claude-multi-agent-investing: Command for Claude Code

.claude/commands/weekly-brief.md

weekly-brief is a command for Claude Code from haiiibin/claude-multi-agent-investing. It costs 40 tokens per session (3,276 once invoked), scanned A, original, MIT.

A command for producing a weekly investment report by combining several analysts and personality-based agents.

In plain words
What is it for?
Use it for a full portfolio report or a focused report on selected tickers, using holdings, watchlists, recent YouTube videos, account cash, and existing transcripts before publishing the result to Notion.
Why use it?
It gathers signals from multiple sources and compares them into one report for the portfolio, reducing the need to run each analysis separately.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is haiiibin/claude-multi-agent-investing's own configuration. It tells Claude Code how to work on claude-multi-agent-investing 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 claude-multi-agent-investing configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python tools/transcribe.py {VIDEO_ID}.

Reuse

Borrowing it

Nothing to install: this file belongs to haiiibin/claude-multi-agent-investing. 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/haiiibin/claude-multi-agent-investing/main/.claude/commands/weekly-brief.md
Clone the repo
git clone --depth 1 https://github.com/haiiibin/claude-multi-agent-investing

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 weekly-brief

README.md
[![agentmods](https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/weekly-brief/github.svg)](https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/weekly-brief)
Your own site
<a href="https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/weekly-brief"><img src="https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/weekly-brief/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 weekly-brief

Your own site · 80×15
<a href="https://agentmods.dev/commands/haiiibin/claude-multi-agent-investing/weekly-brief"><img src="https://agentmods.dev/badge/commands/haiiibin/claude-multi-agent-investing/weekly-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00040 $0.03276
Opus 5 $0.00020 $0.01638
Sonnet 5 $0.00008 $0.00655
Haiku 4.5 $0.00004 $0.00328

Measured 10d ago against content hash bc9a66626738, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

weekly-brief 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 10d 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.

.claude/commands/weekly-brief.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/weekly-brief -- 全组合智能体综合简报

并行调度所有子智能体,交叉比对 YouTube 频道最新信号,对每个持仓给出统一行动建议,并自动推送 Notion 投资日志。

参数

  • 无参数 → 全组合简报(所有持仓 + 关键自选股)
  • focus TICKER1 TICKER2 → 对指定标的深度分析,其余轻量过一遍

第 0 步 -- 加载上下文(并行前必须先完成)

  1. 读取 portfolio/holdings.json
    • 提取所有持仓 ticker(CDR 解析:NVDA.NE → NVDA,COST.NE → COST)
    • 提取自选股前 5 条(按 price_snapshot.date 最近排序)
    • 记录各账户类型和当前现金余额
  2. 扫描 memory/short_term/ 目录,找出近 14 天内已有转录文件(audio_*_transcript.txt)的视频 ID -- 这些无需重复转录。
  3. 建立 主标的列表 = 持仓 ticker + 自选股 ticker(去重)。

第 1 步 -- 并行数据采集(全部同时发起,不等待任何一个完成)

以下任务全部并行

A. YouTube RSS 抓取(5 个频道同时 WebFetch)

频道 RSS
阳光财经 https://www.youtube.com/feeds/videos.xml?channel_id=UC2I5em6UyBpQiO-8ZW0nV3w
视野环球财经 https://www.youtube.com/feeds/videos.xml?channel_id=UCFQsi7WaF5X41tcuOryDk8w
美投君 https://www.youtube.com/feeds/videos.xml?channel_id=UCBUH38E0ngqvmTqdchWunwQ
美投News https://www.youtube.com/feeds/videos.xml?channel_id=UCGpj3DO_5_TUDCNUgS9mjiQ
贝拉聊财金 https://www.youtube.com/feeds/videos.xml?channel_id=UCVomjkM_t0EcctTWSE1Jvxg

提取格式:VIDEO_ID | YYYY-MM-DD | 标题(来自 <yt:videoId> 标签)。 只保留近 14 天内的视频,排除已有转录文件的 ID。

B. 宏观快照(调度 macro-analyst 子智能体)

调用 Agent 工具,subagent_type=macro-analyst,简报:

拉取 SPY/QQQ/VIX/^TNX/DXY/CL=F/GC=F/CAD=X 的 1日、1月、3月涨跌幅。识别当前市场 regime。用 python tools/polymarket.py 查询 Fed + 关税 + 衰退市场的预测概率。包含 USD/CAD。返回 JSON(按 macro-analyst agent spec)。

C. 新闻扫描(调度 news-analyst 子智能体)

调用 Agent 工具,subagent_type=news-analyst,简报:

对以下标的拉取最近新闻:{主标的列表}。每个标的打情绪分,标出高重要性事件(财报、分析师评级变化、产品发布、监管动作)。返回 JSON(按 news-analyst agent spec)。

D. 基本面快照(调度 fundamentals-analyst 子智能体)

调用 Agent 工具,subagent_type=fundamentals-analyst,简报:

对每个持仓标的,拉取:前瞻/追踪 PE、PEG、营收同比增速、毛利率、FCF yield、债务/权益比、分析师共识评级。异常指标高亮。返回紧凑表格。

E. 财报日历(WebSearch + earnings 数据)

查询主标的列表中未来 21 天内的财报日期:

WebSearch: "{ticker} earnings date Q2 2026"

或使用 mcp__yahoo-finance__get_stock_infoearningsDate 字段。

输出格式:TICKER | 预计财报日期 | 预期 EPS | 上季度实际 vs 预期

Read the full file on GitHub · 231 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. 10d ago First seen · 231 lines · 40 tokens per session scan A bc9a66626738

Subscribe to this mod's changes

weekly-brief is a command published in the GitHub repository haiiibin/claude-multi-agent-investing (2 stars, last pushed 19d ago), licensed MIT. It adds 40 tokens to every session and 3,276 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.