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 merrymen-setupgit 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/merrymen-setup)<a href="https://agentmods.dev/skills/millw14/merrymen/merrymen-setup"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/merrymen-setup/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/merrymen-setup"><img src="https://agentmods.dev/badge/skills/millw14/merrymen/merrymen-setup.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 | $0.00048 | $0.01080 |
| Opus 5.5 | $0.00019 | $0.00432 |
| Sonnet 5.5 | $0.00010 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
merrymen-setup 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Merrymen
Use only the connection's available tools and their current schemas. This package points to
https://mcp.merrymen.dev/mcp, a hosted service with OAuth. It does not install
a trading worker on the Bot's computer. Do not create another connection if
the host already has this endpoint configured and usable.
If tools are missing, ask the owner to connect or authenticate the plugin in their host. In Grok chat, the documented route is Connectors → New Connector → Custom, using the server URL above. Grok Bot is a separate product: use its supported plugin connection flow. This package is not evidence of a marketplace listing, and Grok chat's connector screen is not a Grok Bot installer.
The owner opens Merrymen's sign-in and consent page in their own device's browser, chooses the shared agent and permissions, and returns here. Never ask for passwords, OTPs, seed phrases, private keys or access tokens in chat. Never sign in to Merrymen, import a wallet, approve a proposal or sign a permission through the Bot's shared cloud computer, even if it has a browser. Give the owner the link instead.
Read before preparing
- Call
get_merryman_setup. Report its phase, observation time and next step. Uselist_agentsif the owner needs to choose between shared agents. An empty list means no agent is visible to this connection; it does not prove that the owner has no existing account or wallet. A status question does not authorize a new draft. - If an agent already exists, inspect
get_agent_status. Report permission expiry, worker freshness and blockers. Follow the returned owner links for sharing access, funding, permission renewal or recovery. Do not create a replacement wallet or change existing settings to resolve a setup blocker. - Before drafting, inspect a known proposal with
get_proposal, or uselist_proposalswith status=all when available. Resume a matching setup, including an approved draft whose owner signing is unfinished. Preserve choices supplied earlier; ask only if the intended agent/proposal is ambiguous or the configuration conflicts.
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 · 97 lines · 48 tokens per session scan A ee46cf1acf67
merrymen-setup is a skill published in the GitHub repository millw14/merrymen (55 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,080 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.
merrymen-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| merrymen-setupmillw14/merrymen | Skill | 55 | yesterday | MIT | A | 48 | Cursor |
| sanity-singletonssanity-io/agent-toolkit | Skill | 201 | yesterday | MIT | A | 90 | Claude Code |
| prior-art-searchRobThePCGuy/Claude-Patent-Creator | Skill | 211 | 2d ago | MIT | A | 42 | Claude Code |
| sanity-form-component-suspensesanity-io/agent-toolkit | Skill | 201 | yesterday | MIT | A | 149 | Claude Code |
| development-assistantRobThePCGuy/Claude-Patent-Creator | Skill | 211 | 2d ago | MIT | A | 21 | Claude Code |
| mpep-searchRobThePCGuy/Claude-Patent-Creator | Skill | 211 | 2d ago | MIT | A | 32 | Claude Code |
| video-perceptionjordanrendric/claude-video-vision | Skill | 1.5k | 1mo ago | MIT | A | 51 | Claude Code |