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 agentmods add skills/cubha/claude-workflow-plugins/team-researchnpx skills add cubha/claude-workflow-plugins --skill team-researchgit clone --depth 1 https://github.com/cubha/claude-workflow-pluginsWrote 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/cubha/claude-workflow-plugins/team-research)<a href="https://agentmods.dev/skills/cubha/claude-workflow-plugins/team-research"><img src="https://agentmods.dev/badge/skills/cubha/claude-workflow-plugins/team-research.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 | $0.00083 | $0.01428 |
| Opus 5 | $0.00042 | $0.00714 |
| Sonnet 5 | $0.00017 | $0.00286 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
team-research 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 5d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Research — 팀 에이전트 병렬 리서치 오케스트레이터
$ARGUMENTS 에 대해 리서처 서브에이전트를 병렬로 spawn하여 사전 리서치를 수행하고, 결과를 취합하여 보고서를 생성한다.
BRIEF → DISPATCH → COLLECT → SYNTHESIZE → REPORT
이 플러그인은 리서처 서브에이전트 4종을 동봉한다: tech-researcher, architecture-researcher, market-researcher, ux-researcher(--deep 전용).
Phase 0: PARSE — 인자 파싱
$ARGUMENTS 에서 아래를 추출한다:
| 항목 | 추출 대상 | 기본값 |
|---|---|---|
| 프로젝트명 | 첫 번째 인자 또는 자연어에서 추출 | (필수 — 없으면 AskUserQuestion) |
| 깊이 옵션 | --quick, --deep, 없음 |
기본 (4개 에이전트) |
깊이별 에이전트 구성:
| 옵션 | 에이전트 수 | 구성 |
|---|---|---|
--quick |
3개 | tech-researcher + architecture-researcher + market-researcher |
| 기본 | 4개 | tech-researcher + architecture-researcher + market-researcher + 제약사항 (오케스트레이터 직접) |
--deep |
5개 | 기본 + ux-researcher |
Phase 1: BRIEF — 프로젝트 브리핑 수집
기존 자료 탐색 (CLAUDE.md, ANALYSIS-*.md, RESEARCH-*.md, package.json) 후, 없으면 사용자에게 브리핑 요청:
- 어떤 프로젝트인가? 2. 타겟 사용자? 3. 선호/제외 기술? 4. 특별 조사 항목?
Phase 2: DISPATCH — 팀원 배포
리서치 주제 결정 → 오케스트레이터 Context7 리서치(병렬, 설치돼 있으면) → 리서처 서브에이전트 병렬 배포. 상세 절차 및 프롬프트 템플릿은 phase-dispatch.md 참조.
Phase 3: COLLECT — 결과 수집
각 에이전트 완료 시 결과를 검증한다:
| 검증 항목 | 판정 |
|---|---|
| 출력 형식이 올바른가 | 형식 불량 → 핵심만 추출 |
| 출처가 명시되어 있는가 | 출처 없음 → 신뢰도 낮음 표기 |
| 프로젝트 목적과 관련 있는가 | 무관한 내용 → 제외 |
| 다른 에이전트 결과와 모순되는가 | 양쪽 근거 비교 후 판단 |
오케스트레이터의 Context7 결과도 통합한다(수행한 경우).
Phase 4: SYNTHESIZE — 종합 분석
크로스 분석:
- tech-researcher 추천 기술 ↔ architecture-researcher 패턴 호환성
- market-researcher 경쟁 분석 ↔ 차별화에 필요한 기술 요구사항
- (--deep 시) ux-researcher UX 방향 ↔ 기술 스택 UI 프레임워크 적합성
통합 권장안 도출 (1순위 조합 + 2순위 대안 + 주의사항).
Phase 5: REPORT — 보고서 생성
docs/research/RESEARCH-{주제}-{YYYY-MM-DD}.md 파일을 생성한다.
보고서 포맷은 report-template.md 참조.
사용자에게 요약 출력:
📊 팀 리서치 완료
══════════════════════════════════
프로젝트: {프로젝트명}
참여 에이전트: {N}명
보고서: {경로}
══════════════════════════════════
후속 워크플로우 연결
RESEARCH 파일은 후속 프로젝트 범위산정·스택 확정·초기화 단계에서 근거로 재사용된다. 조사(team-research)와 결정(범위·스택 확정)의 역할을 분리하는 것이 핵심이다.
What ships with it
2 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.
- 5d ago First seen · 125 lines · 83 tokens per session scan A af50722732bc
team-research is a skill published in the GitHub repository cubha/claude-workflow-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,428 once invoked, about $0.0004 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
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
add-cloud-flow
Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.