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 friend-removalsgit 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/friend-removals)<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/friend-removals"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/friend-removals/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/friend-removals"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/friend-removals.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 | $0.00000 | $0.00482 |
| Opus 5.5 | $0.00000 | $0.00193 |
| Sonnet 5.5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
friend-removals 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 1mo 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.
What it actually says
friend-removals 插件 — 谁把我删了
触发场景：用户问「谁删除我了」「XX 是不是把我删了」「有谁把我从好友列表移除了」。
机制
VRChat 对方解除与你的好友关系时，你的 WebSocket 会收到 friend-delete 事件，核心事件流实时落库 events 表（type='friend-delete'），并把该好友自动移出本地 friends 表。该事件是「对方主动删你」的信号，不是你自己删人（主动删人走 remove_friend 工具，无此事件）。
工具
| 工具 | 说明 |
|---|---|
get_friend_removals |
列出历史上把你删掉的人与解除时间。userId 省略=全部；days=只看最近 N 天；limit/offset 分页。每条含 userId/displayName（尽力回填其最后使用名）/nickname（本地昵称）/createdAt（解除时刻 UTC） |
使用示例
「谁删除我了？」 → get_friend_removals()
「最近一周谁删了我？」 → get_friend_removals({ days: 7 })
「云白雪浅° 什么时候删的」→ get_friend_removals({ userId: "usr_..." })（也可先 search_users 解析名字）
注意事项
- 显示名回填：friend-delete 事件本身不带对方名字（解除后 VRChat 不再下发），插件经
get_friend_events回溯该 userId 历史最近一次带名事件；若全程匿名则displayName为空串，需结合 userId 判断。 - 数据源口径：仅记录本服务上线期间收到的 friend-delete；本服务未运行时对方删除无法捕获（WS 未连接）。
- 依赖核心
get_recent_events的 SQL 层类型过滤（2026-09-06 修复），早期版本该工具查不到 friend-delete 历史。
What ships with it
2 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.
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.
- 1mo ago First seen · 28 lines · 0 tokens per session scan A 6d442ac32b48
friend-removals is a skill published in the GitHub repository ggg123124/vrchat-assistant (26 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 482 tokens. 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 2026-09-06.
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).