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/db-migration)<a href="https://agentmods.dev/commands/yudefine/nuxt-supabase-starter/db-migration"><img src="https://agentmods.dev/badge/commands/yudefine/nuxt-supabase-starter/db-migration/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.
<a href="https://agentmods.dev/commands/yudefine/nuxt-supabase-starter/db-migration"><img src="https://agentmods.dev/badge/commands/yudefine/nuxt-supabase-starter/db-migration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.01366 |
| Opus 5.5 | $0.00005 | $0.00546 |
| Sonnet 5.5 | $0.00002 | $0.00273 |
| Haiku 4.5 | $0.00001 | $0.00137 |
Grade A, and why
db-migration 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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
建立新的 Supabase migration,確保符合 rules/modules/db-schema/supabase/migration.md 的所有規範(該規約帶 paths: gating,三端都投影)。
Step 1: 確認需求
詢問使用者要建立什麼樣的 migration:
- 新增表格?
- 修改欄位?
- 建立函式?
- 新增 RLS 政策?
Step 2: 建立 Migration 檔案
使用 Supabase CLI 建立 migration(禁止手動建立 .sql 檔案):
supabase migration new <description_in_snake_case>
Step 3: 撰寫 Migration 內容
根據需求撰寫 SQL,必須遵守以下規範:
函式規範(防 search_path injection)
-- ✅ 正確:search_path 必須是空字串
CREATE OR REPLACE FUNCTION schema_name.function_name()
RETURNS return_type
LANGUAGE plpgsql
SECURITY DEFINER
SET search_path = '' -- 必須是空字串
AS $$
BEGIN
-- 使用完整路徑:schema_name.table_name
SELECT * FROM core.users WHERE id = auth.uid();
END;
$$;
-- ❌ 禁止:任何其他 search_path 值
SET search_path = public, pg_temp -- 禁止
SET search_path = public -- 禁止
Schema 規範
- 使用正確的 schema 前綴(如
public.、core.,或專案自訂業務 schema) - 所有表格/函式引用使用完整路徑(避免裸表名觸發
search_pathresolution)
Step 4: 本地測試與類型產生(自動)
依序執行以下步驟,任何步驟失敗則停止並顯示錯誤。MUST 透過 package.json 偵測 consumer 是走遠端 wrapper(pnpm db:*,含 existing-server / self-hosted)還是本機 Docker。NEVER 看到遠端 wrapper 就改跑本機 supabase start。
# 從 package.json 讀 types 路徑(若有自訂);fallback 到 conventional locations
# 避開頂層 return(Node script 不允許)— 用 if/else 與 .find()
TYPES=$(node -e "
const fs = require('fs');
const pkg = require('./package.json');
const custom = pkg.config && pkg.config.dbTypesPath;
const candidates = [
'packages/core/app/types/database.types.ts',
'app/types/database.types.ts',
'shared/types/database.types.ts',
'src/types/database.types.ts',
];
const path = custom || candidates.find(function(p) { return fs.existsSync(p); }) || 'app/types/database.types.ts';
console.log(path);
")
USE_DB_WRAPPER=$(node -e "process.exit(require('./package.json').scripts?.['db:reset'] ? 0 : 1)" 2>/dev/null && echo yes || echo no)
if [ "$USE_DB_WRAPPER" = yes ]; then
# 遠端 / existing-server:走 pnpm db:*(wrapper 會擋本機 Docker;db:reset 內部跑 db:types 寫到 $TYPES)
pnpm db:reset
pnpm db:lint # 安全檢查(必須零警告)
pnpm typecheck
else
# 本機 Docker(this-machine;沒有 pnpm db:reset wrapper)
supabase db reset
supabase db lint --level warning
# 直接重導向到 $TYPES — 不用 tee(pipeline 會吞 supabase gen types 失敗狀態)
supabase gen types typescript --local > "$TYPES"
pnpm typecheck
fi
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.
- 19d ago Changed · -1 lines c7e699da052f
- 1mo ago Changed 95c47c0694af
- 1mo ago Changed · +1 lines ab29e3e2d901
- 1mo ago Changed · -8 lines a883a148a6ce
- 1mo ago Changed · +2 lines af121392f049
- 1mo ago Changed 7af1b73d0d3c
- 1mo ago First seen · 146 lines · 12 tokens per session scan A c65b8e219708
db-migration is a command published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 1,366 once invoked, about $0.0000 per session on Opus 5.5. 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
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.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.