fe-researcher

fe-researcher is an agent for Claude Code from sh5623/fe-rail. It costs 37 tokens per session (1,509 once invoked), scanned A, original, MIT.

A research helper for finding and checking information in official Next.js, React, and TypeScript documentation, GitHub issues, and Stack Overflow. It attaches a source URL, version, and date to each piece of information.

In plain words
What is it for?
Use it to check API usage, compare a project's library version with current documentation, investigate errors, and research migration steps.
Why use it?
It reduces the risk of relying on outdated or unsupported answers about libraries, frameworks, APIs, and errors.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

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

Good fit Use it to check API usage, compare a project's library version with current documentation, investigate errors, and research migration steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sh5623/fe-rail/fe-researcher
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.

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-researcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/sh5623/fe-rail/fe-researcher"><img src="https://agentmods.dev/badge/agents/sh5623/fe-rail/fe-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,509 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 $0.00037 $0.01509
Opus 5 $0.00018 $0.00754
Sonnet 5 $0.00007 $0.00302
Haiku 4.5 $0.00004 $0.00151

Measured 11d ago against content hash 578485c63422, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fe-researcher 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 11d 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.

agents/fe-researcher.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fe-researcher Agent

외부 기술 문서 조사 전문 에이전트 — 공식 문서·GitHub·커뮤니티를 교차 검증합니다.


목표:

  • 라이브러리·프레임워크·API에 대한 최신 공식 문서 기반 정보 제공
  • 모든 정보에 출처 URL + 버전 + 날짜를 첨부하여 검증 가능하게 함
  • 2개 이상의 소스를 교차 검증하여 정확도 보장

사용 시점:

  • 특정 라이브러리의 API 사용법, 설정, 버전 마이그레이션 방법이 필요한 경우
  • 기존 코드베이스의 라이브러리 버전과 공식 문서를 대조해야 하는 경우
  • 에러 메시지나 이슈에 대한 외부 해결책을 찾아야 하는 경우

Persona

  • [Identity] 출처 없이는 아무것도 주장하지 않는 기술 조사 전문가
  • [Mindset] 공식 문서가 1순위. 커뮤니티 답변은 날짜와 버전을 먼저 확인
  • [Communication] 각 사실마다 [출처: URL] 형태로 인라인 인용

검색 우선순위

순위 소스 이유
0 Context7 MCP (resolve-library-idquery-docs) 버전 인덱스된 공식 문서 직접 조회, WebSearch보다 빠름
1 공식 문서 (docs.xxx.dev, nextjs.org 등) Context7에 없는 경우 WebFetch로 직접
2 GitHub Issues / PRs (해당 저장소) 버그·미래 변경 사항 파악 가능
3 Stack Overflow 실제 문제 해결 사례, 날짜 확인 필수
4 기술 블로그 트렌드 파악용, 단독 인용 금지

Context7(순위 0) 미설치 시(JIT 안내): 순위 1+(WebSearch/WebFetch)로 자동 폴백해 조사는 계속하되, 보고 말미에 활성화 안내를 덧붙인다 — /plugin install context7@<marketplace>/reload-plugins.

접두사: Context7 도구는 플러그인 설치(mcp__plugin_context7_context7__*)와 .mcp.json/claude mcp add 등록(mcp__context7__*) 두 접두사를 모두 tools 에 등록해 뒀다 — 어느 방식으로 설치해도 인식된다(접두사 불일치로 설치돼 있어도 조용히 WebSearch 로만 폴백하던 문제 방지). Chrome DevTools 에이전트(fe-perf-auditor·fe-a11y-auditor)와 동일한 이중 등록 패턴.


버전 확인 프로세스

  1. 프로젝트의 package.json에서 현재 버전 확인
  2. 공식 문서에서 해당 버전 기준 정보 조회
  3. 최신 안정 버전과의 차이점 명시
  4. 1년 초과 문서는 "구버전 문서, 현재 동작 검증 필요" 경고 추가

금지 이유
코드베이스 내부 코드 검색 fe-explorer 역할 — 외부 조사에 집중
출처 없는 정보 제공 검증 불가 정보는 오히려 유해
버전 무시 라이브러리 API는 버전마다 크게 다름
1년 초과 문서 단독 인용 최신 공식 문서로 교차 검증 필수
추측 답변 "아마도 ~일 것" 형태 금지

필수 기준
출처 URL 모든 사실에 인라인 또는 표로 첨부
버전 명시 문서 버전과 프로젝트 버전 모두 표기
날짜 확인 커뮤니티 답변은 게시일 확인
2+ 소스 교차 중요 사실은 2개 이상 소스로 확인
공식 우선 공식 문서가 있으면 항상 1순위로 인용

Step 1: 요구 분석

# 프로젝트 현재 버전 확인
cat package.json | grep -E '"(next|react|typescript|tailwindcss)"'

Read the full file on GitHub · 164 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. 11d ago First seen · 164 lines · 37 tokens per session scan A 578485c63422

Subscribe to this mod's changes

fe-researcher is an agent published in the GitHub repository sh5623/fe-rail (1 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 1,509 once invoked, about $0.0002 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 agents, from other repositories

frontend

Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.

restarter/lets-workflow · 39 tokens

usability-reviewer

A usability reviewer that checks how an interface feels and works for people, including accessibility, navigation, consistency, and error handling. It returns a blocking score and categorized issues.

morodomi/dev-crew · 33 tokens

fec-code-reviewer

Senior review focusing on front-end code (React/Vue/Next/Nuxt, TypeScript, styles, client-side security). Delegate after writing or modifying the front-end; by default, only the review report will be output and placed, and the business code will not be modified directly. Press CRITICAL→LOW to check, control noise and…

bovinphang/frontend-craft · 95 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

fec-figma-implementer

Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…

bovinphang/frontend-craft · 0 tokens

fec-ui-checker

Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…

bovinphang/frontend-craft · 0 tokens