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/dashboardnpx skills add eddmpython/dartlab --skill dashboardgit 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 | $0.02117 |
| Opus 5 | $0.00000 | $0.01059 |
| Sonnet 5 | $0.00000 | $0.00423 |
| Haiku 4.5 | $0.00000 | $0.00212 |
Grade A, and why
dashboard 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
엔진 역할
Dashboard 는 프론트엔드 SvelteKit 페이지 다. python API 가 아니다 — 회사 종합 스냅샷을 한 화면에 보여주는 landing 의 /company/[code] 라우트가 본체. python 측에서 실행할 일은 Company.view(port=8400) 으로 브라우저 뷰어를 켜거나, 빌드 파이프라인을 운영자 절차로 돌리는 것.
5-tier 데이터 구조:
| tier | 내용 | 빌드 스크립트 |
|---|---|---|
| finance | BS · IS · CF · 비율 | buildCompanyTier1.py |
| ratios | 재무비율 + 등급 (A-F) | buildCompanyTier2.py |
| grades | radar 5 축 (1-5 스케일) + Altman Z + Beneish M | buildCompanyTier3.py |
| ecosystem | 공급망 links + HHI + Top-N | buildCompanyTier4.py |
| narrative | 한국어 인과 문장 (story 블록) | buildCompanyTier5.py |
클라이언트는 assembleCompany.ts 가 위 5 tier JSON 을 런타임에 합성해 페이지를 그린다.
공개 호출 방식
import dartlab
# dashboard 는 python API 가 아니다. 공개 호출 계약도 아니다.
# 같은 데이터를 계약 호출로 직접 얻는다.
c = dartlab.Company("005930")
c.panel("IS")
c.analysis("financial", "종합평가")
# landing 빌드 (회사 페이지 SSR 포함)
cd landing
npm run build
# 회사 tier 데이터 갱신 (운영자 절차)
uv run python -X utf8 scripts/build/buildCompanyTier1.py 005930
강행 호출 룰 (agent 답변 품질 회귀 차단)
dashboard 는 프론트엔드 정적 페이지 라 ask LLM 의 EngineCall 대상이 아님. 다음 3 룰 강행:
- "회사 페이지" / "대시보드" 질문에 EngineCall 시도 금지 —
EngineCall(apiRef="dashboard")같은 호출 없음. 답변은 URL 안내 (landing/static/company/{code}/index.html또는Company.view()) 또는 동일 데이터의 원천 EngineCall (Company.panel/Company.analysis) 로 우회. - dashboard 안 5 tier 데이터 (finance · ratios · grades · ecosystem · narrative) 인용 시 원천 ref 표기 — dashboard JSON 자체가 아니라 그 데이터가 유래한
Company.panel/Company.analysis결과의[tableRef:...]/[valueRef:...]inline 표기. - 빌드 미수행 종목은 "데이터 부재" 명시 — 빈 블록 페이지를 정상 응답으로 답변 금지.
호출 동작
Company.view(port=8400) — 로컬 SvelteKit dev 서버를 띄우고 기본 브라우저로 /company/{code} 를 연다. 빌드 산출 JSON 이 없으면 페이지가 빈 블록으로 렌더된다 (해당 tier 빌드 먼저 실행 필요).
빌드 파이프라인은 종목별로 5 tier JSON 을 landing/static/company/{code}/ 에 떨어뜨린다. CI matrix 로 종목 분산 (전 상장사 단일 머신 빌드 시 OOM).
python 직접 데이터 조회는 본 skill 이 아니라 engines.company (c.panel("BS") 등) 또는 engines.analysis (c.analysis(...)) 를 통한다.
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.
- 2d ago First seen · 173 lines · 0 tokens per session scan A cc0eb8d6ee63
dashboard 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 2,117 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。.