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 connectgit 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/connect)<a href="https://agentmods.dev/skills/millw14/merrymen/connect"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/connect/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/connect"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/connect.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 | $0.00058 | $0.00966 |
| Opus 5.5 | $0.00023 | $0.00386 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
connect 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.
What it actually says
Help the owner connect this Claude Code to Merrymen.
First check. Look for Merrymen tools in this session (their names end in list_agents, get_agent_status, search_tokens and so on). Any one of them means Merrymen is connected; which ones are there shows what the owner allowed, because a tool whose permission was left unticked is not offered at all.
- None at all: go to the sign-in steps below.
get_merryman_setupis there: call it first, even for a new owner. Use its reported next step; no visible agent does not prove no wallet exists. If the owner requested creation and drafting is allowed, callcreate_merrymanwith their name, strategy and risk choices, then show its owner review link. The owner reviews the exact setup and continues to wallet creation and trading-permission signing in Merrymen. Read setup again after signing; a draft or approval is not a running agent.- Only
list_agentsis there: call it and report which agents are shared; use/merrymen:statusor/merrymen:whyfor an existing agent. Do not infer that an empty result authorizes replacing a wallet. - Some Merrymen tools but no
list_agents: say it is connected but cannot see their agent (it was made without "See your agent's status and settings"), and list what it can do from the tools that are there. - If the owner came here because a request needed a tool that is not there, name the permission it needs:
get_agent_statusneeds "See your agent's status and settings",explain_agent_inactivity"See your agent's decisions",get_portfolio"See your portfolio and trades",get_summary"Create reports and exports",search_tokens"Research markets and public agents". They add a permission by signing in again (step 1 below) and ticking it under "Change what … can do"; a reconnect keeps what they allowed before.
For an existing agent, use create_agent_draft or propose_settings_change for requested configuration changes and return the owner review link. Never use new-agent creation to replace an existing agent. After activation, Merrymen's hosted worker runs independently of this conversation; no terminal or chat must stay open. Report permission expiry, service or funding blockers from the actual setup response.
Hosts with MCP Apps can show the interactive Merryman home for naming, strategy, risk, status, portfolio, activity, settings and alerts. Claude Code can use the same text responses and tools; an embedded view is optional. Other research, trade proposals, reports and community actions stay available in chat when their permission is granted.
If the requested work is complete, stop there; reconnect only when access is missing.
Otherwise, tell the owner how to sign in. You cannot do this step for them: it happens in their browser, on Merrymen's own page.
- Type
/mcp, choose plugin:merrymen:merrymen, and choose Authenticate. (From a terminal instead:claude mcp login plugin:merrymen:merrymen.) With this plugin installed, this is the entry to sign in to even if they already added Merrymen to Claude on claude.ai: the plugin's server takes the place of that connector. - Merrymen opens in the browser. Sign in if asked, check what Claude Code will be able to do, and click Allow.
- Come back and call
get_merryman_setup, or run/merrymen:statusfor an existing agent.
More ways to connect, for other assistants: https://app.merrymen.dev/connect/mcp.
What the connection can and cannot do. It sees only the agent and the permissions the owner allows on that page, and they can disconnect it at any time on Connected apps (https://app.merrymen.dev/connect/apps). With the usual permissions it can also message the agent, run backtests and manage the watchlist and alerts. It can suggest trades or setting changes only if the owner allowed that, and nothing happens until they approve each one in Merrymen. It can never move their funds, see their keys, turn on live trading or loosen their limits.
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 · 30 lines · 58 tokens per session scan A 97ff6f06d3da
connect is a skill published in the GitHub repository millw14/merrymen (55 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 966 once invoked, about $0.0002 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.
connect compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| connectmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 58 | 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 |