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 ggg123124/vrchat-assistant --skill vrchat-world-queriesgit clone --depth 1 https://github.com/ggg123124/vrchat-assistantWrote 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/ggg123124/vrchat-assistant/vrchat-world-queries)<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/vrchat-world-queries"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/vrchat-world-queries/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/ggg123124/vrchat-assistant/vrchat-world-queries"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/vrchat-world-queries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 146 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00020 | $0.04137 |
| Opus 5 | $0.00010 | $0.02069 |
| Sonnet 5 | $0.00004 | $0.00827 |
| Haiku 4.5 | $0.00002 | $0.00414 |
Grade A, and why
vrchat-world-queries scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **添加**：`x_add_creator {screen_name, name}`——screen_name 是 X 用户名**不带 @**；name 是展示名（可中文/日文，MSYS curl 发中文会乱码，**必须 Python urllib 直发**）。博主清单存 DB config 表 `x_creators`（JSON 数组），添加即时生效无需重启 How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VRChat 世界域 — 挑世界/推荐/情报挖掘/X 博主
本 skill 覆盖 vrc-monitor 的世界域：挑新世界、待逛列表（backlog）、世界推荐、PlanetVRC 检索、世界情报/彩蛋/攻略挖掘、X 博主世界推荐，以及地图列表展示格式。
⚠️ 工具表唯一权威在 vrc-monitor-agent skill。本 skill 只写工作流与域内细节，不复制工具表。通用 MCP 调用陷阱见 vrc-monitor-agent「常见陷阱」。 MCP 端点：
http://127.0.0.1:8799/mcp；开图用 open_world 的完整参数/回退语义见 vrchat-social-queries §11.4（跨域指针，本域只记调用行）。
1. 挑新世界（「没去过的 + 适合聊天的」）
用户说「挑个新世界 / 没去过的 / 适合聊天」时，四步：
- 拉候选：
get_new_worlds {onlyUnvisited: true, limit: 50, sortBy: 'favorites'}→ 未逛新世界按收藏降序（⚠️ 字段名worldName不是name；limit 上限 50，不够可翻页/换 sortBy） - 按名粗筛：剔除明显的游戏图（名字含 Game/战斗/恐怖/Roleplay/赌场等），留氛围向（神殿/旅馆/月亮/安静小屋/咖啡厅）
- 补简介：候选逐个
get_world_name {worldId}拿 description + capacity 判断聊天氛围 - 开图：用户拍板后调 MCP
open_world {worldId, type:'hidden', region:'jp'}→ 自动建 jp 隐藏房；管道直发优先、不可用静默回退 API 邀请（响应method: "api"= 回退态，非失败）
用户偏好（通用建议）：给 3-5 个候选表格（名称/人气/在线/氛围一句话）让用户选；用户说「随机挑一个」用 random.choice；用户说「去过某个」就跳过继续推。
数据坑：
get_new_worlds的 favorites 是扫描时快照，会迅速过期——展示人气时对候选逐个get_world_name刷新（缓存命中快），别直接用扫描值visited标记可能不可靠：get_new_worlds {onlyUnvisited:true}仍可能返回逛过的世界——排除已逛世界时交叉核对get_world_name返回的note字段（逛过的世界常留了 note）- 主题化挑世界（睡觉/聊天/氛围等）：
search_worlds用日英关键词效果很好（如おやすみ/sleep）——主题关键词走 API 可靠（区别于中文世界名搜索的坑）
世界待逛列表（backlog）
用户说「把这张图加进待逛/待办」时走 3 工具：
add_to_backlog {worldId, reason?, priority?}— 加入待逛列表（本地待办，不动云端收藏；幂等，priority 0-2；世界不在 world_kb 时插兜底行）get_backlog {status? (pending|visited|all 默认 pending), sortBy? (added_at|priority|favorites 默认 added_at), limit?}— 查看待逛列表；逛完自动从未逛区消失（visited 后 pending 不再显示，记录保留在 visited 历史）remove_from_backlog {worldId}— 移出待逛列表（只清 backlog 标记，保留行，幂等）
2. 世界推荐 recommend_worlds
recommend_worlds：多源融合（本地新世界池 × PlanetVRC × 官方主题搜索 × 用户反馈）+ 本地状态感知（visited/sleep_ok/note）+ 可解释 reasons 数组 + 一键 open_world 闭环。
- 参数：
theme/excludeTheme/sources/excludeVisited - 评分模型：热度 + 新鲜度 + 主题 + 作者画像（30 天窗口熟客）
- 输出带
reasons（如熟悉度39 + 黄金区63% + group+3粒度） - 用户反馈工具：
rate_world {worldId, rating: 1|-1|0}（好图加权/烂图降权）、mark_world_visited {worldId}（事件驱动 visited 会漏记，开图闭环手动确认）、favorite_world {worldId, tag?}（云端收藏，tag 为worldsN/vrcPlusWorldsN动态分组，含 VRC+ 专属收藏夹，写操作需确认）、move_world_group {worldId, toGroup}（世界在收藏分组间移动）、update_favorite_group {group, displayName?}（重命名分组）、clear_favorite_group {group}（清空分组内收藏，destructive 需 confirm）
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 Changed · +4 lines 2aa199c41b2e
- 11d ago First seen · 148 lines · 20 tokens per session scan A 91486bc65a70
vrchat-world-queries is a skill published in the GitHub repository ggg123124/vrchat-assistant (21 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 4,137 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.
holix-sdd-propose
Create Spec-Driven Development changes (OpenSpec-style) — multi-project openspec, understanding gate, assigned tasks before coding.