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 skills add rungchan2/frontend-skills --skill initial-settinggit clone --depth 1 https://github.com/rungchan2/frontend-skillsWrote 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/skills/rungchan2/frontend-skills/initial-setting)<a href="https://agentmods.dev/skills/rungchan2/frontend-skills/initial-setting"><img src="https://agentmods.dev/badge/skills/rungchan2/frontend-skills/initial-setting.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 | $0.00146 | $0.02381 |
| Opus 5 | $0.00073 | $0.01190 |
| Sonnet 5 | $0.00029 | $0.00476 |
| Haiku 4.5 | $0.00015 | $0.00238 |
Grade A, and why
initial-setting 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 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.
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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supabase DB Setting
Supabase 프로젝트에서 DB 스키마 기반 개발환경을 한 번에 세팅한다. 에이전트가 4000줄+ 타입 파일을 직접 읽지 않고도 스키마를 효과적으로 파악할 수 있게 하는 것이 핵심 목적이다.
세팅 항목 요약
| # | 항목 | 파일 |
|---|---|---|
| 1 | DB 스키마 CLI 스크립트 | scripts/db-schema.sh |
| 2 | package.json 스크립트 | db:schema, update-type |
| 3 | Supabase client/server 타입 바인딩 | client.ts, server.ts |
| 4 | CLAUDE.md DB 섹션 | 마이그레이션 규칙 + 테이블/뷰/함수 목록 + CLI 가이드 |
| 5 | 타입 생성 안내 | supabase login → link → update-type |
Step 0: 프로젝트 분석
세팅 전 아래를 파악한다:
분석 대상:
├─ package.json — 패키지 매니저 판별
├─ @supabase/ssr 또는 @supabase/supabase-js 설치 여부
├─ tsconfig.json — path alias (@/ 등)
├─ database.types.ts 기존 위치
├─ supabase client/server 파일 위치
├─ CLAUDE.md 존재 여부 및 기존 DB 섹션
└─ supabase 프로젝트 연결 여부
패키지 매니저 판별:
pnpm-lock.yaml→ pnpm /yarn.lock→ yarn /bun.lockb→ bun / 기본 → npm
Step 1: DB 스키마 CLI 스크립트 설치
이 스킬의 scripts/db-schema.sh를 {project-root}/scripts/db-schema.sh에 복사한다.
순수 bash 스크립트로 tsx/node 설치 없이 바로 실행 가능하다.
DB_TYPES_PATH 환경변수로 타입 파일 위치를 오버라이드할 수 있고, 기본적으로 src/types/, types/, lib/types/ 등을 자동 탐색한다.
복사 후 chmod +x scripts/db-schema.sh 실행 권한을 부여한다.
이미 scripts/db-schema.ts (TypeScript 버전)가 있으면 bash 버전으로 교체를 제안한다.
CLI 지원 명령어
| 명령어 | 설명 |
|---|---|
tables |
전체 테이블 이름 목록 |
table <name> |
특정 테이블 스키마 (Row/Insert/Update) |
views |
전체 뷰 이름 목록 |
view <name> |
특정 뷰 스키마 (Row) |
functions |
전체 RPC 함수 목록 (시그니처 포함) |
function <name> |
특정 함수 상세 (Args/Returns) |
enums |
전체 enum 이름 목록 |
enum <name> |
특정 enum 값 목록 |
search <keyword> |
테이블/뷰/함수/enum 통합 검색 |
Step 2: package.json 스크립트 추가
{
"scripts": {
"db:schema": "bash scripts/db-schema.sh",
"update-type": "supabase gen types typescript --linked --debug > {TYPES_PATH}"
}
}
{TYPES_PATH}: Step 0에서 파악한 database.types.ts 경로- 기존에 동일 스크립트가 있으면 덮어쓰지 않고 확인
Step 3: Supabase client/server 타입 바인딩
기존 Supabase client와 server 파일을 찾아 Database 제네릭 타입을 바인딩한다.
이미 <Database> 제네릭을 사용하고 있으면 스킵한다.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 239 lines · 146 tokens per session scan A a7bbfb9f16a6
initial-setting is a skill published in the GitHub repository rungchan2/frontend-skills (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 146 tokens to every session and 2,381 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
adding-personhog-rpc
Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js clients, Rust implementation (storage trait, postgres queries, service handler, router wiring), and index compatibility validation. Use when adding a new gRPC…
azure-cosmos-ts
Data plane SDK for Azure Cosmos DB NoSQL API operations — CRUD on documents, queries, bulk operations.
kysely
Guidelines for developing with Kysely, a type-safe TypeScript SQL query builder with autocompletion support.
drizzle-orm
Guidelines for developing with Drizzle ORM, a lightweight type-safe TypeScript ORM with SQL-like syntax.
drizzle-migrations
Drizzle ORM schema management and SQLite migrations — adding tables, modifying columns, creating indexes, generating and running migrations, Drizzle query patterns. NOT for Prisma, TypeORM, Sequelize, or raw SQL migration tools.
neo4j-driver-javascript-skill
Neo4j JavaScript/TypeScript Driver v6 — driver lifecycle, executeQuery, managed transactions (executeRead/executeWrite), session.run, Integer handling, JSON serialization, record access, async/await patterns, TypeScript types, error handling, and connection setup for Node.js and browser. Use when writing JS/TS code…