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.
npx skills add millw14/merrymen --skill trader-newsgit clone --depth 1 https://github.com/millw14/merrymenWrote 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/skills/millw14/merrymen/trader-news)<a href="https://agentmods.dev/skills/millw14/merrymen/trader-news"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-news/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/skills/millw14/merrymen/trader-news"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-news.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 | $0.00169 | $0.01449 |
| Opus 5.5 | $0.00068 | $0.00580 |
| Sonnet 5.5 | $0.00034 | $0.00290 |
| Haiku 4.5 | $0.00017 | $0.00145 |
Grade A, and why
trader-news scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trader-news
A chart can look perfect and still be about to gap on an earnings date, a halt or a lawsuit. Before a setup becomes a trade, this skill reads the two feeds that carry those first, for every stock on the watchlist, and tells you only what is new. It also prints how far each stock has moved today, so a headline and a move sit side by side.
Tool in this folder (standard library Python, no keys):
python3 "${CLAUDE_SKILL_DIR}/news.py" # watchlist + plan + portfolio
python3 "${CLAUDE_SKILL_DIR}/news.py" --tickers TSLA NVDA --hours 12
python3 "${CLAUDE_SKILL_DIR}/news.py" --no-sec --json
What it reads and writes
| file / feed | what |
|---|---|
--tickers, else trader/watchlist.json |
the scanner's hits (trader-scanner) |
trader/plan.json |
the trade you are planning (trader-exit) |
trader/portfolio.json |
what you hold (trader-broker records fills there) |
| Yahoo Finance headline RSS | https://feeds.finance.yahoo.com/rss/2.0/headline?s=TSLA®ion=US&lang=en-US |
| Yahoo Finance chart endpoint | the last price against yesterday's close (unofficial, can lag) |
| SEC EDGAR company Atom feed | 8-K by default (--forms 8-K,10-Q for more); needs sec_user_agent in trader/config.json or SEC_USER_AGENT, else filings are skipped with a note |
trader/state/news.json |
what has been shown (kept 30 days) and each ticker's CIK |
The rules
- Headlines are leads, not facts. Before telling the user something happened, open the story or the filing and read it. Quote the source and link it. Never summarise a paywalled story you could not read: say so.
- Filings beat headlines. If an 8-K and a headline disagree, the 8-K is what the company told the SEC.
- Say what it touches. Every item lists the tickers it touches and its
tags: earnings, analyst, legal, deal, capital, people, risk, halt,
regulatory, macro. Filings marked
!carry an important 8-K item: earnings results (2.02), an officer change (5.02), an impairment (2.06), a delisting notice (3.01), past financials no longer reliable (4.02), bankruptcy (1.03) or a cyber incident (1.05). - MOVING marks a stock 3 % or more from yesterday's close (
--move-pct). A move with no headline is worth saying out loud too. - No predictions. Report what was published and how far the price is from yesterday's close. Never say what the stock will do next.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 105 lines · 169 tokens per session scan A 6a26283452c1
trader-news is a skill published in the GitHub repository millw14/merrymen (55 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 1,449 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-11-19.
trader-news compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trader-newsmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 169 | Claude Code |
| sec_edgar0xmariowu/Autosearch | Skill | 56 | 6d ago | MIT | A | 35 | Claude Code |
| xueqiu0xmariowu/Autosearch | Skill | 56 | 6d ago | MIT | A | 30 | Claude Code |
| award-travelAwardTravelFinder/mcp | Skill | 16 | 20d ago | MIT | A | 164 | Claude Code |
| find-my-bookings-and-balancesAwardTravelFinder/mcp | Skill | 16 | 20d ago | MIT | A | 97 | Claude Code |
| setupAwardTravelFinder/mcp | Skill | 16 | 20d ago | MIT | A | 77 | Claude Code |
| cancel-or-change-awardAwardTravelFinder/mcp | Skill | 16 | 20d ago | MIT | A | 69 | Claude Code |