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/eddmpython/dartlab/gathernpx skills add eddmpython/dartlab --skill gathergit clone --depth 1 https://github.com/eddmpython/dartlabWhat 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 | $0.00000 | $0.10590 |
| Opus 5 | $0.00000 | $0.05295 |
| Sonnet 5 | $0.00000 | $0.02118 |
| Haiku 4.5 | $0.00000 | $0.01059 |
Grade A, and why
gather 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 yesterday.
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 — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
엔진 역할
gather는 분석 엔진이 쓰는 외부/보조 데이터를 가져오는 L1 성격의 실행 엔진이다. 가격, 컨센서스, 수급, 뉴스, 배당/분할, 섹터, 내부자거래, 주요주주, 기관 보유, peer, 매크로 원자료를 다룬다.
gather는 원자료 수집과 snapshot 생성이 목적이다. 재무 해석은 analysis, 시장 매크로 해석은 macro, 후보 발굴은 scan이 담당한다.
공개 호출 방식
dartlab.gather 는 두 가지 형태로 쓴다 — 형태 A 가 권장 진입점, 형태 B 는 Gather 클래스 메서드를 직접 부를 때.
# 형태 A — 모듈 callable (권장). dartlab.gather 는 GatherEntry 인스턴스라 axis 디스패치.
import dartlab
dartlab.gather() # 가이드 DataFrame (전체 axis 목록)
dartlab.gather("price", "005930") # KR OHLCV
dartlab.gather("price", "AAPL") # US OHLCV (자동 판정)
dartlab.gather("flow", "005930") # 수급
dartlab.gather("flow", "005930", limit=30) # 최근 30거래일 수급
dartlab.gather("flow", "005930", start="2010-01-04", end="2010-01-08", sleepSec=1.0) # 과거 수급 저속 백필
dartlab.gather("flow", "005930", all=True, sleepSec=1.0) # 가능한 전체 수급 이력
dartlab.gather("flow", "005930", all=True, sleepSec=1.0, proxy="http://user:pass@host:port") # 사용자 프록시 경유
dartlab.gather("flow", targets=["005930", "000660"], limit=30, parallel=2, proxy="http://user:pass@host:port") # 종목 단위 병렬 수급
dartlab.gather("macro") # KR 거시지표 wide
dartlab.gather("macro", "FEDFUNDS") # FRED 자동 감지
dartlab.gather("news", "삼성전자") # Google News RSS
dartlab.gather("narrative", market="KR", days=30) # 뉴스 내러티브 archive
dartlab.gather("krxIndex", "close", market="KOSPI") # 시장군 지수
dartlab.gather("research", "005930") # 증권사 리서치 메타 인덱스
# 네이버 분류/목록 (로컬 개인용 — 재배포 금지). 계약은 아래 "naver* 축" 절.
dartlab.gather("naverTheme") # 전 테마 결합 (7일 로컬 저장·재호출 직독)
dartlab.gather("naverTheme", "list") # 테마 목록만 ("리튬"=해당 테마 · refresh=True=강제 재크롤)
dartlab.gather("naverIndustry", "반도체") # 네이버 업종 분류
dartlab.gather("naverEtf", "KODEX") # ETF 목록 (종목명 필터)
dartlab.gather("naverEtn") # ETN 목록
# 정기공시 due 는 Company.calendar — gather("calendar") 는 0.10 폐기
dartlab.Company("005930").calendar(horizonDays=30) # DART_API_KEY
c = dartlab.Company("005930")
c.gather("price") # 종목코드/market 자동 주입
# 형태 B — Gather 클래스 메서드 (dividends/majorShareholders 같은
# axis 미등록 메서드, snapshot=True 등 세밀한 옵션 필요할 때).
from dartlab.gather import getDefaultGather
g = getDefaultGather()
g.price("005930", market="KR")
g.price("005930", snapshot=True) # PriceSnapshot (현재가)
g.dividends("005930")
g.majorShareholders("005930")
g.collect("005930") # 전체 도메인 병렬 수집 → GatherSnapshot
What ships with it
1 file 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.
- yesterday First seen · 532 lines · 0 tokens per session scan A d8e5bb16354f
gather is a skill published in the GitHub repository eddmpython/dartlab (209 stars, last pushed 10d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 10,590 tokens. 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.
Other skills, from other repositories
build_workspace_app
This guide covers the full lifecycle of building, running, and serving a custom OpenBB Workspace application from an extension project scaffolded by openbb-cookiecutter. It assumes the project shell already exists (see the developextension skill for scaffolding instructions).
configure_mcp_server
This guide covers installation, configuration, authentication, tool discovery, prompt management, and client integration for openbb-mcp-server.
develop_extension
This is a complete guide for creating a new OpenBB Platform extension from scratch. Follow every phase in order. When the user says "build me an application that does X", use this guide to scaffold, implement, install, and verify the extension.
work_with_server
This guide explains how to call tools, interpret responses, discover capabilities, use prompts, and handle errors when interacting with an OpenBB MCP server.
fin-data-acquisition
根据REFINEDDESIGN.md中的变量定义，自动获取所需数据并生成可执行的回归分析脚本（Python/Stata）。.
alphasift
自动选股 Skill。Use when: 用户要按策略筛选 A 股、列出可用策略、运行双低/放量突破/均衡多因子/资金热度等选股，或保存运行并做 T+N 后验评估。通过 alphasift CLI 或 Python 接口输出候选股票列表。.