agentrigs
+ submit rig
~ / rigs / hashgraph-online / hol-guard

hashgraph-online/hol-guard

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

↗ GitHub ★ 784 apache-2.0 updated 3d ago project Codex Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~397 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/hashgraph-online/hol-guard

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit hashgraph-online/hol-guard/.factory/skills/hol-guard .claude/skills/hol-guard
$ npx degit hashgraph-online/hol-guard/integrations/claude-code-plugin/skills/setup .claude/skills/setup
$ npx degit hashgraph-online/hol-guard/integrations/claude-code-plugin/skills/status .claude/skills/status

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (3)

hol-guardsetupstatus

Similar rigs

nizos/tdd-guard
Automated TDD enforcement for Claude Code
★ 2,353 project Claude Code 1 skills 25d ago
Minimalist 1.3k tok ·
terranc/claude-telegram-bot-bridge
A lightweight Telegram bot that bridges Claude Code to any local folder, with autostart support for remote mobile development.
★ 134 project Claude Code 1 skills 4mo ago
Minimalist 2.1k tok ·
greenpolo/cc-multi-cli-plugin
Claude Code plugin: delegate to Codex, Gemini, Cursor, GitHub Copilot, and Qwen CLIs via their native protocols (ACP, ASP). Use /gemini:research, /cursor:debug, /codex:execute, /copilot:review and more — Claude can also auto-dispatch.
★ 92 collection Claude CodeCodex 5 skills 23d ago
Pragmatist 2.2k tok ·
stefanoginella/aicontainer
Sandboxed devcontainer for running Claude Code, Codex, and OpenCode in bypass / auto-approve mode.
★ 20 project Claude CodeCodex 1 skills 4d ago
Pragmatist 13.0k tok ·
copied ✓