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 binggandata/bggg-skills --skill bggg-tiktok-searchgit clone --depth 1 https://github.com/binggandata/bggg-skillsWrote 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/binggandata/bggg-skills/bggg-tiktok-search)<a href="https://agentmods.dev/skills/binggandata/bggg-skills/bggg-tiktok-search"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/bggg-tiktok-search/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/binggandata/bggg-skills/bggg-tiktok-search"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/bggg-tiktok-search.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 Data Exfiltration · line 30 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 | $0.00141 | $0.02205 |
| Opus 5 | $0.00071 | $0.01103 |
| Sonnet 5 | $0.00028 | $0.00441 |
| Haiku 4.5 | $0.00014 | $0.00220 |
Grade A, and why
bggg-tiktok-search scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$WEBBRIDGE_URL/status" How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BGGG TikTok Search
目标
用用户本地真实 Chrome 的 TikTok 登录态完成内容调研、博主搜索、视频采样、主页采集和截图留证。默认只读取公开或用户可见页面,不做点赞、关注、评论、私信、发布或账号设置修改。
前置条件
任选一种控制路径:
- WebBridge:本地 WebBridge daemon 和浏览器扩展可用。
- Chrome/CDP:用户自己启动带 remote debugging 的 Chrome,脚本通过 Playwright 连接。
- Apple Events:macOS Chrome 开启
View > Developer > Allow JavaScript from Apple Events后使用scripts/tk_real_chrome.py。 - 手动辅助:当登录、验证码、地区弹窗或风控出现时,让用户在真实 Chrome 里处理后继续。
WebBridge 健康检查:
WEBBRIDGE_URL="${WEBBRIDGE_URL:-http://127.0.0.1:10086}"
curl -s "$WEBBRIDGE_URL/status"
CDP 健康检查:
python3 <skill-dir>/scripts/tk_research.py check-cdp
工作流
- 判断任务类型:
- 关键词找视频 →
search - 关键词找博主 →
authors - 已有博主主页 →
creator - 用户已经把 Chrome 打到目标页 →
current
- 关键词找视频 →
- 操作 Chrome:
navigate打开 TikTok 搜索页/博主页。fill输入搜索词,click触发搜索。snapshot读取页面内容,定位视频卡片。evaluate提取结构化数据(URL、作者、标题、互动数)。- 截图留证,避免把 base64 截图直接贴进上下文。
- 滚动加载更多,重复提取。
- 结果保存:
- 结构化数据写入
collected_items.json。 - 截图保存到
screenshots/。 - 生成
research_notes.md做业务蒸馏。
- 结构化数据写入
- 后续衔接:
- 要下载视频 → 交给
bggg-tiktok-downloader - 要分析视频 → 交给
bggg-tiktok-readvideo
- 要下载视频 → 交给
WebBridge 操作示例
1. 打开 TikTok 并搜索关键词
# 打开 TikTok 首页(新标签页,session 隔离)
curl -s -X POST "$WEBBRIDGE_URL/command" \
-H 'Content-Type: application/json' \
-d '{"action":"navigate","args":{"url":"https://www.tiktok.com","newTab":true,"group_title":"TikTok Research"},"session":"tiktok-search"}'
# 获取页面 snapshot,找到搜索框的 @e ref
curl -s -X POST "$WEBBRIDGE_URL/command" \
-d '{"action":"snapshot","session":"tiktok-search"}'
# 在搜索框填入关键词(用 @e ref 或 CSS selector)
curl -s -X POST "$WEBBRIDGE_URL/command" \
-d '{"action":"fill","args":{"selector":"input[type=search]","value":"skincare routine"},"session":"tiktok-search"}'
# 点击搜索按钮或按回车
curl -s -X POST "$WEBBRIDGE_URL/command" \
-d '{"action":"click","args":{"selector":"button[type=submit]"},"session":"tiktok-search"}'
2. 提取视频卡片数据
# 用 evaluate 提取视频列表的结构化数据
curl -s -X POST "$WEBBRIDGE_URL/command" \
-d '{"action":"evaluate","args":{"code":"(() => { const cards = [...document.querySelectorAll(\"[data-e2e=search-card-video]\")].slice(0, 10); return cards.map((c, i) => { const link = c.querySelector(\"a\"); const author = c.querySelector(\"[data-e2e=search-card-user-avatar]\"); const metrics = [...c.querySelectorAll(\"[data-e2e=video-views]\")]; return { index: i, url: link ? link.href : null, title: c.innerText.slice(0, 200), author: author ? author.getAttribute(\"href\") : null, raw_text: c.innerText.slice(0, 500) }; }); })()"},"session":"tiktok-search"}'
What ships with it
9 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 · 182 lines · 141 tokens per session scan A 33c15b01e533
bggg-tiktok-search is a skill published in the GitHub repository binggandata/bggg-skills (594 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 2,205 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…