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.
npx agentmods add settings/cacr92/wereply/settingsgit clone --depth 1 https://github.com/cacr92/WeReplyGrade C, and why
settings 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 yesterday.
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.
"command": "jq -r '.tool_input.command' | { read cmd; case \"$cmd\" in *\"rm -rf\"*|*\"del /s\"*|*format*|*shutdown*|*reboot*) echo '🚫 禁止执行危险命令'; exit 2 ;; esac; }" How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"env": {
"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"
},
"permissions": {
"defaultMode": "bypassPermissions"
},
"alwaysThinkingEnabled": true,
"statusLine": {
"type": "command",
"command": "npx ccusage statusline"
},
"enabledPlugins": {
"rust-analyzer-lsp@claude-plugins-official": true,
"typescript-lsp@claude-plugins-official": true
},
"hooks": {
"SessionStart": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "cat <<'EOF'\n=========================================\n🦀 饲料配方系统 - Tauri + Rust + React\n=========================================\n\n📋 开发规范提醒：\n ❌ 禁止 console.log - 使用 message 组件\n ❌ 禁止 as any - 使用精确类型断言\n ✅ 修改代码后更新 CHANGELOG.md\n ✅ Rust 修改后会自动生成类型绑定\n\n⚠️ AI 执行流程规范（强制遵守）：\n 1️⃣ 需求分析 - 按序号列出（1. 2. 3. ...）\n 2️⃣ 任务分解 - 带任务编号（任务1、1.1、1.2...）\n 3️⃣ 创建TodoWrite - 立即创建任务追踪清单\n 4️⃣ 说明每一步 - 执行前必须说明在做什么\n 5️⃣ 标记完成状态 - 逐项标记 ✓已完成/✗未完成\n 6️⃣ 逻辑验证 - 检查逻辑和数据流\n 7️⃣ 代码审查 - 运行lint检查\n\n❗ 如果AI偏离以上流程，请立即打断！\n=========================================\nEOF"
},
{
"type": "command",
"command": "echo \"\n当前分支: $(git branch --show-current)\nGit 状态: $(git status --short | wc -l | tr -d ' ') 个变更\""
}
]
}
],
"UserPromptSubmit": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "echo 💬 开始处理请求..."
}
]
}
],
"PreToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "jq -r '.tool_input.file_path' | { read file_path; case \"$file_path\" in *.env|*.db|*.sqlite|*.key|*.pem|*.p12|*package-lock.json|*Cargo.lock|*.git/*) echo '🚫 禁止修改敏感文件'; exit 2 ;; esac; }"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command":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.
- yesterday First seen · 164 lines scan C 8854e2588b01
settings is a settings file published in the GitHub repository cacr92/WeReply (6 stars, last pushed 7mo 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.
Other settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
superset
Agent settings declaring 1 hook event (PreToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.
electron
Agent settings declaring 17 allowed tools.
uv
Agent settings declaring 2 hook events (SessionStart, PostToolUse).