Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sophymarine/openregistrynpx agentmods add skills/sophymarine/openregistry/korea-opendartWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sophymarine/openregistry/korea-opendart)<a href="https://agentmods.dev/skills/sophymarine/openregistry/korea-opendart"><img src="https://agentmods.dev/badge/skills/sophymarine/openregistry/korea-opendart/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sophymarine/openregistry/korea-opendart"><img src="https://agentmods.dev/badge/skills/sophymarine/openregistry/korea-opendart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01015 |
| Opus 5 | $0.00000 | $0.00508 |
| Sonnet 5 | $0.00000 | $0.00203 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
South Korea — OPENDART (전자공시) Lookup 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 12d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
South Korea — OPENDART (전자공시) Lookup
Live, direct-to-government access to 금융감독원 전자공시시스템 OPENDART (Financial Supervisory Service — Electronic Disclosure System).
Single-country variant of the cross-border Cross-Border UBO Chain Walker. Use this skill when the user is explicitly focused on South Korea.
What you get
- Direct query to OPENDART (전자공시). Every tool call hits 금융감독원 전자공시시스템 OPENDART (Financial Supervisory Service — Electronic Disclosure System) at the moment you ask. No nightly scrape, no aggregator middle layer.
- Unmodified responses. Field names, status codes, and (where available) raw filing bytes are returned exactly as the registry's own system emits them.
- Native ID format support. DART corp_code (8-digit) or stock_code (6-digit, e.g.
005930for Samsung Electronics). - Sample entity: Samsung Electronics Co., Ltd. (삼성전자).
Available tools (jurisdiction = KR)
search_companies, get_company_profile, list_filings, get_financials, get_officers, get_shareholders, get_document_metadata, fetch_document
For every tool, pass jurisdiction: "KR" (case-insensitive).
Example prompts
Pull Samsung Electronics' latest quarterly disclosure with full financials
List all Hyundai Motor (005380) major shareholders disclosed in the last annual filing
Find LG Energy Solution's audit report from OpenDART
Workflow
Step 1 — Resolve the entity
search_companies({ jurisdiction: "KR", query: "<name or ID>" })
get_company_profile({ jurisdiction: "KR", company_id: "<id>" })
Step 2 — Pull the relevant register slice
Pick from the available tools list above. For UBO walks across borders, return to the Cross-Border UBO Chain Walker.
Quirks specific to South Korea
- OPENDART is the public-disclosure system for listed and large unlisted Korean firms — not all Korean companies appear; private SMEs are not in scope.
get_financialsreturns IFRS-formatted statements (KIFRS).fetch_documentreturns the original Korean-language XBRL / iXBRL filing.- Officers (임원) and major shareholders (주주) are filed quarterly/annually in mandatory disclosure forms.
- Stock codes (6-digit) and corp codes (8-digit) are distinct identifiers; use
get_company_profileto map between them.
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.
- 12d ago First seen · 73 lines · 0 tokens per session scan A bc3a3cac9ff3
South Korea — OPENDART (전자공시) Lookup is a skill published in the GitHub repository sophymarine/openregistry (17 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,015 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
qcc-risk-screen
A full risk-screening workflow for Chinese companies using Qichacha, a business-information service. It checks legal, enforcement, tax, bankruptcy, ownership, operating, and other company-risk records.
qcc-ownership-trace
A workflow for tracing a company's ownership, including its controlling person, direct shareholders, investments, beneficial owners, and registration changes.
get-market-quotes
Retrieve real-time equity, index, and ETF quotes with price, change, and sparkline history. Use when the user asks for current market prices, how a ticker is doing, or a quick market snapshot.
track-tariff-trends
Retrieve MFN applied tariff-rate timeseries for a reporting country — applied vs bound rates by year, plus the optional US effective tariff rate. Use when the user asks how a country's MFN tariffs have changed over time.
get-prediction-markets
Retrieve active prediction-market contracts (Polymarket) with live yes-price probabilities, volume, and close dates, filterable by category or keyword. Use when the user asks what the market odds are on a geopolitical, economic, or election outcome.
investor-materials
Use when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first meeting, or drafting the recurring monthly investor update. NOT the slide narrative (that is pitch-deck), NOT the projection spreadsheet (that…