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-riskgit 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-risk)<a href="https://agentmods.dev/skills/millw14/merrymen/trader-risk"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-risk/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-risk"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/trader-risk.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 | $0.00301 | $0.03511 |
| Opus 5.5 | $0.00120 | $0.01404 |
| Sonnet 5.5 | $0.00060 | $0.00702 |
| Haiku 4.5 | $0.00030 | $0.00351 |
Grade A, and why
trader-risk 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
trader-risk
The Risk Manager is the gate between a proposal and Merrymen. Every order written by trader-budget or trader-broker's flatten passes through it. A BLOCK is final for that order: it does not go to the user for a yes, and it never becomes a Merrymen proposal. Merrymen checks its own signed limits again when the proposal is made, when the owner approves it and when the agent executes it; this check says no first, with the reason, before anyone is asked. Most people who day trade lose money. These limits keep each loss and each day's losses small. They do not make a trade win.
${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).
python3 "${CLAUDE_SKILL_DIR}/check.py" # trader/ files; writes trader/state/risk.json
python3 "${CLAUDE_SKILL_DIR}/check.py" --json
python3 "${CLAUDE_SKILL_DIR}/check.py" --no-write # look without recording
python3 "${CLAUDE_SKILL_DIR}/check.py" --now "2026-10-19 10:15" # pin the clock (New York time)
What it reads and writes
| file | what |
|---|---|
trader/orders.json |
the proposed orders (trader-budget, or trader-broker's flatten) |
trader/config.json |
the limits (trader-budget ships config.example.json) |
trader/portfolio.json |
cash and holdings; if missing, a fresh account funded with the budget |
trader/prices.json |
a fresh price raises the entry it measures risk from; also values holdings |
trader/merrymen/tokens.json |
Merrymen's stock tokens: the registry address for each symbol, paused or not |
trader/merrymen/agent.json |
the agent's status, mode, permission expiry, signed limits and 24-hour budget |
trader/merrymen/quotes.json |
the quote_trade result for this exact order |
trader/state/broker.json |
what was proposed or filled today: duplicates, trades per day, daily loss |
trader/state/risk.json |
the verdicts it writes, with a fingerprint of each exact order |
Entries and exits
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 · 214 lines · 301 tokens per session scan A 734a91edc308
trader-risk is a skill published in the GitHub repository millw14/merrymen (55 stars, last pushed yesterday), licensed MIT. It adds 301 tokens to every session and 3,511 once invoked, about $0.0012 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-risk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trader-riskmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 301 | 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 |