsIn 1 list24

Agent Browser

194

thedaviddias/skill-check

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

AI, LLMs & Agents

Tech Stack Eval

393

shawnpang/startup-founder-skills

When the user needs to choose between technologies, frameworks, or tools — or says "which framework should I use", "compare X vs Y", "should we migrate from X to Y", "what database should I use", "calculate TCO".

AI, LLMs & Agents46

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.