werewolf-6p

werewolf-6p is a skill for Claude Code, Codex from nexus-research-lab/nexus. It costs 31 tokens per session (3,757 once invoked), scanned A, original, Apache-2.0.

A six-player Werewolf game format for a shared chat room, with an AI host acting as moderator. The user can join the randomized player group or watch as a spectator.

In plain words
What is it for?
Use it to run a six-player social deduction game among AI agents, with one user playing or observing.
Why use it?
It provides clear rules for choosing players, assigning roles, running turns, and deciding the winner. It also prevents the host from being treated as a player.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

Good fit Use it to run a six-player social deduction game among AI agents, with one user playing or observing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nexus-research-lab/nexus/werewolf-6p
Install

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.

Any agent
npx skills add nexus-research-lab/nexus --skill werewolf-6p
Clone the repo
git clone --depth 1 https://github.com/nexus-research-lab/nexus

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for werewolf-6p

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexus-research-lab/nexus/werewolf-6p/github.svg)](https://agentmods.dev/skills/nexus-research-lab/nexus/werewolf-6p)
Your own site
<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.

agentmods 80×15 button for werewolf-6p

Your own site · 80×15
<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>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,757 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 5159bb6ed584, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/werewolf-6p/SKILL.md · 212 lines

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:

  1. Treat the Room host Agent as the permanent moderator. Exclude it from roles, targets, speeches, votes, deaths, and win-condition counts.
  2. Ask the user exactly once whether to join as a player or spectate, using AskUserQuestion, unless the opening request already states that choice explicitly.
  3. If the user spectates, randomly select six non-host Agent players. The user receives no role and takes no game turn.
  4. 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.
  5. 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.
  6. 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_message with destination=current_room and visibility=private for 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 AskUserQuestion for 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.

Read the full file on GitHub · 212 lines

Changes

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.

  1. 11d ago First seen · 212 lines · 31 tokens per session scan A 5159bb6ed584

Subscribe to this mod's changes

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.

Related

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…

walkinglabs/learn-harness-engineering · 142 tokens

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…

agentscope-ai/agentscope-java · 91 tokens

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.

agentscope-ai/agentscope-java · 38 tokens

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.

agentscope-ai/agentscope-java · 39 tokens

agent-optimization

Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.

Prism-Shadow/penguin-harness · 22 tokens

agent-evaluation

Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.

Prism-Shadow/penguin-harness · 28 tokens