edgar

A provider for reading United States company filings and financial data from SEC EDGAR, the US Securities and Exchange Commission's public disclosure system. It supports company lookup by stock ticker or CIK and can access filings, financial statements, ratios, and some economic data.

In plain words
What is it for?
Use it to read 10-K annual reports, 10-Q quarterly reports, 8-K current reports, S-1 registration statements, XBRL financial data, live filings, and FRED economic indicators. FRED is the US Federal Reserve's database of economic time series.
Why use it?
It gives one company interface for US disclosures and finances, so users do not need separate code paths for each EDGAR data source.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/eddmpython/dartlab/edgar
Any agent
npx skills add eddmpython/dartlab --skill edgar
Clone the repo
git clone --depth 1 https://github.com/eddmpython/dartlab

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03756
Opus 5 $0.00000 $0.01878
Sonnet 5 $0.00000 $0.00751
Haiku 4.5 $0.00000 $0.00376

Measured 2d ago against content hash dc943c5ac693, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

edgar 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.

src/dartlab/skills/specs/engines/edgar/SKILL.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

엔진 역할

edgar 는 별도 사용자 capability 가 아니라 — dartlab.Company facade 가 ticker / CIK 를 받았을 때 자동 활성화되는 provider 다. DartCompany ↔ EdgarCompany 는 public 메서드 양쪽 동등 SSOTpanel / select / trace / disclosure / liveFilings / readFiling / analysis / credit / quant 모두 같은 시그니처. 시장만 다름. (industry 는 KR 가치사슬 지도 전용 — US 동등 데이터 부재로 EXEMPT, 아래 EXEMPT 섹션 참조.)

EDGAR 재무는 두 소스로 분기한다 (DART 와 같은 메커니즘):

  • 소문자 native (c.panel("is"/"bs"/"cf"/"cis"/"sce"/"ratios")) — panel 단일 artifact 의 row payload 에 보존된 XBRL native 셀을 read-time 분해 (presentation role 앵커링). DART c.panel("is") 의 panel 셀 경로 미러. compare(codes, topic="is") finance 비교도 이 native 셀을 쓴다 (account=snakeId, USD 실값).
  • 대문자 companyfacts (c.panel("IS"/"BS"/"CF"/"RATIOS")) — SEC companyfacts 벌크(edgar/finance) 위임. panel 과 무관, 항상 가용.

live filings 는 SEC EDGAR API. 거시는 FRED (gather("macro", "FEDFUNDS")).

⚠ native(소문자) 경로는 panel artifact 에 native payload 가 있어야 동작한다. 2026-06-06 이전 빌드된 panel 은 payload 가 없어 c.panel("is")·compare(topic=finance) 가 빈 결과 — EDGAR_FULL_REBUILD=1 (originalSync.yml dispatch) 전수 재빌드로 backfill. 대문자 companyfacts 경로는 영향 없음.

공개 호출 방식

import dartlab

# 1. Company facade — ticker 또는 CIK 인식 자동 EDGAR 라우팅
c = dartlab.Company("AAPL")
print(c.market)       # "US"
print(c.panel.shape)  # 항목 x 기간 격자 크기 (DART 와 동일 인터페이스)

# 2. DART 와 동등 인터페이스 (XBRL 자동 정규화)
bs = c.panel("BS", freq="Q")
is_y = c.panel("IS", freq="Y")
ratios = c.panel("ratios")

# 3. 공시
filings = c.filings()                  # 공시 문서 목록 + 링크

# 3.5. 공시 수평화 보드 — engines.panel 의 US 미러 (DART c.panel 과 동일 표면)
c.panel                                    # item × 기간 wide (pl.DataFrame) — 잡는 순간 보드
c.panel("Risk")                            # 섹션 행 검색 (10-K item 본문)
c.panel("is", freq="year")                 # native 재무 (소문자 — panel payload 셀, role 앵커)
c.panel("ratios", freq="year")             # native 재무비율 (core 공식, panel 자급)
c.panel("IS")                              # 대문자 — companyfacts 위임 (내부 finance, 항상 가용)
c.panel.search("supply chain")             # 본문 전체검색

# 3.6. 회사 간 재무 비교 — 탑레벨 verb (DART 와 동일 호출계약, native 셀 기반)
import dartlab
dartlab.compare(["AAPL", "MSFT"], topic="is", freq="year")   # account(snakeId)×회사, USD 실값

# 3.7. 전종목 횡단 scan — market="us" (companyfacts 기반 재무축)
dartlab.scan("profitability", market="us")                   # opMargin/netMargin/roe/roa + grade
dartlab.scan("account", "sales", market="us")                # 단일 계정 전종목 시계열

# 4. 보조 엔진도 동일 (US 자동)
analysis = c.analysis("financial", "수익성")
credit = c.credit()
quant = c.quant("모멘텀")

# 5. 시장 데이터 (gather ticker 자동 판정)
price = dartlab.gather("price", "AAPL")
macro = dartlab.gather("macro", "FEDFUNDS")
news = dartlab.gather("news", "Apple", market="US")

# 6. 한글 별칭 자동 해결 — 영문 alias resolveEnglishAlias
result = dartlab.searchName("인텔")        # → Intel (EDGAR 자동 재검색)

# 7. EDGAR 직접 client (저수준)
from dartlab import OpenEdgar
client = OpenEdgar()
filings = client.filings("AAPL", form="10-K", limit=5)

Read the full file on GitHub · 261 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 261 lines · 0 tokens per session scan A dc943c5ac693

Subscribe to this mod's changes

edgar 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 3,756 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.

Related

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).

OpenBB-finance/OpenBB · 57 tokens

configure_mcp_server

This guide covers installation, configuration, authentication, tool discovery, prompt management, and client integration for openbb-mcp-server.

OpenBB-finance/OpenBB · 31 tokens

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.

OpenBB-finance/OpenBB · 53 tokens

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.

OpenBB-finance/OpenBB · 33 tokens

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)。.

csmar432/finai-research · 36 tokens

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。.

ZhuLinsen/alphasift · 76 tokens