Agent skill
Setup
Install or initialize HOL Guard local runtime protection for Claude Code. Use when the user explicitly asks to install, enable, set up, or repair HOL Guard.
Get the complete skill folder, including its scripts and reference files.
·
When to use this skill
Use Setup when an AI agent needs a reusable SKILL.md workflow for this job: Install or initialize HOL Guard local runtime protection for Claude Code. Use when the user explicitly asks to install, enable, set up, or repair HOL Guard.
When not to use it
Skip Setup when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/setup/SKILL.md. For a shared project, commit the folder at .claude/skills/setup/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
What supports this recommendation?
70/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 77/100
- Practical detail
- 68/100
- Source evidence
- 63/100
- Source signals
- 70/100
Model compatibility evidence
- claude · inferred
The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.
- chatgpt · untested
No model-specific signal or recorded compatibility test was found.
- gemini · untested
No model-specific signal or recorded compatibility test was found.
- copilot · untested
No model-specific signal or recorded compatibility test was found.
- llama · untested
No model-specific signal or recorded compatibility test was found.
- perplexity · untested
No model-specific signal or recorded compatibility test was found.
- mistral · untested
No model-specific signal or recorded compatibility test was found.
- grok · untested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Set up HOL Guard for Claude Code
HOL Guard is a separate open-source local runtime package. This plugin is the Claude Code discovery and setup companion; the actual security boundary is installed and maintained by the `hol-guard` CLI.
Follow this sequence exactly:
1. Check whether HOL Guard is already available without changing the machine:
```bash command -v hol-guard && hol-guard --version ```
2. If `hol-guard` is missing, explain that installation changes the user's Python/pipx environment and ask for explicit approval before installing it. Do not silently substitute another package manager.
3. After approval, install from PyPI with the documented command:
```bash pipx install hol-guard ```
If `pipx` is unavailable, stop and show the user the install requirement. Do not curl or execute an unreviewed bootstrap script as a fallback.
4. Initialize Guard interactively:
```bash hol-guard init ```
Do not add `--yes` unless the user explicitly requests unattended setup. `hol-guard init` owns Claude Code hook installation and avoids maintaining a second security implementation in this plugin.
5. Verify the resulting local protection:
```bash hol-guard status ```
6. Tell the user what Guard reports as active or degraded. Do not claim protection from plugin installation alone.
HOL Guard works locally without Guard Cloud. Cloud connection is optional and should only be offered when the user asks for synchronized history, team policy, fleet visibility, or shared approvals.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.
Open your saved libraryIntended uses
- Use Setup when this documented workflow matches the task.
Related skills
Related skills in this directory, for comparison before you install another skill.
coding
Prompt template
A Half-Built Pyramid and the Leader Who Turned Labor Into Legacy
A reusable prompt for asking an AI assistant to work as A Half-Built Pyramid and the Leader Who Turned Labor Into Legacy.
Content score 57/100 · provisional
coding
Prompt template
Act as a Patient, Non-Technical Android Studio Guide
A reusable prompt for asking an AI assistant to work as Act as a Patient, Non-Technical Android Studio Guide.
Content score 56/100 · provisional
coding
Agent skill
Add Ave Record
The main workflow for this repo. Adds one new AVE record end to end.
Content score 65/100 · provisional
coding
Agent skill
Add Backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
Content score 70/100 · provisional