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.
git 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/second-opinion)<a href="https://agentmods.dev/commands/yudefine/nuxt-supabase-starter/second-opinion"><img src="https://agentmods.dev/badge/commands/yudefine/nuxt-supabase-starter/second-opinion.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 | $0.00015 | $0.00421 |
| Opus 5 | $0.00008 | $0.00211 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
second-opinion 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 8d 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.
What it actually says
/second-opinion — 獨立 Code Review
以全新視角審查最近的變更，專注在真正會影響 production 的問題。
審查範圍
git diff HEAD~1..HEAD # 或指定的 commit range
審查重點
只報告以下類別的問題：
1. 邏輯錯誤
- Off-by-one、條件反轉、null/undefined 未處理
- 非同步競態條件
2. 安全漏洞
- SQL injection、XSS、CSRF
- 敏感資料洩漏（API keys、passwords、error internals）
- RLS policy 繞過
3. 資料完整性
- 資料庫操作缺少 transaction
- Cache invalidation 遺漏
- 型別不匹配（runtime vs compile time）
4. 環境差異
- Dev-only code 洩漏到 production
- 硬編碼的 localhost/開發環境值
- 缺少的環境變數
審查原則
- 不報告 style、naming、refactoring 建議
- 不報告 「可以更好」但不影響正確性的改動
- 只報告 會在 production 造成 bug、crash、或安全問題的發現
- 每個發現附上：檔案位置、問題描述、建議修復
輸出格式
## Second Opinion Review
### 🔴 Critical
（無 / 列出）
### 🟡 Warning
（無 / 列出）
### ✅ Verdict
[SHIP IT / HOLD — 需要修復 N 個問題]
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.
- 8d ago First seen · 63 lines · 15 tokens per session scan A cc2863c9f26a
second-opinion is a command published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 421 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.
Other commands, from other repositories
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
refactor-sprint
Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
game-feel-pass
Review moment-to-moment feedback, response timing, and juice so core actions feel readable and satisfying.
input-review
Review input handling, device coverage, buffering, and control responsiveness from an engine-neutral perspective.
localization-pass
Review localization readiness for text, UI expansion, locale risks, and translation workflow.
save-system-review
Review save/load architecture, persistence risks, and migration concerns.