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-entrygit 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-entry)<a href="https://agentmods.dev/skills/millw14/merrymen/trader-entry"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-entry/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-entry"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-entry.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 | $0.00199 | $0.02280 |
| Opus 5.5 | $0.00080 | $0.00912 |
| Sonnet 5.5 | $0.00040 | $0.00456 |
| Haiku 4.5 | $0.00020 | $0.00228 |
Grade A, and why
trader-entry 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trader-entry
The Entry Timer turns a setup into one moment: the bar that confirms it. It reads bars, 1-minute or 5-minute, and waits for each one to finish. A price that pokes above the high in the middle of a bar is not an entry. A bar that CLOSES above it is. Then it says the time and the price, writes them down for the Exit Planner, and stops. It never buys anything. Day trading loses most people money, and a clean signal does not change that.
${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).
python3 "${CLAUDE_SKILL_DIR}/entry.py" check TSLA # 15-minute opening range, 5-minute bars
python3 "${CLAUDE_SKILL_DIR}/entry.py" check TSLA --write # also save trader/entry.json
python3 "${CLAUDE_SKILL_DIR}/entry.py" check TSLA --setup level --level 371.20
python3 "${CLAUDE_SKILL_DIR}/entry.py" check TSLA --interval 1m --min-volume-x 1.5
python3 "${CLAUDE_SKILL_DIR}/entry.py" watch TSLA --until 15:30 # one line per closed bar, stops on the trigger
python3 "${CLAUDE_SKILL_DIR}/entry.py" watchlist # every hit in trader/watchlist.json
Other flags: --or-minutes N (default 15), --json, --offline FILE (a
saved Yahoo chart JSON, .json or .json.gz, or a folder of
<TICKER>.json), --now "2026-10-19 10:15" (New York time) to replay a day.
watch with --now or --offline runs on a simulated clock and replays the
day bar by bar without waiting.
What it reads and writes
| file | what |
|---|---|
trader/watchlist.json |
the scanner's hits (hits[].symbol), for watchlist |
trader/config.json |
no_entries_before (09:45) and no_entries_after (15:30), New York time. Optional |
| Yahoo chart API | today's bars, range=1d&interval=5m (or 1m): free, unofficial, can lag |
trader/entry.json |
with check --write, or when watch triggers: symbol, setup, status, time, bar, price, level, opening range |
The rule
- Opening range (orb). The high and low of the first 15 minutes: the 9:30, 9:35 and 9:40 five-minute bars, or fifteen 1-minute bars. The level to beat is the range high.
- Level. A price you give, like a 20-day high from
/trader-scanner. - The trigger is the first completed bar after the range that CLOSES above the level. A wick above is not a trigger. A close exactly at the level is not above it.
- The time is that bar's close time (the 10:10 bar closes at 10:15 AM). The price is its close, to the cent.
- Only closed bars count. A bar is closed when the clock passes its start plus 5 (or 1) minutes and Yahoo has caught up to that moment (it waits a minute at most). Yahoo's live tick, like 10:49:45, is never a bar.
- Volume, if you want it.
--min-volume-x 1.5also needs the trigger bar's volume at 1.5 times the range bars' average. The 9:30 bar holds the opening auction, so 1.0 is already strict. - Time limits. No entries before 9:45 or after 15:30 (config). On a 1:00 p.m. early close the cutoff moves up with the close, to 12:30.
- What it says. Waiting (and how far the last close is from the level), triggered, expired, or no data. Before 9:30: not open yet. Before 9:45: the range is still forming. Weekends and NYSE holidays: the market is closed.
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 · 148 lines · 199 tokens per session scan A 7164d3e90a72
trader-entry is a skill published in the GitHub repository millw14/merrymen (55 stars, last pushed yesterday), licensed MIT. It adds 199 tokens to every session and 2,280 once invoked, about $0.0008 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-entry compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trader-entrymillw14/merrymen | Skill | 55 | yesterday | MIT | A | 199 | 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 |