solidity-typescript-hardhat-template

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.

Security

Grade A, and why

solidity-typescript-hardhat-template 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 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.

.claude/settings.json · 40 lines

What it actually says

{
	"permissions": {
		"allow": [
			"Bash(npm run test)",
			"Bash(npm run compile)",
			"Bash(npm run coverage)",
			"Bash(npm run format:*)",
			"Bash(npm run sol:format:*)",
			"Bash(npm run lint:*)",
			"Bash(npm run solhint)"
		]
	},
	"hooks": {
		"PostToolUse": [
			{
				"matcher": "Edit|Write",
				"hooks": [
					{
						"type": "command",
						"command": "npx prettier --write \"$CLAUDE_FILE_PATH\" 2>/dev/null || true",
						"description": "Auto-format edited files with Prettier"
					}
				]
			}
		],
		"PreToolUse": [
			{
				"matcher": "Edit|Write",
				"hooks": [
					{
						"type": "command",
						"command": "if echo \"$CLAUDE_FILE_PATH\" | grep -qE '^\\.env$|package-lock\\.json$'; then echo 'BLOCK: Do not edit .env or lock files' >&2; exit 1; fi",
						"description": "Block edits to .env and lock files"
					}
				]
			}
		]
	}
}

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.

Related

Other settings, from other repositories