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 nexus-research-lab/nexus --skill werewolf-6pgit clone --depth 1 https://github.com/nexus-research-lab/nexusWrote 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/nexus-research-lab/nexus/werewolf-6p)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/werewolf-6p"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/werewolf-6p/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/nexus-research-lab/nexus/werewolf-6p"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/werewolf-6p.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.03757 |
| Opus 5 | $0.00015 | $0.01878 |
| Sonnet 5 | $0.00006 | $0.00751 |
| Haiku 4.5 | $0.00003 | $0.00376 |
Grade A, and why
werewolf-6p 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Six-Player Werewolf
This skill layers werewolf game rules on top of the Room communication kernel. The Room system prompt already documents public @<member> wake semantics and the built-in nexus Room tools; this skill only defines the game contract. The host Agent is always the moderator and never a player.
Game Setup
Resolve participation before assigning any role:
- Treat the Room host Agent as the permanent moderator. Exclude it from roles, targets, speeches, votes, deaths, and win-condition counts.
- Ask the user exactly once whether to join as a player or spectate, using
AskUserQuestion, unless the opening request already states that choice explicitly. - If the user spectates, randomly select six non-host Agent players. The user receives no role and takes no game turn.
- If the user joins, use
用户玩家as the stable public name and randomly select five non-host Agent players. Extra non-host Agents are spectators and must not receive role cards or game wakes. - Stop before dealing roles if the Room has fewer than six candidate Agent players for spectator mode or fewer than five for user-participation mode. State the exact missing count; never start a partial game.
- Shuffle the six active players against
2 werewolves + 1 seer + 1 witch + 2 villagers. A participating user enters the same randomized role pool as every Agent player; never hand-pick or restrict the user's role.
The user can only join as a player and can never replace the host. Use the exact participation choices 参加本局 and 仅旁观 so the result is unambiguous.
After the active roster and roles are fixed, announce only the public roster. Keep the participation answer, role mapping, and inactive candidate list out of the public feed.
Wake Plumbing
The game has three execution channels:
- Public feed: a normal public reply containing a non-code
@<member>wakes that Agent member. An Agent handoff has exactly one naked@; a handoff to the user has none. - Agent private channel: use
nexus.send_messagewithdestination=current_roomandvisibility=privatefor Agent role cards, hidden collection, and host state. A private message can be record-only or can wake Agent recipients. - User private channel: only the host uses
AskUserQuestionfor the participation choice, the user's role card, and every hidden user decision. It pauses the host turn until the user answers without publishing the prompt or answer to the Room feed. Player Agents never use it to contact the user.
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 · 212 lines · 31 tokens per session scan A 5159bb6ed584
werewolf-6p is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 3,757 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.