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 skeggsguy/adventure-party --skill hiregit clone --depth 1 https://github.com/skeggsguy/adventure-partyWrote 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/skeggsguy/adventure-party/hire)<a href="https://agentmods.dev/skills/skeggsguy/adventure-party/hire"><img src="https://agentmods.dev/badge/skills/skeggsguy/adventure-party/hire/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/skeggsguy/adventure-party/hire"><img src="https://agentmods.dev/badge/skills/skeggsguy/adventure-party/hire.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 | $0.00078 | $0.02486 |
| Opus 5 | $0.00039 | $0.01243 |
| Sonnet 5 | $0.00016 | $0.00497 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
hire 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 11d ago.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hire
A hireling is a foreign coding CLI — another vendor's command-line coding
tool, on the user's own subscription — standing in for a party member. This
skill hires one into a role or releases it. It ships no code and runs no
quest: it proves a command works, then records it in .claude/party.json,
where the muster rule reads it in every later session.
Hiring is standing configuration, not a one-off summons. Once fighter is hired out, every muster of fighter runs through that command until the user releases it — and both directions are one command.
The Guide is never hireable; it is the session the user is talking to. The
three hireable roles are fighter, cleric and wizard.
No arguments — status
Read .claude/party.json if it exists. Most projects won't have one; that
is not an error and is not the moment to create it. Report one line per
role — hired to what, or the party's own member — and name both commands:
/party:hire <role> <cli> to hire, /party:hire <role> to release.
A bare /party:hire then starts the hire flow below with both gaps to
fill, in one clickable interaction; if the user asked only for status, stop
after the report.
/party:hire <role> <cli> — hire
Work in this order, stopping at the first step that fails. Each step exists to make a later, more expensive failure impossible.
-
Fill the gaps with choices. The full
/party:hire <role> <cli>form still works, and an argument already supplied skips the question it answers. Put every missing choice to the user as a clickable question with options, never a free-typed prompt.A role outside
fighter,clericandwizard, including the Guide, can't be hired: if one was supplied, say so plainly and stop. When both role and CLI are missing, put both questions in the same clickable interaction; the role options arefighter,clericandwizard.For a missing CLI, run
command -vfor this short alphabetical list of coding-CLI binary names:aider,codex,copilot,cursor-agent,gemini,opencode. Offer only the names the sweep actually finds, alphabetically, plusOther; attach no vendor descriptions and do not rank them. A name that is stale or absent simply never appears.Otheraccepts a name or full path the sweep missed; if nothing is found, it is the only CLI option. -
Find the binary and confirm what it is. Run
command -v <cli>. Not found ends it — offer to take a full path instead. Then run its version flag and show the user the output. A name on PATH proves nothing about what answers to it: on Windows,bashis the WSL shim andconvertis a filesystem tool, andcommand -vfinds both happily. -
Probe how to run it. Read the CLI's own help output and settle the four things that matter — how to run a single prompt non-interactively (no TUI, no REPL, exits when done), how to grant it write access to files, how to select a model on the command line, and how to set reasoning effort if the CLI has that knob.
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.
- 11d ago First seen · 193 lines · 78 tokens per session scan A 4b36eb186e40
hire is a skill published in the GitHub repository skeggsguy/adventure-party (5 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,486 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…