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 johnfkoo951/cmdspace-plugins --skill research-pipelinegit clone --depth 1 https://github.com/johnfkoo951/cmdspace-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/johnfkoo951/cmdspace-plugins/research-pipeline)<a href="https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/research-pipeline"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/research-pipeline/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.
<a href="https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/research-pipeline"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/research-pipeline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00105 | $0.03480 |
| Opus 5.5 | $0.00042 | $0.01392 |
| Sonnet 5.5 | $0.00021 | $0.00696 |
| Haiku 4.5 | $0.00011 | $0.00348 |
Grade A, and why
research-pipeline 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 1mo 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research-to-Publication Pipeline
CMDS Process(Connect - Merge - Develop - Share) 기반 연구-출판 파이프라인 오케스트레이터입니다.
워크플로우 개요
Phase 1: Connect (자료 조사) → Phase 2: Merge (문헌 분석) → Phase 3: Develop (원고 집필) → Phase 4: Edit (편집) → Phase 5: Share (출판) → [Phase 6: Web (선택)]
Phase 0: 프로젝트 초기화
0-1. 사용자 옵션 확인
반드시 AskUserQuestion 도구를 사용하여 아래 질문들을 제시한다:
{
"questions": [
{
"header": "출력 유형",
"question": "어떤 형태의 출력물을 만들까요?",
"options": [
{"label": "학술 논문 (Recommended)", "description": "IMRaD 구조의 학술지 투고용 논문"},
{"label": "학회 발표", "description": "Conference paper + 발표 슬라이드 구조"},
{"label": "뉴스레터", "description": "더배러 스타일 에세이"},
{"label": "강의 자료", "description": "대학 강의용 교안"}
],
"multiSelect": false
},
{
"header": "언어",
"question": "어떤 언어로 작성할까요?",
"options": [
{"label": "한국어 (Recommended)", "description": "국내 학술지 투고용. 영문 초록 포함"},
{"label": "영어", "description": "국제 학술지/학회 투고용"},
{"label": "이중 언어", "description": "한국어 본문 + 영어 전체 번역본"}
],
"multiSelect": false
},
{
"header": "시작 Phase",
"question": "어디서부터 시작할까요?",
"options": [
{"label": "Phase 1부터 (Recommended)", "description": "자료 조사부터 전체 파이프라인 실행"},
{"label": "Phase 2부터", "description": "이미 논문 목록이 있어서 분석부터 시작"},
{"label": "Phase 3부터", "description": "문헌 리뷰 완료, 원고 작성부터"},
{"label": "기존 프로젝트 재개", "description": "_pipeline-state.md가 있는 프로젝트 이어하기"}
],
"multiSelect": false
},
{
"header": "웹 배포",
"question": "완료 후 웹페이지로 배포할까요?",
"options": [
{"label": "배포 안 함 (Recommended)", "description": "원고 파일만 생성"},
{"label": "웹 배포", "description": "연구 결과를 Academic Paper Showcase 웹페이지로 Vercel 배포"}
],
"multiSelect": false
}
]
}
0-2. 프로젝트 폴더 생성
- 위치:
00. Inbox/03. AI Agent/03-1. Claude Code (MBP)/YYYY-MM-DD-research-{slug}/ {slug}는 연구 주제에서 생성 (예:knowledge-sharing-ai)
What ships with it
3 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.
- 1mo ago First seen · 372 lines · 105 tokens per session scan A d27a7b190897
research-pipeline is a skill published in the GitHub repository johnfkoo951/cmdspace-plugins (7 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 3,480 once invoked, about $0.0004 per session on Opus 5.5. 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
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, list, or version-gated kanban views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
ariadne:workspace-instructions
Create or update workspace-level instruction files for code repositories or ordinary project folders, including AGENTS.md, CLAUDE.md, GEMINI.md, local override files, and Ariadne vault-link blocks. Use when a user wants to initialize, repair, or refresh workspace instructions, connect a workspace to a registered…
ariadne:global-discovery
Register existing Markdown knowledge vaults for machine-level discovery so cold agents can find long-term knowledge from any workspace. Use when checking, adding, updating, repairing, or removing global vault discovery.