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/scannpx skills add eddmpython/dartlab --skill scangit 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 | $0.07584 |
| Opus 5 | $0.00000 | $0.03792 |
| Sonnet 5 | $0.00000 | $0.01517 |
| Haiku 4.5 | $0.00000 | $0.00758 |
Grade A, and why
scan 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 2d 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
엔진 역할
scan은 여러 기업을 한 번에 훑어 후보를 찾는 L1.5 횡단 엔진이다. L1 (company · gather) 위에서 전체 종목 universe 를 스캔해 ranking · filter · candidate evidence table 을 만든다. 단일 종목 심층 분석은 L2 (analysis · credit · macro · quant · industry) 의 책임. 질문의 단위가 "삼성전자를 분석해줘"이면 Company/analysis가 우선이고, "조건에 맞는 종목을 찾아줘", "전종목에서 상위 기업을 골라줘"이면 scan이 우선이다.
account와 ratio는 primitive다. 복합 투자 질문은 screen preset/spec 또는 quality, valuation, growth, profitability 같은 축으로 시작하고, 최종 판단은 후보별 analysis, credit, quant로 검증한다.
공개 호출 방식
import dartlab
# 전체 스캔 축 가이드
guide = dartlab.scan()
# 축 실행
quality = dartlab.scan("quality")
valuation = dartlab.scan("valuation")
cashflow = dartlab.scan("cashflow")
# primitive
revenue = dartlab.scan("account", "매출액")
roe = dartlab.scan("ratio", "roe")
inventory = dartlab.scan("note", "재고자산") # 주석 lineitem 횡단 (재고 세분·리스·법인세 등)
# 조건형 스크리닝
fields = dartlab.scan("fields", "roe")
value = dartlab.scan("screen", "value")
custom = dartlab.scan("screen", spec={"where": []})
# 파생 필드 조합 (spec.define): 순현금 = 현금 - 단기차입, 저부채 교차
safe = dartlab.scan("screen", spec={
"define": {"netCash": {"op": "sub",
"left": "finance.account.cash_and_cash_equivalents",
"right": "finance.account.shortterm_borrowings"}},
"where": [{"field": "@netCash", "op": ">", "value": 0},
{"field": "finance.ratio.debtRatio", "op": "<", "value": 30}],
"sort": {"field": "@netCash", "desc": True}})
# 시계열(연간 격자) + 상대(업종 횡단) 파생: 꾸준한 흑자 · 성장 · 업종내 상위
comp = dartlab.scan("screen", spec={
"define": {
"opMin3y": {"op": "min", "field": "finance.account.operating_profit", "years": 3},
"salesCagr3y": {"op": "cagr", "field": "finance.account.sales", "years": 3},
"roeIndPct": {"op": "percentile", "field": "finance.ratio.roe", "by": "industry"}},
"where": [{"field": "@opMin3y", "op": ">", "value": 0}, # 3년 연속 흑자
{"field": "@salesCagr3y", "op": ">", "value": 0.05}, # 매출 CAGR 5%+
{"field": "@roeIndPct", "op": ">", "value": 80}], # 업종내 ROE 상위 20%
"sort": {"field": "@roeIndPct", "desc": True}})
# 저장 스크린으로 등재된 실증본: dartlab.scan("screen", "resilientCompounders")
# 판정 근거 포함 결과: members, coverage, funnel, excluded, nearMiss, executionRef
explained = dartlab.scan("screen", "resilientCompounders", explain=True)
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.
- 2d ago First seen · 437 lines · 0 tokens per session scan A ff95dfbb3bb3
scan 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 7,584 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。.