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 instructions/gejyn14/kiwoom-plugin/claude-mdgit 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/instructions/gejyn14/kiwoom-plugin/claude-md)<a href="https://agentmods.dev/instructions/gejyn14/kiwoom-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/gejyn14/kiwoom-plugin/claude-md.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 | $0.02118 | $0.02118 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
kiwoom-plugin CLAUDE.md 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kiwoom-plugin
키움증권 REST API를 Claude Code에 연결하는 것 전부를 담은 저장소. 플러그인 두 개 + MCP 서버 본체.
구조
kiwoom-plugin/
├── .claude-plugin/marketplace.json 마켓플레이스 (플러그인 2개 등록)
├── plugins/
│ ├── kiwoom/ 조회 전용 플러그인
│ │ ├── .claude-plugin/plugin.json
│ │ ├── .mcp.json 서버를 uvx로 실행 (주문 없음)
│ │ └── skills/ stock-research, portfolio-review, pnl-report,
│ │ market-scan, condition-search, kiwoom-setup
│ └── kiwoom-trader/ 조회 + 주문 플러그인
│ ├── .mcp.json 서버를 --allow-orders로 실행
│ └── skills/ 위 6개 + place-order
├── server.json 공식 MCP 레지스트리 매니페스트
└── server/ MCP 서버 본체 (파이썬 패키지 kiwoom-mcp)
├── kiwoom_mcp/{cli,server,runner,policy}.py
├── tests/ 211개
├── pyproject.toml
├── Dockerfile / compose.yaml 헤드리스 컨테이너 (토큰 주입)
└── README.md
세 저장소의 관계
- kiwoom-cli — 키움 API 236종 CLI. 안전장치(주문 확인 게이트, dry-run, 멱등키, envelope)가 전부 여기 있다. 서버는 이것을 감쌀 뿐 다시 구현하지 않는다.
- kiwoom-plugin (이 저장소) — 플러그인 + 스킬 + 서버.
kiwoom-mcp— 서버를 담던 별도 저장소. 이 저장소로 흡수하고 삭제 중(로컬 삭제됨, GitHub는 수동 삭제 대기).
개발
cd server
pip install -e ".[dev]"
pytest tests/ -q # 211개
ruff check kiwoom_mcp/ tests/
서버는 kiwoom-cli를 의존성으로 쓴다 (PyPI의 kiwoom-cli). 도구 표면이 kiwoom-cli의 명령 트리에서 나오므로, kiwoom-cli가 바뀌면 여기 테스트가 먼저 깨진다.
플러그인 배선 (중요)
두 플러그인의 .mcp.json은 서버를 PyPI에서 실행한다:
uvx --from "kiwoom-mcp==0.1.1" kiwoom-mcp [--allow-orders]
- 정확한 버전에 고정한다 (
==0.1.1), 범위나 bare가 아니라. 진짜 제약은 "git 태그여야 한다"가 아니라 uvx 캐시 경로가 안정적이어야 한다는 것이다 — barekiwoom-mcp는 새 릴리스가 나올 때마다 경로가 바뀌고, macOS는 키체인 접근을 바이너리 단위로 승인하므로 그때마다 승인 창이 다시 뜬다. .mcp.json이 고정하는 버전은 반드시 PyPI에 게시된 버전이어야 한다. 서버를 올렸으면: 버전 범프 → 빌드 → PyPI 게시 → 두.mcp.json의==X.Y.Z를 갱신. 게시 전에 pin을 올리면 플러그인이 연결에 실패한다.- 게시 전 검증이나 저장소 직접 실행은 git 형태를 쓴다:
uvx --from "git+https://github.com/gejyn14/[email protected]#subdirectory=server" kiwoom-mcp(#subdirectory=server로 하위 디렉터리만 설치, uv가 지원함).
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.
- 4d ago First seen · 97 lines · 2,118 tokens per session scan A 3a84f9a8364f
kiwoom-plugin CLAUDE.md is an instructions file published in the GitHub repository gejyn14/kiwoom-plugin (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,118 tokens to every session, about $0.0106 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 instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.