auto_trader AGENTS.md

auto_trader AGENTS.md is an instructions file for Codex, OpenCode from mgh3326/auto_trader. It costs 1,936 tokens per session, scanned A, original, MIT.

Entry instructions for an automated trading repository, covering its architecture, safe operating rules, and required project guidance.

In plain words
What is it for?
They are for entering the repository safely, finding its main instructions, and understanding limits around trading execution, model use, code changes, and financial records.
Why use it?
They tell an outside coding agent which rules to follow before changing trading code, including branch, worktree, broker, and ledger restrictions.

Instructions file for CodexOpenCode

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 instructions/mgh3326/auto_trader/agents-md
Clone the repo
git clone --depth 1 https://github.com/mgh3326/auto_trader

Made for: Codex, OpenCode.

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 auto_trader AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mgh3326/auto_trader/agents-md.svg)](https://agentmods.dev/instructions/mgh3326/auto_trader/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mgh3326/auto_trader/agents-md"><img src="https://agentmods.dev/badge/instructions/mgh3326/auto_trader/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,936 This file is loaded in full into every session.
When invoked 1,936 The same file — it is already loaded in full.
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 $0.01936 $0.01936
Opus 5 $0.00968 $0.00968
Sonnet 5 $0.00387 $0.00387
Haiku 4.5 $0.00194 $0.00194

Measured 3d ago against content hash eb33cde60a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto_trader AGENTS.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 3d 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.

AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — 외부 에이전트(Codex 등) 진입점

이 파일은 얇은 포인터다. 정본은 CLAUDE.md. 작업을 시작하기 전에 리포지토리 루트의 CLAUDE.md전부 읽어라. 아키텍처, 명령어, 표면별 계약(레저/브로커/MCP), 런북 맵은 모두 거기에 있고, 이 파일과 충돌하면 CLAUDE.md가 이긴다. 아래 하드룰은 CLAUDE.md에서 추린 요약이며, CLAUDE.md를 읽지 못한 경우에도 절대 위반하면 안 되는 최소 집합이다.

하드룰 — 절대 위반 금지

  1. 런타임 LLM 경계 (ROB-501): app/** 런타임 코드에 in-process LLM provider (Gemini/OpenAI/Grok 등) import·인스턴스화 금지. LLM 판단은 out-of-process MCP consumer 몫. 정적 가드 테스트(tests/services/action_report/snapshot_backed/test_no_internal_llm_imports.py)가 이를 스캔한다.
  2. 브랜치 보호: main·production 직접 push 금지. 모든 코드 변경은 feature branch + PR.
  3. Worktree 규칙: canonical repo /Users/mgh3326/work/auto_trader는 항상 main 체크아웃 고정. 코드 변경은 /Users/mgh3326/work/auto_trader.<issue-id> worktree에서 수행. 머지된 브랜치 위에 계속 커밋 금지 — follow-up은 최신 origin/main 기준 새 브랜치로 시작.
  4. 브로커 실행 표면은 전부 default-disabled: demo/mock/live 실행 경로는 env 게이트 (예: BINANCE_SPOT_DEMO_ENABLED, KIWOOM_MOCK_ENABLED, TOSS_API_ENABLED) + per-call confirm=True 이중 게이트 뒤에 있다. 게이트 완화, 호스트 allowlist 확장, fail-closed→fail-open 전환, 하드 인바리언트 상수(레버리지 1x, notional cap, 동시 포지션 상한 등) 변경 금지. 이런 변경이 필요해 보이면 멈추고 운영자에게 보고하라.
  5. 레저 쓰기는 서비스 레이어 경유만: alpaca_paper_order_ledger, binance_demo_order_ledger, kis_live_order_ledger, live_order_ledger, toss_live_order_ledger 등 주문 레저에 직접 SQL INSERT/UPDATE/DELETE 금지. fill 기록은 evidence-first — 브로커 증거 없이 filled 마킹 금지.
  6. 스케줄러 등록 금지: 신규 TaskIQ/cron/Prefect 스케줄 연결은 명시 승인 없이 금지. 기본은 scheduleless 출고(CLI/수동 lever만).
  7. kis_mock 주문은 귀속 없이 나가지 않는다: place_order(is_mock=True) / account_mode="kis_mock"strategy 필수. 브로커 전송 이전에 review.kis_mock_signal_ledger 에 신호 행이 커밋돼야 하고, 실패하면 주문을 보내지 않는다 (error_code: attribution_required / signal_record_unavailable). 이 게이트를 우회·완화하거나 placeholder strategy 를 만들어 넣지 마라 — 귀속 불가는 값이 아니라 에러다. 귀속을 못 정하겠으면 멈추고 운영자에게 보고하라.
  8. 심볼 형식: DB 기준은 . 구분(BRK.B). 변환은 app/core/symbol.py (to_kis_symbol/to_yahoo_symbol/to_db_symbol)만 사용하고 직접 문자열 치환 금지.
  9. 검증·보고 규율: 완료 주장 전 관련 테스트를 실제 실행하고 결과 원문을 보고하라. 실패·스킵을 성공으로 보고 금지. push 완료 주장은 git ls-remote로 대조 가능해야 한다.
  10. Secrets: API 키·토큰 repo 커밋 금지. 로그·보고에 secret 값 출력 금지 (missing env는 key 이름만 보고).
  11. Telegram 승인 콜백 durable inbox (W5): 게이트 3종 (ORDER_PROPOSALS_TELEGRAM_CALLBACK_DURABLE_ENABLED / ..._WORKER_ENABLED / ..._RECOVERY_SCHEDULE_ENABLED) 전부 default false 유지. 콜백 코어의 게이트 (published-binding preflight, 단일소비 nonce, commit lease, target lock, approval hash) 우회·이동 금지. 코어 진입 후의 generic internal_error 를 재시도로 바꾸지 마라 — 브로커 미전송 증거가 아니라서 재주문이 된다 (docs/runbooks/telegram-callback-durable-inbox.md §5). terminal 스크럽 DB CHECK 완화 금지. W5 TaskIQ envelope/result boundary는 job의 canonical UUID 하나 또는 빈 recovery envelope만 허용하며, incoming retry/private labels와 label metadata를 폐기하고 SmartRetry 권한을 주지 않는다. raw args/kwargs/ labels/results/exception strings를 확장하거나 로그·Sentry·결과에 남기지 마라. callback_query.from은 exact built-in dict, from.id는 required exact bounded int, present update_id는 매번 exact bounded int여야 하며 coercion은 금지한다. terminal 11-field scrub과 마지막 update_identity_digest를 완화하지 마라.
  12. 매수 게이트 A/B shadow (ROB-1301): variant B는 순수 기록이다. 라이브 게이트 문언·주문·워치·제안 승격 금지. 채점 전 중간값으로 정책 변경 금지. 스케줄러/자동화 트리거로 연결하지 마라. Q6 epoch의 collection_armed_at/고정 28일 경계/policy projection hash는 변경 금지이며, first_valid_record_at으로 시작점을 옮기지 마라. 0건도 INSUFFICIENT_SAMPLE / NO_FIRING으로 종료하고 readiness는 창 종료와 전 사건 성숙의 AND다. caller wiring은 epoch marker serving 뒤 별도 PR에서만 한다.
  13. screener pick log: buy_candidate_fanout 안에서 쓰지 마라 (no-write 계약). 관측 레코더는 바깥, SCREENER_PICK_LOG_ENABLED 기본 false, fail-open, 스케줄러 금지. 가격은 exact decimal 문자열.
  14. NHPLUG 모의 read-only (Stage 1): 데이터는 moapi.nhplug.com:8443만, /n2/acctinfoacct_type=03 allowlist만 사용하며, build 후 scheme·host·port와 act_no를 send 직전에 재검증한다. 동일 계좌번호의 상충 type 응답은 거부한다. 운영 OAuth 호스트는 nhplug/auth.py의 token/revoke 2 path 예외뿐이다. NHPLUG_MOCK_ENABLED default false 유지, vendor SDK·NHPLUG_BASE_URL/NHPLUG_AUTH_URL·주문 endpoint/TR 추가 금지. 주문 메서드/MCP/레저/reconcile/스케줄러는 Stage 1 범위 밖이다.

Read the full file on GitHub · 93 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. 3d ago First seen · 93 lines · 1,936 tokens per session scan A eb33cde60a5b

Subscribe to this mod's changes

auto_trader AGENTS.md is an instructions file published in the GitHub repository mgh3326/auto_trader (5 stars, last pushed 3d ago), licensed MIT. It adds 1,936 tokens to every session, about $0.0097 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.

Related

Other instructions, from other repositories

robosystems CLAUDE.md

Instructions for RoboFinSystems/robosystems, covering claude.md - robosystems development guide, critical rules, api endpoints (local testing), health check and extensions operation write (close a period).

RoboFinSystems/robosystems · 6,079 tokens

loopback-training-server CLAUDE.md

Instructions for aderaaij/loopback-training-server, covering training api, tech stack, project structure, frontend (web dashboard) and development.

aderaaij/loopback-training-server · 8,389 tokens

bitcoin-risk-brief AGENTS.md

AGENTS.md instructions for akarazhev/bitcoin-risk-brief, covering repository guidelines, project structure & module organization, build, test, and development commands, required project context and superpowers workflow.

akarazhev/bitcoin-risk-brief · 1,416 tokens

wiii AGENTS.md

AGENTS.md instructions for meiiie/wiii, covering agents.md, repository context, wiii + neko brand memory, operating rules and product entry and release truth.

meiiie/wiii · 2,365 tokens

wiii CLAUDE.md

Claude Code instructions for meiiie/wiii, a project described as: Wiii is an open-source durable AI workbench for conversations, local and cloud agents, files, tools, memory, artifacts, and permission-aware integrations.

meiiie/wiii · 316 tokens

fullstack-clean-architecture AGENTS.md

Instructions for aps08/fullstack-clean-architecture, covering agent & project guidelines, agent behavior rules, 🚀 quick commands, frontend (web/) and backend (server/).

aps08/fullstack-clean-architecture · 1,733 tokens