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 avalon-8-10pgit 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/avalon-8-10p)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/avalon-8-10p"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/avalon-8-10p/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/avalon-8-10p"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/avalon-8-10p.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 | $0.00034 | $0.02260 |
| Opus 5 | $0.00017 | $0.01130 |
| Sonnet 5 | $0.00007 | $0.00452 |
| Haiku 4.5 | $0.00003 | $0.00226 |
Grade A, and why
avalon-8-10p 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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
8–10-Player Avalon
This skill layers a complete base game of Avalon on top of the Room communication kernel. The Room system prompt already defines public @<member> wakes and the built-in nexus Room tools; this skill defines only the game contract. The host Agent is always the moderator and never a player.
Game Setup
Resolve participation and player count before assigning roles:
- Exclude the host Agent from roles, leadership, teams, votes, 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. Use the exact choices参加本局and仅旁观. - If the opening request explicitly names 8, 9, or 10 players, use that count. Reject any unsupported count instead of silently changing it.
- Otherwise choose the largest supported count in the order
10, 9, 8that the Room can fill. A participating user occupies one player seat; a spectating user occupies none. - Randomly select the required non-host Agent players. Extra Agents and a spectating user remain spectators and receive no role card or game wake.
- If the requested count cannot be filled, stop before dealing roles and state the exact number of missing players. If no count was requested and fewer than eight seats can be filled, report how many players are missing for an eight-player game.
- Use
用户玩家as the participating user's stable public name. A participating user enters the same randomized role pool as every Agent player and can receive any role, become leader, join a quest, and vote.
Use exactly this role table:
| Players | Good | Evil |
|---|---|---|
| 8 | Merlin, Percival, 3 Loyal Servants | Morgana, Assassin, Minion |
| 9 | Merlin, Percival, 4 Loyal Servants | Mordred, Morgana, Assassin |
| 10 | Merlin, Percival, 4 Loyal Servants | Mordred, Morgana, Oberon, Assassin |
Shuffle roles across all active players, then independently randomize the circular seating order and first leader. Announce only the player count, active roster, seating order, and first leader. Keep the participation answer, role mapping, and inactive candidate list private.
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.
- 7d ago First seen · 153 lines · 34 tokens per session scan A 6800e14b6374
avalon-8-10p is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 2,260 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 2026-09-03.
Other skills, from other repositories
threejs-animation
Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
threejs-loaders
Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.
threejs-materials
Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.
threejs-fundamentals
Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.