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/fill-event-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/fill-event-triage)<a href="https://agentmods.dev/commands/mgh3326/auto_trader/fill-event-triage"><img src="https://agentmods.dev/badge/commands/mgh3326/auto_trader/fill-event-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/fill-event-triage"><img src="https://agentmods.dev/badge/commands/mgh3326/auto_trader/fill-event-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 | $0.00041 | $0.01821 |
| Opus 5 | $0.00020 | $0.00911 |
| Sonnet 5 | $0.00008 | $0.00364 |
| Haiku 4.5 | $0.00004 | $0.00182 |
Grade A, and why
fill-event-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 9d 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.
fill-event-triage
체결(fill) 이벤트가 들어왔다. 너는 신선한 세션이지만, 매매 맥락은 지속 아티팩트에 산다. 아래 순서로 맥락을 복원하고, 매도/매수 분기에서 적절히 분석하고, dry_run 제안까지만 낸다. 실주문 금지.
입력
$ARGUMENTS 에 공백구분 key=value 로 체결 요약이 온다:
ledger_id=... event_key=... broker=... account_mode=... market=... symbol=... side=... filled_qty=... filled_price=... filled_notional=... currency=... filled_at=... correlation_id=...
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.get_cash_balance(...)— 매도 체결 후 현금/주문가능금액 재확인 (핵심). 특히 sell fill에서 어떤 통화로 얼마가 풀렸는지, 주문가능금액의 변화까지 같이 본다.get_portfolio_allocation(include_cash=true)— 활성 MCP profile에 해당 도구가 노출되어 있는 경우에만 호출한다. 매도 후 포트폴리오 비중 변화 / 현금 비율의 타겟 괴리를 점검한다.session_context_get_recent(market=<market>, limit=10)— 직전 트리아지·결정 핸드오프(decision/next_action/open_question). "지난번에 뭘 보고 뭘 미뤘나".session_context_append(...)— refs에{event_key, ledger_id, correlation_id, symbols}포함해 다음 신선 런이 읽을 핸드오프를 적재.
2. 분석
side 값에 따라 분기한다. 두 분기 모두 read-only 검토이며, 어떤 분기에서도 실주문을 호출하지 않는다.
분기 A — 매도(sell) 체결
풀린 현금과 그 재배치 판단에 집중한다.
- 어떤 현금/통화가 풀렸는가? (
filled_notional×currency, 수수료/슬리피지 고려) - 매도 후 현재 포트폴리오가 타겟 대비 under / over 어디에 있는가? (
get_portfolio_allocation결과의 비중 vs 타겟) - 기존 후보(latest report) / 활성 watch / 직전
session_context중 매도 자금으로 재검토해야 할 것이 있는가? - 운영자가 검토할 dry-run buy / redeploy 제안은 무엇인가? (재배치 후보 종목, 분할 수량, 지정가 구간)
분기 B — 매수(buy) 체결
체결된 트랜치의 완결성과 잔여 주문 가정의 유효성에 집중한다.
- 의도된 트랜치(tranche)가 실제로 다 체결되었는가? (
filled_qtyvs 의도 수량) - 남은 rung(미체결 주문) 가정이 여전히 유효한가? (지정가, 노트, 손절선, max_action)
- 운영자가 남은 주문을 pause / tighten / leave 중 어떻게 해야 하는가? 그 근거는 무엇인가?
분기 C — buy.support_reserve_net confirmed fill (operator §45/§46)
이 분기는 confirmed broker fill 이고, 해당 주문이 동일 policy version의
buy.support_reserve_net 티어였다는 주문/제안 증거가 있을 때만 적용한다. 가격 모양,
심볼, 또는 추정 RSI로 티어를 추론하지 않는다. 귀속 증거가 없거나 주문 상태가
unknown/ambiguous이면 KEEP_RESERVED_AND_BLOCK으로 결론 내리고 취소 대상이나 가용
현금을 만들어내지 않는다.
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.
- 9d ago First seen · 97 lines · 41 tokens per session scan A 37bb96b37636
fill-event-triage is a command published in the GitHub repository mgh3326/auto_trader (6 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,821 once invoked, about $0.0002 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.