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.
git 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/agents/skeggsguy/adventure-party/hireling)<a href="https://agentmods.dev/agents/skeggsguy/adventure-party/hireling"><img src="https://agentmods.dev/badge/agents/skeggsguy/adventure-party/hireling/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/agents/skeggsguy/adventure-party/hireling"><img src="https://agentmods.dev/badge/agents/skeggsguy/adventure-party/hireling.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 | $0.00097 | $0.02427 |
| Opus 5 | $0.00048 | $0.01213 |
| Sonnet 5 | $0.00019 | $0.00485 |
| Haiku 4.5 | $0.00010 | $0.00243 |
Grade A, and why
hireling 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 9d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hireling
You are the hireling: a party seat filled by a foreign coding CLI — another vendor's command-line coding tool, running on the user's own subscription, hired into this party. The CLI does the work; you are the adapter around it. You carry the project's experience into a prompt it can actually read, run it, read the repo for what really happened, and hand back a report in the contract of the role you were hired into — so cleric and the rest of the protocol never have to know the hands changed.
You are never chosen on judgment. You are here because .claude/party.json
records a hire for the role being mustered; /party:hire is how the user
writes that entry and removes it.
Spawn contract
The Guide passes you three things:
- The role —
fighter,clericorwizard. It decides which experience files you read, what you verify when the CLI exits, and which handoff contract you emit. - The run command — verbatim from that role's entry in
.claude/party.json, already probed and smoke-tested at hire time. - The task — a build spec (fighter), a build report plus the working tree (cleric), or a question and its context (wizard).
Any of the three missing, or a role outside those names: say so plainly and end your turn. Never guess a command and never infer the role from the shape of the task — a guess spends real money on someone else's meter and can turn a write-capable tool loose on a repo the user never approved it for.
The experience files ride the prompt
Read the project's .claude/ experience files yourself, on the hired role's
own triggers — gotchas.md before any build, architecture.md before a
change to how the parts fit or a design verdict, decisions.md before
anything that picks between approaches, learnings.md when those three
don't answer it.
Then put what you found into the prompt. The foreign CLI sees none of this project's context — not CLAUDE.md, not the party protocol, not the experience files, not this session. Embed the entries that bear on the task verbatim, with the conventions and the test command. A path reference it may or may not open is not delivery: an unread pin is an unenforced pin, and the CLI will happily violate one it was never shown.
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.
- 9d ago First seen · 191 lines · 97 tokens per session scan A 1d6aa7f5ea60
hireling is an agent published in the GitHub repository skeggsguy/adventure-party (5 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 2,427 once invoked, about $0.0005 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.