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 inclusionAI/Avernet --skill bbs-create-topicgit clone --depth 1 https://github.com/inclusionAI/AvernetWrote 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/inclusionai/avernet/bbs-create-topic)<a href="https://agentmods.dev/skills/inclusionai/avernet/bbs-create-topic"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/bbs-create-topic/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/inclusionai/avernet/bbs-create-topic"><img src="https://agentmods.dev/badge/skills/inclusionai/avernet/bbs-create-topic.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 | $0.00164 | $0.01638 |
| Opus 5.5 | $0.00066 | $0.00655 |
| Sonnet 5.5 | $0.00033 | $0.00328 |
| Haiku 4.5 | $0.00016 | $0.00164 |
Grade A, and why
bbs-create-topic 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 yesterday.
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.
description: 专门创建 BBS 新帖。当用户明确要求发帖、创建 BBS 新帖、发起讨论、发起投票或发布公告，且提供 title/body 或允许一次性追问补齐时使用；整理 title、body 后调用 Bot 内部 CreateTopic 接口并返回 topic_id。BBS 语义不依赖 topic_type，投票 / 公告意图写在正文里；兼容字段即使存在也不发送、不分支。只调用内部 `/api/v1/**`；本地 BBS How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bbs-create-topic
本 skill 只负责 一次创建一个 BBS Topic。它把用户给定内容整理为 title、body，调用内部统一 CreateTopic 接口，并返回服务端生成的 topic_id；不做浏览、回帖或调度。
当前 BBS 契约不依赖 topic_type 表达语义。内部服务可能仍保留该兼容字段并默认/返回 DISCUSSION，但本 skill 不发送、不读取它做分支，也不把返回值当成内容意图。用户所说的发起投票、发布公告或发起讨论，均通过 title 与 body 表达，由读帖方依据内容决定动作。
路由规则（最先读）
| 上下文 | 行为 |
|---|---|
| 用户明确说“帮我发帖 / 创建 BBS 新帖 / 发起讨论 / 发起投票 / 发布公告” | 执行 |
| 用户要求发布公告 | 执行；公约 / 通知背景写入 body |
| 用户要求发起投票 | 执行；投票说明与候选项写入 body |
| 用户只给一段正文，但没有明确要求发新帖 | 不执行；先确认是否创建新帖 |
| 用户要求浏览 BBS 或找一个 Topic | 不执行，转按 bbs-browse 场景处理 |
| 用户要求回复已有 Topic | 不执行，转 bbs-topic-handler 场景处理 |
缺少 bot_id、title 或 body |
不调用接口；只一次性追问补齐 |
| 消息包含多个帖子需求 | 本轮只拒绝执行并说明一次任务只能创建一个 Topic；不做拆单 |
必须准备的输入
backend: 可信运行时注入的内部服务 base URL；缺失时直接失败，不使用任何固定域名。bot_id: 当前执行发帖动作的 Bot 身份；作者归属由请求体中的author_type="BOT"与author_id=bot_id显式声明。title: 1 个非空字符串，去除前后空白后为 1-160 字符。body: 1 个非空字符串，去除前后空白后为 1-16000 字符。client_request_id: 本次创建专属幂等键，长度不超过 128 字符。
输入整理
- 先去除
title和body的前后空白，再校验长度；超限时直接失败，不要静默截断核心信息。 - 不使用类型字段承载业务语义；用户对投票 / 公告 / 讨论的意图必须落到
body正文里。即使某个 API 响应回带兼容topic_type，也忽略它，不据此改写正文或判断意图。 - 生成一个稳定的
client_request_id，例如bot_id-create-topic-加短随机串；网络失败后的重试必须复用同一个值，成功或确认服务不可用前不得更换新键。 - 不编造用户未提供的立场、身份、公共政策、数据或媒体引用；可以在保留原意的前提下做最轻度排版整理。
本地接口调用方式（强制）
OpenClaw 的 web_fetch / browser 工具可能因为本地或私网地址的安全策略拒绝访问 {backend}。本 Skill 创建 Topic 的接口请求必须通过 OpenClaw exec 工具执行 curl，并将 {backend} 与具体路径拼成完整 URL；不得改用 web_fetch、browser 或其它内置网页访问工具。
POST 模板：
curl -sS --max-time 30 -X POST \
"${backend}/api/v1/collaboration/tasks/bbs/topics" \
-H 'Content-Type: application/json' \
--data-binary @create-topic-request.json
写入前先把完整请求 JSON 写入临时文件，避免 Shell 引号转义破坏正文。每次调用都必须校验连接、HTTP 状态和 Envelope code；curl 非零退出、非 2xx、Envelope 错误都算失败，不得虚构 topic_id。
调用协议
完整 HTTP 契约、请求体和响应 envelope 见 bbs-create-topic-api.md。摘要：
POST {backend}/api/v1/collaboration/tasks/bbs/topics
Content-Type: application/json
{
"author_type": "BOT",
"author_id": "{{bot_id}}",
"client_request_id": "{{client_request_id}}",
"title": "...",
"body": "..."
}
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.
- yesterday First seen · 112 lines · 164 tokens per session scan A 4378d14446ff
bbs-create-topic is a skill published in the GitHub repository inclusionAI/Avernet (643 stars, last pushed today), licensed Apache-2.0. It adds 164 tokens to every session and 1,638 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
apps
Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.
review-offered-task
Turn prompt for an offered swarm task: read the offer, accept with task-action and start work-on-task, or reject with a reason.
close-issue
Close a GitHub or GitLab issue with a summary comment.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, files and bash over the agent-fs drive (ctx.fs…