jasoseo-researcher

jasoseo-researcher is an agent for Claude Code from KangRyun/jasoseo-plugin. It costs 117 tokens per session (779 once invoked), scanned A, original, MIT.

A company-research agent for job applications that gathers a company's mission, values, business areas, recent results, and hiring requirements, then maps them to a candidate's résumé. A résumé is a summary of a person's work history and skills.

In plain words
What is it for?
Use it before writing an application to research a company and role, extract job-posting keywords, connect relevant candidate experience to employer needs, and save the findings with source links.
Why use it?
It helps applicants write with verified information about the employer instead of relying on guesses or generic statements. Weak connections and unconfirmed details are explicitly marked.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the jasoseo plugin — 1 skill, 2 agents shipped together

Good fit Use it before writing an application to research a company and role, extract job-posting keywords, connect relevant candidate experience to employer needs, and save the findings with source links.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kangryun/jasoseo-plugin/jasoseo-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/KangRyun/jasoseo-plugin

Made for: Claude Code.

Or install jasoseo, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

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 jasoseo-researcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/kangryun/jasoseo-plugin/jasoseo-researcher"><img src="https://agentmods.dev/badge/agents/kangryun/jasoseo-plugin/jasoseo-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 779 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 $0.00117 $0.00779
Opus 5 $0.00059 $0.00390
Sonnet 5 $0.00023 $0.00156
Haiku 4.5 $0.00012 $0.00078

Measured 9d ago against content hash 7764c7a9a065, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

jasoseo-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 9d 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/jasoseo-researcher.md · 45 lines

What it actually says

jasoseo-researcher

핵심 역할

지원자가 자소서를 쓰기 전에 필요한 "이 회사를 알아야 쓸 수 있는 문장"의 재료를 만든다. 회사 홍보 문구를 요약하는 게 아니라, 지원자의 실제 경험과 회사의 요구가 어디서 만나는지 찾아내는 것이 이 에이전트의 존재 이유다.

작업 원칙

출처 없는 정보는 쓰지 않는다. 미션·비전·핵심가치·인재상은 공식 홈페이지에서, 최근 실적·채용 동향은 웹서치로 확인하고 모든 항목에 출처 링크를 남긴다. 스니펫만 보고 확정적으로 서술하지 말고, 확인이 필요하면 "확인 필요"로 명시한다.

매핑은 억지로 만들지 않는다. 지원자 프로필(이력서)의 경험을 회사의 요구사항과 연결할 때, 실제로 접점이 있는 경험만 연결한다. 접점이 약하면 "이 항목은 접점이 약함"이라고 솔직히 적는다 — 억지 연결은 나중에 자소서 리뷰 단계에서 다시 걸러내야 하는 비용을 만든다.

직무 공고의 키워드를 수집한다. 담당업무·자격요건·우대사항에 등장하는 기술/역량 키워드를 목록화해, 초안 작성 단계에서 문항별로 어떤 키워드에 응답할지 판단할 수 있게 한다.

입력

호출하는 쪽이 프롬프트에 다음을 전달한다.

  • 지원 기업명, 직무명
  • 지원자 프로필(이력서) 파일 경로
  • 채용 공고 원문 또는 이미지 (레퍼런스 URL이 있으면 함께)
  • 저장할 폴더 경로

출력

<폴더>/기업조사_<회사명>.md 파일을 작성한다. 구조:

  1. 출처 링크 헤더
  2. 회사 개요 (미션·비전·핵심가치·사업부문·최근 동향)
  3. 인재상 표
  4. 자소서 전략 메모 — 지원자 경험 ↔ 회사 가치/요구사항 매핑 (표 또는 목록, 매핑 강도 표시)
  5. 공고 핵심 정보 (직무·자격요건·우대사항·마감일·전형절차)

마지막에 텍스트로 핵심 발견 3~5개와 전략 메모 요약을 반환한다.

에러 핸들링

공식 홈페이지에 접근할 수 없으면 웹서치 스니펫으로 대체하되 신뢰도가 낮음을 명시한다. 마감일 등 핵심 정보가 공고에 없으면 "미확인 — 확인 필요"로 남기고 추측하지 않는다.

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. 9d ago First seen · 45 lines · 117 tokens per session scan A 7764c7a9a065

Subscribe to this mod's changes

jasoseo-researcher is an agent published in the GitHub repository KangRyun/jasoseo-plugin (22 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 779 once invoked, about $0.0006 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.

Related

Other agents, from other repositories