Borrowing it
Nothing to install: this file belongs to Benboerba620/daily-watchlist. 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/Benboerba620/daily-watchlist/main/.claude/commands/dw-today.mdgit clone --depth 1 https://github.com/Benboerba620/daily-watchlistWrote 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/benboerba620/daily-watchlist/dw-today)<a href="https://agentmods.dev/commands/benboerba620/daily-watchlist/dw-today"><img src="https://agentmods.dev/badge/commands/benboerba620/daily-watchlist/dw-today/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/benboerba620/daily-watchlist/dw-today"><img src="https://agentmods.dev/badge/commands/benboerba620/daily-watchlist/dw-today.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 | $0.00007 | $0.00739 |
| Opus 5 | $0.00003 | $0.00369 |
| Sonnet 5 | $0.00001 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
dw-today 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.
What it actually says
生成每日监控简报。
工作流
Step 1: 读取配置
一次性读取以下文件:
config/daily-watchlist.yamlconfig/daily-watchlist-watchlist.mdtemplates/daily-watchlist-report-template.mdconfig/hypothesis-tracker.yaml(如存在)hypothesis/H*.md(如存在)
重点读取 reporting 段:
reporting.model_profilereporting.secondary_verify
只要 reporting.model_profile == "domestic" 或 reporting.secondary_verify == true,后续所有 WebSearch 结果都必须执行二次验证。
Step 2: 先触发日报生成脚本
必须先执行:
python scripts/generate_daily_report.py
执行后会在 daily-watchlist-reports/YYYY-MM/YYYY-MM-DD.md 生成一份日报骨架。读取该文件,后续所有补充都基于这份新生成的日报进行。
如果存在 hypothesis/H*.md,脚本会同时生成“假设联动”区,并把本地可确认的异动/财报信号回写为证据。
Step 3: 补新闻与主题
新闻检索必须由 Claude Code 通过 WebSearch 完成。
异动新闻:
- 对“重点异动”中的每只股票搜索
"{ticker} {name} stock news today"
财报反应:
- 对“已披露”中存在实际 EPS 的股票搜索
"{ticker} earnings reaction"
主题新闻:
- 对配置中的每个
focus_area(最多 3 个)按keywords组合搜索 - 命中
required_any才纳入 - 命中
exclude直接剔除
Step 4: 二次验证
触发二次验证时,逐条检查:
- 来源是否可信
- 发布时间是否足够新
- 标题与正文关键事实是否一致
- 报告中引用的数字、日期、公司名能否在原文核对
处理规则:
- 可核对且可信:写入日报
- 关键信息可核对但来源一般:写入并标注疑点
- 无法核对:写成
⚠️ 待人工确认:{原因}
Step 5: 完成日报
把骨架里的占位内容替换为实际内容:
- “用 WebSearch 补充新闻与原因分析”
- “用 Claude Code WebSearch 进行主题新闻检索并在核实来源后写入”
- 其他占位说明
最终写回 daily-watchlist-reports/YYYY-MM/YYYY-MM-DD.md。
Step 6: Wiki 归档(如有)
如果存在 wiki/entities/,仅归档高信号事件:
- 涨跌幅绝对值大于等于 10%
- 财报 beat/miss
格式:
## YYYY-MM-DD
- {TICKER} {+/-X.X%}: {一句话原因} ([source](url))
失败处理
- 脚本失败时跳过对应部分,继续后续流程
- WebSearch 失败时标记为“待人工补充”
- 不要编造数据
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.
- 10d ago First seen · 90 lines · 7 tokens per session scan A f3402f01b92c
dw-today is a command published in the GitHub repository Benboerba620/daily-watchlist (60 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 739 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
sonarqube
Analyze SonarCloud quality issues for a specific PR.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
refactor
Analyze code for SOLID violations and suggest targeted improvements.
generate-tests
Generate comprehensive tests for specified code.