portfolio-agent: Instructions file for Claude Code

CLAUDE.md

portfolio-agent CLAUDE.md is an instructions file for Claude Code from Daegyu519/portfolio-agent. It costs 2,187 tokens per session, scanned B, original, MIT.

A set of Claude Code instructions for a portfolio decision-support project. It defines how evidence, calculations, recommendations, notes, and secrets must be handled.

In plain words
What is it for?
Use it to guide work on portfolio analysis, source-backed recommendations, invalidation conditions, structured decision states, and project architecture.
Why use it?
It keeps investment decisions traceable and prevents the agent from inventing figures, trading through a read-only connection, or mixing different kinds of information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Daegyu519/portfolio-agent's own configuration. It tells Claude Code how to work on portfolio-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything portfolio-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Daegyu519/portfolio-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Daegyu519/portfolio-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Daegyu519/portfolio-agent

Made for: Claude Code.

Wrote 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.

agentmods badge for portfolio-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daegyu519/portfolio-agent/claude-md/github.svg)](https://agentmods.dev/instructions/daegyu519/portfolio-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/daegyu519/portfolio-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/daegyu519/portfolio-agent/claude-md/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.

agentmods 80×15 button for portfolio-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daegyu519/portfolio-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/daegyu519/portfolio-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,187 This file is loaded in full into every session.
When invoked 2,187 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02187 $0.02187
Opus 5 $0.01094 $0.01094
Sonnet 5 $0.00437 $0.00437
Haiku 4.5 $0.00219 $0.00219

Measured 8d ago against content hash b64459d891fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

portfolio-agent CLAUDE.md scanned grade B with 1 finding 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 8d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

├── .mcp.json # 프로젝트 스코프 MCP 서버 (secrets는 ${ENV})
CLAUDE.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — 포트폴리오 의사결정 에이전트

개인용 투자 의사결정 지원 에이전트. 내 보유 포트폴리오를 읽고 근거와 무효화 조건이 붙은 판단(보유/축소/추가)을 내린다. 뉴스 요약기가 아니라 의사결정 시스템이다.

이 파일은 실행 체크리스트가 아니라 행동 계약이다. 작업 목록은 TASKS.md에 있다.


최우선 규율 (절대 위반 금지)

  • IMPORTANT: 토스 API는 읽기 전용이다. 주문·거래·정정·취소 엔드포인트는 코드에 존재해서도 안 된다. sources 클라이언트에 매매 함수를 만들지 마라.
  • IMPORTANT: 수치는 LLM이 생성하지 않는다. 가격은 토스, 재무·공시는 DART/EDGAR 원문에서 온다. 계산(집중도·상관·리스크·리밸런싱)은 engines/의 코드가 한다. LLM은 그라운딩된 텍스트 위에서 요약·종합·논지 판정만.
  • IMPORTANT: 모든 판단에는 (a) 근거 원문 링크와 (b) 무효화 조건("이 판단이 뒤집히려면 무엇이 참이어야 하는가")이 반드시 붙는다. 이 두 필드가 없는 추천은 불완전한 출력으로 간주하고 반려하라.
  • 사실 하나당 소스 오브 트루스 하나. 구조화된 논지 상태는 MySQL, 서술·추론 원문은 마크다운 vault. 같은 사실을 두 곳에 쓰지 마라(중복 = drift).
  • 벡터 검색은 수치 경로에 절대 넣지 마라. 벡터는 "주제적으로 비슷한 과거 노트/사례" 회수 전용이다.
  • 관찰 트랙(기술적 분석·뉴스 감성)은 Obsidian 병렬 전용이다. 코드 지표·YOLO 차트 패턴·FinBERT 뉴스 감성 — 전부 확률적/관찰 신호이고, 의사결정 엔진·그라운딩 번들(E#)·게이트·논지 상태머신에 절대 들어가지 않는다 (벡터와 같은 격리 범주). engines/technical.py·engines/patterns.py·engines/sentiment.py·knowledge/charts.py·sentiment_export.py. 강한 신호는 다이제스트 '판단 필요'로 표면화해 사람이 /review 하는 트리거로만 쓴다. 상세: docs/technical.md·docs/sentiment.md.
  • 시크릿은 코드·커밋에 넣지 마라. 전부 .env. 노출 시 즉시 재발급.

작업 방식

  • 확실하지 않으면 진행하지 말고 물어라. 두 접근이 갈리면 둘 다 설명하고 내가 고르게 하라.
  • 요청 범위 밖 리팩터링 금지. 최소 변경.
  • 논리 단위별로 커밋을 분리하라. 한 번에 몰아 커밋하지 마라.
  • 코드 변경 후 관련 테스트를 돌려라.
  • 기능은 한 번에 하나. end-to-end 검증 후에만 완료로 표시.

스택

  • 언어: Python 3.11+
  • 정형 저장소: MySQL (Repository 추상화로 감싼다 — 엔진 교체 가능하게)
  • 비정형 지식: 마크다운 vault (vault/), Obsidian은 같은 폴더를 보는 human 뷰어일 뿐
  • 데이터 소스(읽기전용): 토스증권 오픈 API, OpenDART, SEC EDGAR, (보조) 뉴스 API
  • 에이전트: Claude Code (오케스트레이터) + 커스텀 MCP 서버(stdio)
  • 벡터(지연): 코퍼스 쌓이면 sqlite-vec/numpy 파생 인덱스

아키텍처 개요 (계층)

Claude Code (오케스트레이터)
  └─ MCP 서버 (stdio, 읽기전용)
       ├─ sources 클라이언트 : 토스·DART·EDGAR 읽기
       ├─ engines           : quant(계산) · thesis(논지 상태머신)
       └─ synthesis         : 근거+무효화 조건 판단 (LLM)
  └─ 저장 : MySQL(정형 SoT) · 마크다운 vault(Obsidian)

디렉토리 구조

portfolio-agent/
├── CLAUDE.md
├── TASKS.md                  # 작업 백로그 (이 파일 아님)
├── .env.example              # 키 목록만. 실제 .env는 gitignore
├── .mcp.json                 # 프로젝트 스코프 MCP 서버 (secrets는 ${ENV})
├── config/settings.py        # 목표 비중(core-satellite), 임계치, 경로
├── src/
│   ├── storage/              # Repository 인터페이스 + mysql_repo + schema.sql
│   ├── knowledge/            # vault(.md) read/write
│   ├── sources/              # toss_client(읽기전용)·dart_client·edgar_client
│   ├── engines/              # quant.py(계산, LLM 없음)·thesis.py(상태머신)
│   ├── synthesis/            # prompts.py·decision.py (근거+무효화 강제)
│   ├── mcp/                  # portfolio_server.py·sources_server.py
│   └── cli/                  # brief.py (온디맨드 심층 판단 + 백그라운드 감시)
├── vault/                    # theses/ · reflections/ · engineering-journal/
└── tests/

Read the full file on GitHub · 123 lines

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. 8d ago First seen · 123 lines · 2,187 tokens per session scan B b64459d891fe

Subscribe to this mod's changes

portfolio-agent CLAUDE.md is an instructions file published in the GitHub repository Daegyu519/portfolio-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,187 tokens to every session, about $0.0109 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens