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-brokergit 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-broker)<a href="https://agentmods.dev/skills/millw14/merrymen/trader-broker"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-broker/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-broker"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-broker.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 | $0.00228 | $0.03908 |
| Opus 5.5 | $0.00091 | $0.01563 |
| Sonnet 5.5 | $0.00046 | $0.00782 |
| Haiku 4.5 | $0.00023 | $0.00391 |
Grade A, and why
trader-broker 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trader-broker
The Order Executor is the only skill in this pack that can lead to a trade, so it is the strictest. The broker is the user's own Merrymen agent: Claude never holds keys, never signs and never trades directly. It prepares a proposal; the owner approves it in Merrymen; the agent executes it inside its own signed limits. A trade happens only after four gates, every time, for every order:
- trader-risk passed this exact order today (matched by fingerprint, which covers the token address and the agent).
- The user typed an explicit yes for this one order in the chat.
- The user allowed Claude's own permission card for
propose_trade, once. - The owner approved the proposal in Merrymen, signed in on Merrymen's own page, within 15 minutes. The agent's signed per-trade limit, daily budget, drawdown breaker and permission expiry still apply after that.
Three yeses from the user, one PASS from the rules. No yes, no trade.
${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).
python3 "${CLAUDE_SKILL_DIR}/merrymen.py" summary # what the saved Merrymen results say
python3 "${CLAUDE_SKILL_DIR}/ticket.py" show # every ticket, READY or not
python3 "${CLAUDE_SKILL_DIR}/ticket.py" approve --index 1 --reply "yes"
python3 "${CLAUDE_SKILL_DIR}/ticket.py" result --index 1 --status proposed --proposal-id prp_... --approval-url URL
python3 "${CLAUDE_SKILL_DIR}/ticket.py" result --index 1 --status paper_filled --filled-qty 0.0685 --filled-price 364.95
python3 "${CLAUDE_SKILL_DIR}/ticket.py" flatten --symbol TSLA --value-usdg 25.40
python3 "${CLAUDE_SKILL_DIR}/ticket.py" log
ticket.py and merrymen.py never talk to Merrymen. Claude calls the
Merrymen tools and saves what they return; the scripts render tickets, check
that a reply is a real yes for that order, build the flatten ticket, and keep
the log in trader/state/broker.json. --now "2026-10-19 10:15" pins the
clock (New York time).
What ships with it
2 files 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 · 241 lines · 228 tokens per session scan A c2d981bc7795
trader-broker is a skill published in the GitHub repository millw14/merrymen (55 stars, last pushed yesterday), licensed MIT. It adds 228 tokens to every session and 3,908 once invoked, about $0.0009 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-broker compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trader-brokermillw14/merrymen | Skill | 55 | yesterday | MIT | A | 228 | 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 |