Borrowing it
Nothing to install: this file belongs to mgh3326/auto_trader. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mgh3326/auto_trader/main/.claude/commands/crypto-alert-triage.mdgit clone --depth 1 https://github.com/mgh3326/auto_traderWrote 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/commands/mgh3326/auto_trader/crypto-alert-triage)<a href="https://agentmods.dev/commands/mgh3326/auto_trader/crypto-alert-triage"><img src="https://agentmods.dev/badge/commands/mgh3326/auto_trader/crypto-alert-triage/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/commands/mgh3326/auto_trader/crypto-alert-triage"><img src="https://agentmods.dev/badge/commands/mgh3326/auto_trader/crypto-alert-triage.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 | $0.00029 | $0.00976 |
| Opus 5 | $0.00015 | $0.00488 |
| Sonnet 5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
crypto-alert-triage 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 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.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
crypto-alert-triage
watch 알림이 발화해 너를 깨웠다. 너는 신선한 세션이지만, 매매 맥락은 지속 아티팩트에 산다. 아래 순서로 맥락을 복원하고, 발화를 분석하고, dry_run 제안까지만 낸다. 실주문 금지.
입력
$ARGUMENTS 에 공백구분 key=value 로 이벤트 요약이 온다:
event_uuid=... symbol=... market=... source_report_uuid=... metric=... operator=... threshold=... current_value=...
먼저 이를 파싱한다. market이 비면 crypto로 간주.
1. 맥락 복원 (반드시 이 순서)
get_operating_briefing(market=<market>)— 현재 보유 / 미체결 주문(만료시각) / 활성 watch / 최신 리포트 / 최근 session_context.investment_report_get(report_uuid=<source_report_uuid>)— 발화 item의 rationale / evidence_snapshot / trigger_checklist / max_action / watch_condition. "왜 이 watch를 걸었나"를 복원.session_context_get_recent(market=<market>, limit=10)— 직전 트리아지·결정 핸드오프(decision/next_action/open_question). "지난번에 뭘 보고 뭘 미뤘나".
2. 분석
- 트리거가 여전히 유효한가? (현재가 vs threshold, 노이즈 여부)
trigger_checklist항목을 하나씩 점검.max_action(side/qty·notional/limit/ladder_level)이 지금도 타당한가? 포트폴리오 제약(미체결/현금/중복 반대주문) 반영.- 손실매도 가드·현금 정책 등 memory/CLAUDE.md 정책과 충돌 없는가.
3. dry_run 미리보기 (read-only)
- 필요하면
buy_ladder_fill_preview/sell_ladder_fill_preview등 read-only preview로 실행안을 시뮬레이션. - 실주문 절대 금지: place/modify/cancel/reconcile 도구는 권한으로 차단되어 있고, 호출해서도 안 된다. 너는 제안만 한다.
4. 출력 (둘 다 수행)
session_context_append(entries=[{ "market": "<market>", "entry_type": "decision", "title": "<symbol> watch 트리아지", "body": "<핵심 판단 + 제안 dry_run + 다음 액션>", "refs": { "report_uuid": "<source_report_uuid>", "event_uuid": "<event_uuid>", "symbols": ["<symbol>"] }, "created_by": "crypto-alert-triage", "session_label": "alert-triage" }])— 다음 신선 런이 읽을 핸드오프.- 마지막 assistant 메시지로 Discord와 Telegram 양쪽에 그대로 전달 가능한 간결 요약을 낸다(이게
--output-format json의.result로 회신된다). 아래 섹션 제목을 유지한다:## 알림 요약- 발화 symbol/market/조건/current_value를 한 줄로 요약.
- 트리거가 여전히 유효한지 한 줄로 요약.
## 제안 verdictapprove_dry_run,wait,reject,needs_human_review중 하나.- 핵심 근거 2~3개.
- 제안 dry_run 실행안(side/수량/지정가)이 있으면 적고, 없으면
dry_run 제안 없음으로 적는다.
## 결정 필요- 운영자 확인이 필요한 경우에만 이 섹션을 포함한다.
- 섹션을 포함할 때 마지막 줄은 다음 문장 그대로 쓴다: operator 세션에서:
session_context 최근 제안 승인 검토
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.
- 8d ago First seen · 53 lines · 29 tokens per session scan A 6e0374bd31a8
crypto-alert-triage is a command published in the GitHub repository mgh3326/auto_trader (6 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 976 once invoked, about $0.0001 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 commands, from other repositories
cost-report
Generate a local Claude Code cost report from the ECC cost-tracker metrics log.
review
Review code changes against project conventions.
pm-burn
Cost burn-rate — LLM cost over the last N days vs a human-equivalent baseline (savingsx). Flags cost outliers and abnormal-burn agents.
flow-nexus-payments
Credit management, billing, and payment configuration.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.