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 commands/yudefine/nuxt-supabase-starter/guardgit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote 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.
[](https://agentmods.dev/commands/yudefine/nuxt-supabase-starter/guard)<a href="https://agentmods.dev/commands/yudefine/nuxt-supabase-starter/guard"><img src="https://agentmods.dev/badge/commands/yudefine/nuxt-supabase-starter/guard.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.00339 |
| Opus 5 | $0.00005 | $0.00169 |
| Sonnet 5 | $0.00002 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade C, and why
guard 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 6d 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.
- `rm -rf` What it actually says
/guard — 安全護欄 Dashboard
顯示內容
1. 永久保護路徑
這些路徑由 guard-check.mjs 硬編碼，無法解凍：
supabase/migrations/— 已套用的 migration 不可修改.github/workflows/— CI/CD 配置需人工審查.env/.env.*— 環境變數需人工管理wrangler.jsonc/wrangler.toml— 部署配置需人工審查
2. 自訂凍結路徑
讀取 .claude/guard-state.json 並列出 frozen_paths。
3. 危險指令警告
提醒以下指令需要額外確認：
git push --forcegit reset --hardrm -rfsupabase db push（production）
輸出格式
## 🛡️ Guard Status
### 永久保護
- 🔒 supabase/migrations/
- 🔒 .github/workflows/
- 🔒 .env / .env.*
- 🔒 wrangler.jsonc
### 自訂凍結
- 🧊 <path> (since <date>)
- （無）
### 管理
- 凍結: /freeze <path>
- 解凍: /unfreeze <path>
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.
- 6d ago First seen · 50 lines · 9 tokens per session scan C 9d0b856b8e60
guard is a command published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 339 once invoked, about $0.0000 per session on Opus 5. 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 2026-08-30.
Other commands, from other repositories
validate-auth-schema
Check that the Drizzle schema in db/schema/ still satisfies what Better Auth expects. Better Auth derives its required tables from the enabled plugins, so the generated JSON — not the upstream docs — is the source of truth.
gen-prisma-model
Add a new Prisma model to this codebase: $ARGUMENTS.
dataform-new-table
Create new Dataform table using TDD workflow.
sqlanvil-new-table
Create a new sqlanvil (Postgres/Supabase) table using TDD.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.