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/mappersnpx skills add eddmpython/dartlab --skill mappersgit 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 | $0.03679 |
| Opus 5 | $0.00000 | $0.01840 |
| Sonnet 5 | $0.00000 | $0.00736 |
| Haiku 4.5 | $0.00000 | $0.00368 |
Grade A, and why
mappers 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
엔진 역할
mappers 는 사용자 capability 가 아니라 내부 모듈 이다. DART 사업보고서·재무제표·주석의 한글 계정명을 dartlab 공통 snake_id 로 정규화한다. EDGAR 측은 SEC GAAP 태그 → 같은 snake_id (양쪽 SSOT 동등).
AI 가 직접 쓸 자리는 RunPython 안의 prelude 헬퍼 — normalizeColumn(topic, hint), columnsFor(topic), availableTopics(). 매핑 자체 편집은 운영자 절차 (src/dartlab/mappers/{topic}.json 직접 수정).
공개 호출 방식
# RunPython 안에서 — prelude 자동 노출
import dartlab
c = dartlab.Company("005930")
bs = c.panel("BS", freq="Q")
# 한글 → snake_id 정규화 (추측 금지)
col = normalizeColumn("BS", "총자산") # → "total_assets"
col2 = normalizeColumn("IS", "영업") # → "operating_profit"
# 가능 컬럼 목록 (snake_id · label · aliases)
cols = columnsFor("BS")
print(cols)
# 가능 topic
print(availableTopics()) # BS / IS / CF / CIS / SCE
강행 호출 룰 (agent 답변 품질 회귀 차단)
mappers 는 내부 정규화 모듈 — Company.panel / scan 결과 안에서 자동 적용. 다음 3 룰 강행:
- mappers 단독 EngineCall 금지 —
EngineCall(apiRef="mappers")호출 없음. Company.panel / scan 결과의snake_id컬럼은 이미 정규화 완료. - snake_id 임의 추측 금지 —
normalizeColumn(topic, hint)또는columnsFor(topic)RunPython 안에서 호출해 정확 매칭 후 사용. "total_equity" 같은 추측 키로 dict 접근 시 KeyError (P5 RunPython 회귀 사례). -표준계정코드 미사용-|...fallback 데이터는 표준화 후보로 표기 — Company.panel 결과 dict 의 nonstd_ 컬럼은 매핑 미완. 답변 본문에 "표준화 미완 N 건" 명시 + 임의 합산 금지.
호출 동작
normalizeColumn(topic, hint) — topic 안에서 hint 와 매칭되는 표준 snake_id 반환. 매칭 실패 시 None (또는 ValueError, 구현 따라). 한글 풀네임 · 부분 키워드 · snake_id 자기 자신 모두 받음.
columnsFor(topic) — 해당 topic 의 모든 표준 컬럼 list. 각 항목은 snake_id · label (한글) · aliases (한글/영문 변형) · category · type.
매핑 데이터는 src/dartlab/mappers/{topic}.json 의 _metadata.description + key:value (한글 → 영문 canonical) + category/type 분류.
6 매퍼 (topic 별)
| topic | 파일 | 책임 |
|---|---|---|
| BS | bs.json |
재무상태표 — 자산·부채·자본 계정 |
| IS | is.json |
손익계산서 — 매출·비용·이익 계정 |
| CF | cf.json |
현금흐름표 — 영업·투자·재무 활동 |
| CIS | cis.json |
포괄손익계산서 — OCI 항목 |
| SCE | sce.json |
자본변동표 — 자본 구성 변동 |
| ratios | ratios.json |
재무비율 — ROE · 부채비율 등 파생 |
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 · 259 lines · 0 tokens per session scan A 575e1d416f1f
mappers 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 3,679 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。.