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/gejyn14/kiwoom-plugin/kiwoom-setupnpx skills add gejyn14/kiwoom-plugin --skill kiwoom-setupgit clone --depth 1 https://github.com/gejyn14/kiwoom-pluginWrote 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/gejyn14/kiwoom-plugin/kiwoom-setup)<a href="https://agentmods.dev/skills/gejyn14/kiwoom-plugin/kiwoom-setup"><img src="https://agentmods.dev/badge/skills/gejyn14/kiwoom-plugin/kiwoom-setup.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01310 |
| Opus 5 | $0.00041 | $0.00655 |
| Sonnet 5 | $0.00016 | $0.00262 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
kiwoom-setup 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
설정 진단
먼저 상태를 본다
kiwoom_run(["auth","status"])
돌아오는 것: profile, domain(실제 접속 도메인), configured,
appkey_source, has_token, token_source, token_storage.
domain은 설정 파일 값이 아니라 실제로 접속하는 도메인이다. KIWOOM_DOMAIN
환경변수가 모든 프로필을 덮으므로, 설정에 mock이라 적혀 있어도 실거래로 갈 수 있다.
오류별 대응
| error.code | 뜻 | 대응 |
|---|---|---|
AUTH_REQUIRED |
토큰 없음 | 아래 "토큰 발급" |
TOKEN_EXPIRED |
토큰 만료 (upstream 8005) | 재발급 |
INVALID_CREDENTIALS |
appkey/secretkey를 키움이 거부 (upstream 8001) | 키가 폐기·만료된 것이다. 개발자센터에서 새로 발급받아 kiwoom config setup |
NOT_CONFIGURED |
appkey 없음 또는 config.toml 손상 | kiwoom config setup (터미널에서) |
KEYCHAIN_UNAVAILABLE |
OS 키체인 접근 불가 | 아래 "키체인 없는 환경" |
만료 토큰이 TOKEN_EXPIRED로 안 올 수 있다. 일반 조회에서 토큰이 만료되면
실제 응답은 code: "UPSTREAM_ERROR", upstream_code: 3이고 구체적인 번호는
메시지 안에만 들어 있다 — 인증에 실패했습니다[8005:Token이 유효하지 않습니다].
error.code만 보고 "서버 오류"라고 답하지 말고 메시지의 대괄호 번호를 읽는다.
토큰 발급
MCP 도구로는 auth login을 실행할 수 없다 — 서버가 차단한다
(MCP_ADMIN_BLOCKED). 자격증명 수명주기는 서버가 소유하며, 모델이 토큰을
발급·폐기하게 두지 않는다. 사용자에게 터미널에서 직접 실행하도록 안내한다:
kiwoom auth login
appkey/secretkey가 환경변수로 주어져 있으면 MCP 서버가 첫 호출에서 토큰을 발급하고 만료되면 스스로 재발급한다 (기동 중에는 발급하지 않는다 — 키체인 승인 창이 뜨면 헤드리스 서버가 답할 수 없어 멈춘다). 이 경우 사용자가 할 일은 없다.
키체인 없는 환경 (컨테이너, CI, 샌드박스)
어느 쪽이 무엇을 읽는지 구분해야 한다.
kiwoom-cli 2.14.0이 읽는 환경변수는 넷뿐이다:
KIWOOM_ACCOUNT, KIWOOM_DOMAIN, KIWOOM_PROFILE, KIWOOM_TOKEN.
appkey/secretkey는 kiwoom-cli가 읽지 않는다 — 그래서 셸에 KIWOOM_APPKEY를
export해 두어도 kiwoom auth login은 "appkey/secretkey not set"으로 실패한다.
appkey/secretkey 환경변수를 쓰는 것은 MCP 서버다. 서버가 이 값으로 직접
토큰을 발급해 KIWOOM_TOKEN에 심고, 그다음부터는 kiwoom-cli가 그 토큰을 쓴다.
# MCP 서버가 읽는다 (서버가 토큰을 발급해 준다)
export KIWOOM_APPKEY_FILE=/run/secrets/kiwoom_appkey # 또는 KIWOOM_APPKEY
export KIWOOM_SECRETKEY_FILE=/run/secrets/kiwoom_secretkey # 또는 KIWOOM_SECRETKEY
# kiwoom-cli가 읽는다
export KIWOOM_DOMAIN=mock
서버 없이 kiwoom-cli만 쓰거나 자격증명을 컨테이너에 넣고 싶지 않다면, 키체인이 있는 호스트에서 발급한 토큰을 직접 주입한다 — 이쪽은 kiwoom-cli가 바로 이해한다:
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.
- 5d ago First seen · 98 lines · 81 tokens per session scan A 1402cc2f1894
kiwoom-setup is a skill published in the GitHub repository gejyn14/kiwoom-plugin (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,310 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.