fe-start

fe-start is a skill for Claude Code from sh5623/fe-rail. It costs 152 tokens per session (5,192 once invoked), scanned A, original, MIT.

An automated feature-development workflow that takes an approved feature.md file through confirmation, implementation, review, commit, and pull request creation.

In plain words
What is it for?
Use it for features with clear requirements and clear pass-or-fail checks. It is not intended for one-line changes, quick bug fixes, exploratory work, or unclear requirements.
Why use it?
It coordinates the repeated steps of feature work and pauses for approval before coding and before the later workflow stage.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the fe-rail plugin — 5 skills, 15 agents, 4 hooks shipped together

Good fit Use it for features with clear requirements and clear pass-or-fail checks. It is not intended for one-line changes, quick bug fixes, exploratory work, or unclear requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sh5623/fe-rail/fe-start
Install

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.

Any agent
npx skills add sh5623/fe-rail --skill fe-start
Clone the repo
git clone --depth 1 https://github.com/sh5623/fe-rail

Made for: Claude Code.

Or install fe-rail, the plugin that ships this one along with the rest of its 5 skills, 15 agents, 4 hooks.

Wrote 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.

agentmods badge for fe-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/sh5623/fe-rail/fe-start/github.svg)](https://agentmods.dev/skills/sh5623/fe-rail/fe-start)
Your own site
<a href="https://agentmods.dev/skills/sh5623/fe-rail/fe-start"><img src="https://agentmods.dev/badge/skills/sh5623/fe-rail/fe-start/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.

agentmods 80×15 button for fe-start

Your own site · 80×15
<a href="https://agentmods.dev/skills/sh5623/fe-rail/fe-start"><img src="https://agentmods.dev/badge/skills/sh5623/fe-rail/fe-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,192 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.05192
Opus 5 $0.00076 $0.02596
Sonnet 5 $0.00030 $0.01038
Haiku 4.5 $0.00015 $0.00519

Measured 4d ago against content hash da7c88fdd0d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fe-start 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 4d 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.

skills/fe-start/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FE Start — 원스톱 자동화 스킬

feature.md 하나로 PR까지 자동으로 처리합니다. 중간에 딱 두 번만 묻습니다.

When to Use

  • "fe-start feature.md" 실행 시
  • "feature.md로 시작해줘" 라고 말할 때
  • 자동화 모드로 기능 개발 시작할 때

When NOT to Use

  • 단발 버그 핫픽스 / 1줄·국소 변경 → fe-build 또는 직접 수정
  • 탐색·조사성 작업(무엇을 만들지 미정) → 직접 프롬프트
  • 통과/실패 신호가 모호해 완료 판정이 어려운 작업 → 풀 파이프라인 부적합

반복되고 통과/실패가 명확한 기능 개발에만 풀 파이프라인을 쓴다 (루프 비용 대비 효과).

Instructions

Phase 0 — feature.md 읽기 및 분석


feature.md 존재 확인 → 없으면: "feature.md가 없습니다. fe-spec 스킬로 먼저 작성해주세요." → 있으면: 파일 읽고 요구사항 파악

분석 결과를 요약해서 보여줍니다:

  • 구현할 컴포넌트/기능
  • 영향받는 파일
  • 예상 소요 단계

Phase 1 — 첫 번째 확인 ⛔ STOP

Phase 0 요약을 보여준 뒤 AskUserQuestion 으로 진행 여부를 묻는다 (자유 텍스트 아님 — 단일 선택 라디오). 승인 전 코드 작성 금지.

// AskUserQuestion 호출 — 단일 선택(라디오)
{
  "questions": [{
    "header": "구현 시작",
    "question": "위 내용으로 구현을 시작할까요?",
    "multiSelect": false,
    "options": [
      { "label": "구현 시작", "description": "스펙대로 Phase 2 부터 구현 진행" },
      { "label": "계획만",    "description": "코드 작성 없이 계획만 확인하고 멈춤 (--plan-only 와 동일)" },
      { "label": "중단",      "description": "시작하지 않고 멈춤" }
    ]
  }]
}
  • 구현 시작 → Phase 2 로 진행. 그 외(계획만·중단·Other) → 코드 작성 없이 멈추고 사용자 지시를 기다린다.

예외 (중복 확인 방지): fe-spec Phase 3 의 "풀 자동" 선택으로 진입한 경우, 구현 시작 승인을 이미 받은 것이므로 이 질문은 생략하고 Phase 2 부터 시작한다. (standalone fe-start feature.md 진입은 그대로 이 확인을 거친다.)


Phase 2 — 구현 (fe-build 스킬 기준 적용)

  1. 프레임워크 규칙 로드 (fe-build Phase 1 ④ 와 동일) — 이 스킬의 base directory 기준 ../../docs/framework-rules.md 에서 «공통 규칙» 절 + 감지한 프레임워크 절만 Read 한다(모노레포면 ../../docs/monorepo.md 도). 소비자 프로젝트 CLAUDE.md 가 우선. 이후 모든 에이전트 위임(fe-architect·fe-build-fixer·fe-reviewer·fe-perf-auditor·fe-a11y-auditor)에 그 절대경로를 브리프로 넘긴다 — 에이전트는 플러그인 트리 위치를 모른다.
  2. 관련 기존 코드 탐색
  3. 타입 정의
  4. 커스텀 훅 작성
  5. 컴포넌트 구현
  6. 테스트 작성

재위임 상한·실패 출구 (Phase 3·4 공통) 자동 수정/리뷰 재위임은 같은 항목 군(群) 기준 누적 3회까지. 3회 후 미해소면 루프를 멈추고 사람에게 에스컬레이션 — 미해소 항목·시도 이력(각 회차 무엇을 바꿨고 왜 막혔는지)·추정 원인을 STOP 으로 보고한다. (개별 에이전트 maxTurns 는 단일 호출 경계라 이 오케스트레이션 루프를 못 막는다.) 반복 신호 전달: 직전 회차 미해소 사유를 다음 위임 컨텍스트에 넣어 같은 접근의 재시도를 막는다.

Read the full file on GitHub · 268 lines

Changes

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.

  1. 4d ago Changed · +18 lines da7c88fdd0d7
  2. 11d ago First seen · 250 lines · 152 tokens per session scan A ee6e8afa6233

Subscribe to this mod's changes

fe-start is a skill published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 5d ago), licensed MIT. It adds 152 tokens to every session and 5,192 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

procoder

Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…

azrtydxb/procoder · 101 tokens

pr-feedback

Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.

jjanczur/tyran · 57 tokens

detect-task

Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.

restarter/lets-workflow · 41 tokens

loop-bb-pr

A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.

restarter/lets-workflow · 118 tokens

take-task

A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.

restarter/lets-workflow · 76 tokens

session-boundary

Internal skill for commands. Resolve and VALIDATE this branch's session boundary - the ref a session's commit range is measured from - and report how much it can be trusted. Do not trigger on user conversation; only when a command needs the session range.

restarter/lets-workflow · 55 tokens