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 zhinjs/zhin --skill qq-group-admingit clone --depth 1 https://github.com/zhinjs/zhinWrote 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/zhinjs/zhin/qq-group-admin)<a href="https://agentmods.dev/skills/zhinjs/zhin/qq-group-admin"><img src="https://agentmods.dev/badge/skills/zhinjs/zhin/qq-group-admin/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/zhinjs/zhin/qq-group-admin"><img src="https://agentmods.dev/badge/skills/zhinjs/zhin/qq-group-admin.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00378 |
| Opus 5.5 | $0.00014 | $0.00151 |
| Sonnet 5.5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
qq-group-admin 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 10d 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
qq-group-admin
Load only when the current group and target member are explicit. Every tool targets the current conversation; you cannot choose another group. Each tool re-checks your live role (bot_state) before acting.
Official limits (enforced by QQ, not by this skill): you must be group owner/admin; only ordinary members (not owner, admins or bots) can be removed or muted; mute is at most 30 days; recall works only within 2 minutes; member removal and join-request APIs are invite-only (11253 = no access).
group_kick and handle_join_request need a fresh human approval each time; show the target member and the reason. A previous approval never authorizes the next action. set_mute always needs approval.
Automatic moderation needs a confirmed rule and target group; never invent trigger conditions from permissions alone.
recall_member_message keeps the master/admin/trusted/owner requester permission without per-call approval and also works in guild channels (platform-enforced admin rights). To recall your own message, use qq-messages.
Not available on official bots: invite to group, leave group, special title, anonymous, announcement, essence, poke and group sign-in.
What ships with it
4 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.
- 10d ago Changed 325cac536aaa
- 14d ago First seen · 35 lines · 36 tokens per session scan A bee4d8249dd6
qq-group-admin is a skill published in the GitHub repository zhinjs/zhin (137 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 378 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-30.
qq-group-admin compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qq-group-adminzhinjs/zhin | Skill | 137 | today | MIT | A | 36 | Claude Code, Codex |
| Market Research BriefAgentEra/Agently | Skill | 1.7k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| Release Notes GeneratorAgentEra/Agently | Skill | 1.7k | yesterday | Apache-2.0 | A | 46 | Claude Code, Codex |
| discord-bot-architectfindscripter/everything-skills | Skill | 11 | today | none | A | 103 | Claude Code |
| article-writernetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 62 | Claude Code, Codex |
| skin-creatornetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| content-plannernetease-youdao/LobsterAI | Skill | 6.2k | yesterday | MIT | A | 63 | Claude Code, Codex |