What is tool-defense?

A tower-defense game displayed above the coding prompt, where the enemies represent the agent's real tool calls. You place and upgrade towers to defend the base while the agent works.

It is for visualising Bash, file edits, web or MCP calls, and agent calls as different enemies in a terminal game. It needs function hooks and mouse input.

It turns tool activity into a game you can watch and interact with during the agent's turn. It does not use model tokens.

tool-defense — Plugin for Claude Code by davila7/claude-code-templates

About the project

Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.

davila7/claude-code-templates · 33,152 stars · on GitHub · aitmpl.com

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.

Clone the repo

git clone --depth 1 https://github.com/davila7/claude-code-templates

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/davila7/claude-code-templates/tool-defense/github.svg)](https://agentmods.dev/plugins/davila7/claude-code-templates/tool-defense)

Your own site

<a href="https://agentmods.dev/plugins/davila7/claude-code-templates/tool-defense"><img src="https://agentmods.dev/badge/plugins/davila7/claude-code-templates/tool-defense/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/davila7/claude-code-templates/tool-defense"><img src="https://agentmods.dev/badge/plugins/davila7/claude-code-templates/tool-defense.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

tool-defense scanned grade A with 0 findings 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 1mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

cli-tool/components/mods/games/tool-defense/.claude-plugin/plugin.json · 21 lines

What it actually says

{
  "name": "tool-defense",
  "version": "0.1.0",
  "description": "A tower defense above the Claude Code prompt where every enemy is one of Claude's real tool calls: Bash sends runners, an Edit or Write a slow tank, a web or MCP call a flyer, an Agent a boss. Build and upgrade towers by clicking beside the road, hold the base through Claude's turn. Zero tokens. Needs an interactive terminal with a mouse.",
  "author": {
    "name": "claude-code-templates",
    "url": "https://www.aitmpl.com"
  },
  "repository": "https://github.com/davila7/claude-code-templates",
  "license": "MIT",
  "keywords": [
    "tower-defense",
    "arcade",
    "game",
    "terminal",
    "tui",
    "tool-calls",
    "function-hooks"
  ]
}

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.

1mo ago Changed 11048d532b2c
1mo ago First seen · 21 lines scan A 3e97dc86eaa0

Subscribe to this mod's changes

tool-defense is a plugin published in the GitHub repository davila7/claude-code-templates (33,152 stars, last pushed yesterday), 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 A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.

Claude Code Productivity agent-skills ai-agents anthropic anthropic-claude claude

tool-defense next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tool-defensedavila7/claude-code-templates	Plugin	33k	yesterday	MIT	A	—	Claude Code
keep-alivemrzeszowski/claude-code-keep-alive	Plugin	2	4mo ago	MIT	A	—	Claude Code
cavemanJuliusBrussee/caveman	Plugin	118k	today	Apache-2.0	A	—	Claude Code
claude-status-barm1ckc3s/claude-status-bar	Plugin	726	17d ago	MIT	A	—	Claude Code
claude-skills-library marketplacefrankxai/claude-skills-library	Plugin	47	yesterday	MIT	A	—	Claude Code
statusline-for-claude-codeilia-pluzhnikov/claude-code-statusline	Plugin	120	18d ago	MIT	A	—	Claude Code
commander-hub marketplaceKevinZai/commander	Plugin	6	yesterday	MIT	A	—	Claude Code