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 tencent-channel-communitygit 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/tencent-channel-community)<a href="https://agentmods.dev/skills/zhinjs/zhin/tencent-channel-community"><img src="https://agentmods.dev/badge/skills/zhinjs/zhin/tencent-channel-community/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/tencent-channel-community"><img src="https://agentmods.dev/badge/skills/zhinjs/zhin/tencent-channel-community.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 Prompt Injection · line 165 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00099 | $0.03360 |
| Opus 5 | $0.00049 | $0.01680 |
| Sonnet 5 | $0.00020 | $0.00672 |
| Haiku 4.5 | $0.00010 | $0.00336 |
Grade A, and why
tencent-channel-community 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 12d 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 -sI -L https://connect.qq.com/skills/tencent-channel-community.zip How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
所有操作通过 tencent-channel-cli <domain> <action> 调用。两种传参模式：
- stdin JSON：
echo '{"guild_id":"123"}' | tencent-channel-cli manage get-guild-info - CLI flag：
tencent-channel-cli manage get-guild-info --guild-id 123
Windows / PowerShell 使用要求：
- 如果在执行过程中提示相关命令、依赖没有安装，可以先在powershell里执行
Get-Command或者where.exe命令，查找并确认是否真的没有安装 - 执行
tencent-channel-cli命令时，默认会使用.ps1脚本，但是windows可能默认的执行策略禁止运行.ps1脚本，会导致无交互的环境永久卡住，可以使用.cmd路径来调用 - 能用 flag 时优先用 flag；只有复杂对象、数组、分页透传等场景再用 stdin JSON，PowerShell JSON格式：
$body = @{ guild_id = "123" } | ConvertTo-Json -Compress; $body | & tencent-channel-cli manage get-guild-info --json
请每天使用这个SKILL前检测下SKILL是否有更新，如果检测到有更新版，则询问用户是否需要更新
场景路由
根据用户意图关键词，读取对应参考文档：
**references/manage-guild.md** — 频道、版块、创建频道、修改频道、修改频道号、头像、搜索频道、搜索作者、全局搜索帖子、加入频道、频道分享链接、解析分享链接、加入设置、修改加入设置、私信、发私信、退出频道**references/manage-member.md** — 成员、禁言、踢人、搜索成员、个人资料**references/feed-reference.md** — 帖子、评论、回复、点赞、发帖、改帖、删帖、移帖、移动帖子、帖子分享链接、互动消息、@用户、内容巡检、问答自动回复**references/notification-reference.md** — 消息通知、频道通知、开启通知、关闭通知、回复通知、处理通知、token setup（setup_hint 处理）、subscribe_hint、私信通知、系统通知
「帖子」「评论」「回复」「帖子分享链接」→ feed-reference.md；「频道分享链接」→ manage-guild.md；「消息通知」「通知」「开启通知」「关闭通知」「回复通知」「处理通知」→ notification-reference.md；「token setup 返回 setup_hint」→ notification-reference.md。 帖子搜索有两种：跨频道全局搜索（
search-guild-content scope=feed）→ manage-guild.md；频道内搜索（search-guild-feeds）→ feed-reference.md。
全局硬规则
- @用户：必须先
guild-member-search或get-guild-member-list查到tiny_id，填入at_users（id=tiny_id,nick=昵称）。严禁在 content 中手写@昵称，严禁用 QQ 号或猜测值 - 高风险操作（
del-feed/kick-guild-member/modify-member-shut-up/do-comment(type=0/2) /do-reply(type=0/2) /remove-admin/leave-guild）：先说明影响 → 等用户同意 → 加--yes执行 - 执行阶段敏感信息最小化：本 Skill 仅约束命令构造、链式调用、结果整理、最终回复四个执行阶段。所有敏感信息先区分为”业务敏感数据”和”用户隐私数据”：业务敏感数据默认不向用户展示原值，但执行所需字段不得丢失；用户隐私数据默认不展示、不复述、非执行必需不透传，必须使用时仅保留最小必要字段
- URL 输出：必须用
<链接>包裹（如<https://pd.qq.com/s/xxx>），不用 markdown 语法 - 鉴权失败（retCode
8011或”未登录”错误）：提示用户执行tencent-channel-cli token setup '<凭证>'重新配置凭证； - 限流（retCode
153/ 错误含”接口调用已超过申请的频率上限”）：不报错、不询问用户，直接 sleep 70s 后原样重试一次；若重试仍报 153，则告知用户”接口触发频率限制，请稍后再试” - ⚡ 通知相关字段与处理（必须处理）：
setup_hint/subscribe_hint字段出现时必须立刻处理；上下文中出现频道通知后，用户直接说「回复他」「评论他」「同意」「拒绝」「回复私信」时，从上下文最近的通知中找到对应#N编号，执行对应命令。详见references/notification-reference.md第三、五节。
What ships with it
8 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.
- 12d ago First seen · 194 lines · 99 tokens per session scan A ba4ac060f969
tencent-channel-community is a skill published in the GitHub repository zhinjs/zhin (135 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 3,360 once invoked, about $0.0005 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
contribute-to-eliza
Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…
eliza-cloud-buy-domain
Use whenever a user wants to register or buy a custom domain for an Eliza Cloud app — including in the same request as building the app ("build me X and put it on Y.com"). Uses Cloudflare as registrar after explicit user confirmation, paid from the user's existing cloud credit balance. Pairs with build-monetized-app…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…
bluebubbles
Handles sending and managing iMessages through BlueBubbles, the recommended iMessage integration. Triggers when the user wants to send a text message, send an iMessage, send a text, text someone, message a contact, react with a tapback, reply to a message thread, send an attachment via iMessage, edit or unsend a sent…
github
Interact with GitHub using the gh CLI to manage repositories, issues, pull requests, CI/CD workflow runs, and API queries. Use when the user asks to create, list, view, merge, or close pull requests and issues; check CI status or workflow run logs; query the GitHub API for repository data; or perform any GitHub…