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-social-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-social-queries)<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/vrchat-social-queries"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/vrchat-social-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-social-queries"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/vrchat-social-queries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 53 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.
- medium Data Exfiltration · line 81 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 | $0.04909 |
| Opus 5 | $0.00010 | $0.02455 |
| Sonnet 5 | $0.00004 | $0.00982 |
| Haiku 4.5 | $0.00002 | $0.00491 |
Grade A, and why
vrchat-social-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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8799/mcp -X POST \ How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VRChat 好友/社交域 — 查询工作流与写操作
本 skill 覆盖 vrc-monitor 的好友/社交域：在线列表、同房/同屏、上线规律、常玩统计、社交画像、关系分析、昵称管理，以及全部社交写操作（boop / 上传 / 邀请 / 开房 / 好友管理）。
⚠️ 工具表唯一权威在 vrc-monitor-agent skill（全部 MCP 工具及参数）。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（
data:前缀、MCP 入参格式）见 vrc-monitor-agent「常见陷阱」。 MCP 端点：http://127.0.0.1:8799/mcp；服务未启动处理见 vrc-monitor-agent「服务健康检查」。
1. 好友在线列表
用户问"现在有哪些好友在线 / XX 在线吗"时，直接调 get_online_friends，一条调用拿全要素：昵称（有本地昵称用昵称）｜所在世界｜房间类型｜在线时长｜房间停留时长。
返回的每条好友记录含：
| 字段 | 说明 |
|---|---|
nickname |
本地昵称（null = 无；展示用 nickname || displayName） |
locationParsed |
结构化房型：worldId/instanceId/type（public/hidden/friends/group/private/local）/ownerId/region |
worldName |
世界名（缓存优先，未缓存自动批量 API 查询并写 world_cache；查询失败/private 为 null） |
onlineMinutes / onlineSince |
本次在线时长：会话起点 = 最近 friend-offline 之后最早的一条 friend-online（WS 重连会重复推送 friend-online，取最新会严重低估，MIN(>last_off) 跳过重复推送）；无 offline 记录 = 取最早 friend-online |
durationMinutes / enteredAt |
房间停留时长：进入时间 = max(会话起点, 最新位置事件时间)（防跨会话污染）；null = 未知（traveling/无匹配事件） |
展示紧凑表格（五列）：| 好友 | 世界 | 房型 | 在线 | 停留 |；房型中文图标 🌐公开/🤫隐藏/👥好友房/🏷️群组房/🔒私密/💻本地；同房好友（完整 location 相同）额外高亮。⚠️ private 房停留时长可算但语义是"位置隐藏前最后一次更新"，参考价值低。
2. "XX 现在和谁一起？" / 同实例好友
1. get_friend_info(userId=目标) → 取 location 字段（如 "wrld_xxx:77182~hidden(usr_owner)~region(jp)"）
2. get_online_friends() → 所有在线好友的位置
3. 按完整 location 字符串匹配 → 同实例的好友
4. 从 location 解析 owner：hidden(usr_xxx)/private(usr_xxx)/friends(usr_xxx)/group(grp_xxx)
5. get_world_name(worldId) → 世界名（location.split(':')[0]）
- 只能看到你也是好友的人（API 限制）
~hidden(usr_A)= A 的隐藏房；~private(usr_B)= B 的私密房；~friends(usr_C)= C 的好友房- 直接读
get_online_friends返回的locationParsed字段即可（type/ownerId/worldId/instanceId/region 已结构化），不需要手写解析
3. "今天和谁一起玩了？" / 同屏交叉查询 → get_companions
⚠️ 不要委派子 agent 做同屏查询——子 agent 只会查少量已知 userId，会漏掉其他人。直接用 MCP 工具：
curl -s http://127.0.0.1:8799/mcp -X POST \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_companions","arguments":{"startTime":"<UTC起>","endTime":"<UTC止>","userId":"<目标userId，可省略=当前账号>"}}}'
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 Changed · +10 lines c24914efe11c
- 11d ago First seen · 199 lines · 20 tokens per session scan A da88c166e8dd
vrchat-social-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 4,909 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
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.
holix-cron
Schedule recurring agent tasks via Holix built-in gateway cron (not crontab or custom scripts).