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 agentmods add skills/qq362946/fantasy/fantasy-netnpx skills add qq362946/Fantasy --skill fantasy-netgit clone --depth 1 https://github.com/qq362946/FantasyWrote 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/qq362946/fantasy/fantasy-net)<a href="https://agentmods.dev/skills/qq362946/fantasy/fantasy-net"><img src="https://agentmods.dev/badge/skills/qq362946/fantasy/fantasy-net.svg" alt="Measured on agentmods" 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 | $0.00157 | $0.04748 |
| Opus 5 | $0.00078 | $0.02374 |
| Sonnet 5 | $0.00031 | $0.00950 |
| Haiku 4.5 | $0.00016 | $0.00475 |
Grade A, and why
fantasy-net 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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- REFERENCE_GUIDELINES.md 6.0 KB
- references/config-check.md 3.3 KB
- references/config-scenarios.md 4.8 KB
- references/config.md 4.4 KB
- references/database/best-practices.md 2.6 KB
- references/database/database-check.md 1.8 KB
- references/database/index.md 1.8 KB
- references/database/mongodb.md 4.0 KB
- references/database/separate-table.md 3.8 KB
- references/ecs/ecs-check.md 2.6 KB
- references/ecs/entity-definition.md 2.9 KB
- references/ecs/entity-operations.md 1.6 KB
- references/ecs/index.md 1.6 KB
- references/ecs/lifecycle.md 4.2 KB
- references/ecs/object-pool.md 1.4 KB
- references/ecs/scene.md 4.7 KB
- references/ecs/subscene.md 8.3 KB
- references/event/check-event.md 4.7 KB
- references/event/entity-event.md 4.3 KB
- references/event/event-awaiter-design.md 1.7 KB
- references/event/event-awaiter-implement.md 2.4 KB
- references/event/event-awaiter-troubleshoot.md 1.7 KB
- references/event/event-awaiter.md 1.0 KB
- references/event/index.md 3.4 KB
- references/event/struct-event.md 3.6 KB
- references/guidelines-examples.md 8.5 KB
- references/http-check.md 1.4 KB
- references/http-controller.md 3.4 KB
- references/http-server.md 3.6 KB
- references/http.md 1.2 KB
- references/logging-check.md 1.5 KB
- references/logging.md 5.0 KB
- references/protocol/define-common.md 3.0 KB
- references/protocol/define-inner.md 2.6 KB
- references/protocol/define-outer.md 3.1 KB
- references/protocol/define.md 1.7 KB
- references/protocol/export-install.md 2.6 KB
- references/protocol/export.md 1.4 KB
- references/protocol/index.md 729 B
- references/protocol/protocol-check.md 1.6 KB
- references/review.md 7.9 KB
- references/server/address-check.md 3.5 KB
- references/server/address.md 6.6 KB
- references/server/entry-initialize-hook-check.md 8.5 KB
- references/server/entry-initialize-hook.md 8.7 KB
- references/server/kubernetes.md 3.0 KB
- references/server/roaming/error-codes.md 3.2 KB
- references/server/roaming/handler.md 766 B
- references/server/roaming/index.md 2.8 KB
- references/server/roaming/messaging.md 2.7 KB
- references/server/roaming/on-create-terminus.md 5.0 KB
- references/server/roaming/on-dispose-terminus.md 3.6 KB
- references/server/roaming/protocol.md 2.8 KB
- references/server/roaming/roaming-check.md 5.2 KB
- references/server/roaming/setup.md 5.8 KB
- references/server/roaming/transfer.md 1.6 KB
- references/server/server-message-handler-check.md 1.1 KB
- references/server/server-message-handler.md 6.0 KB
- references/server/setup-server-check.md 1.1 KB
- references/server/setup-server.md 4.7 KB
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.
- 5d ago First seen · 175 lines · 157 tokens per session scan A 87c9dee07314
fantasy-net is a skill published in the GitHub repository qq362946/Fantasy (1,407 stars, last pushed 2d ago), with no licence file. It adds 157 tokens to every session and 4,748 once invoked, about $0.0008 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
luban-dev
Luban 游戏配置全栈工具,支持枚举/Bean/数据表的增删改查、代码生成、TEngine 集成。触发场景:(1) 编辑游戏配置数据(配置表/数据表/道具表/技能表/奖励表/活动表),(2) 新增/修改/删除配置表结构,(3) 定义枚举/Bean/字段,(4) 导表/生成配置代码,(5) 编写 luban.conf 或 Schema 定义,(6) Luban 类型系统/校验器问题。即使用户未明确说"Luban",只要是编辑游戏配置数据,也应使用此技能。.
html-to-ugui
HTML 原型转 Unity UGUI 智能 Prefab 生成管线。通过 AI 生成符合 UI-DSL 的 HTML,用 Playwright/浏览器烘焙 JSON v2 坐标、图片和适配意图,再导入 Unity 由 HtmlToUGUIBaker 生成可维护、多终端适配的 UGUI Prefab。触发场景:(1) 需要从自然语言生成 Unity UGUI 界面 (2) 需要从 HTML 原型烘焙 UGUI (3) UI 中包含图片并希望一键导入/绑定 Sprite (4) 需要 PC/mobile/pad 多终端适配 Prefab。.
tengine-dev
TEngine Unity 游戏框架开发指导。触发词:TEngine, UIWindow, UIWidget, GameEvent, AddUIEvent, LoadAssetAsync, SetSprite, HybridCLR, YooAsset, Luban, GameModule, 热更, 资源加载, UI开发, 事件系统, 配置表.
aibridge-development-workflow
AIBridge/Unity 项目的标准开发工作流。Use when creating, modifying, fixing, refactoring, or validating C# code, Unity assets, prefabs, editor tools, package structure, tests, AGENTS.md, or local Skills. Preserves visible modes for Skills matching, requirement confirmation, analysis, implementation, and final checklist. Do not use…
et-code
ET framework C# code authoring and review workflow. Use when creating or modifying Entity, Component, System, Helper, message handlers, package dependencies, assemblies, module analyzer boundaries, C# file placement, .meta handling, ECS layering, or component contract logic in WOW/ET packages.
uw-ui-toolkit-binder
Generate Unity 6+ UI Toolkit Runtime Data Binding code using MVVM pattern with [CreateProperty], DataBinding, and PropertyPath. Use when creating UI screens, HUDs, menus, inventories, settings panels, or any data-bound UI elements with UI Toolkit. Triggers on requests like "create a health bar", "build the HUD", "make…