A safety guard for shell commands, which are text instructions that can change files, systems, or online services. It blocks commands that could delete data or force major changes.

Use it to prevent dangerous commands involving file deletion, Git force-pushing, Docker, Kubernetes, Terraform, cloud services, databases, and similar tools.

It reduces the chance that an accidental command will remove files, damage a database, erase cloud resources, or overwrite shared Git history.

safety-net — Plugin by andreasasprou

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add andreasasprou/agent-skills

agentmods

npx agentmods add plugins/andreasasprou/agent-skills/safety-net

Clone the repo

git clone --depth 1 https://github.com/andreasasprou/agent-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan C 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade C, and why

safety-net scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"description": "Block destructive shell commands before execution. Prevents rm -rf, git push --force, docker system prune, kubectl delete, terraform destroy, cloud deletions (AWS/GCP/Azure), database drops, and 200+ dang

plugins/safety-net/.claude-plugin/plugin.json · 42 lines

What it actually says

{
  "name": "safety-net",
  "description": "Block destructive shell commands before execution. Prevents rm -rf, git push --force, docker system prune, kubectl delete, terraform destroy, cloud deletions (AWS/GCP/Azure), database drops, and 200+ dangerous patterns.",
  "version": "0.4.0",
  "author": {
    "name": "Andreas Asprou"
  },
  "homepage": "https://github.com/andreasasprou/agent-skills",
  "repository": "https://github.com/andreasasprou/agent-skills",
  "license": "MIT",
  "keywords": [
    "safety",
    "hooks",
    "security",
    "destructive",
    "block",
    "rm",
    "git",
    "aws",
    "docker",
    "kubernetes",
    "kubectl",
    "helm",
    "terraform",
    "pulumi",
    "gcloud",
    "gsutil",
    "azure",
    "database",
    "psql",
    "mysql",
    "mongo",
    "redis",
    "github",
    "gh",
    "stripe",
    "chmod",
    "dd",
    "mkfs"
  ]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 42 lines scan C d880c27f2d13

Subscribe to this mod's changes

safety-net is a plugin published in the GitHub repository andreasasprou/agent-skills (7 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security

humanizer

Rewrite AI-sounding text so it reads naturally without changing what it says.

blader/humanizer · not measured

nextjs

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

vercel/next.js · not measured

claude-plugins-official marketplace

Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.

anthropics/claude-plugins-official · not measured

knowledge-work-plugins marketplace

Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.

anthropics/knowledge-work-plugins · not measured

ecc

Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.

affaan-m/ECC · not measured

ui-ux-pro-max

UI/UX design intelligence. Searchable local database with 84 styles, 192 palettes, 74 font pairings, 25 charts, and 22 stacks (React, Next.js, Vue, Nuxt.js, Nuxt UI, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP…

nextlevelbuilder/ui-ux-pro-max-skill · not measured

safety-net