Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gaojiongwenv587-beep/threads-skillsnpx agentmods add skills/gaojiongwenv587-beep/threads-skills/threads-filterWrote 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/gaojiongwenv587-beep/threads-skills/threads-filter)<a href="https://agentmods.dev/skills/gaojiongwenv587-beep/threads-skills/threads-filter"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-filter/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/gaojiongwenv587-beep/threads-skills/threads-filter"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-filter.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 | $0.00140 | $0.02446 |
| Opus 5 | $0.00070 | $0.01223 |
| Sonnet 5 | $0.00028 | $0.00489 |
| Haiku 4.5 | $0.00014 | $0.00245 |
Grade A, and why
threads-filter 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
threads-filter — 智能篩選 Skill
三源採集 → 存檔 →
filter-comment.py三維評分 → 輸出評論候選列表
評分邏輯是真正的 Python 代碼,不是提示詞估算。
篩選腳本位於:~/Desktop/threads-filter-comment/filter-comment.py
PHASE SETUP:首次配置向導
觸發條件:~/.threads-filter-comment.json 不存在,或用戶說「重新配置篩選」。
向導流程
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎯 threads-filter 首次配置向導
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Step 1/4:關鍵詞矩陣(keywords / priority_keywords)
Step 2/4:排除詞庫(exclude_keywords)
Step 3/4:AI 配置(api_url / api_key / model)
Step 4/4:確認並寫入
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Step 1 / 4 — 關鍵詞矩陣
請提供兩類關鍵詞:
🔑 高優先核心詞(命中即標記 high priority):
例:韓國、首爾、江南、釜山、韓國醫美、飛韓國
🏷️ 一般關鍵詞(命中標記 medium priority):
例:醫美、整形、微整、玻尿酸、保養、護膚、外貌焦慮
→ 儲存為 priority_keywords、keywords
Step 2 / 4 — 排除詞庫
哪些帖子要直接跳過?
預設已包含:醫院、診所、歡迎預約、歡迎諮詢、價格、優惠、促銷、line:、微信
需要補充同業競品名稱嗎?
→ 儲存為 exclude_keywords
Step 3 / 4 — AI 配置
是否啟用 AI 語境判斷?(預設:啟用)
如果啟用,請提供:
ai_api_url:(OpenAI 相容端點)
ai_api_key:
ai_model:(預設 Qwen/Qwen3.5-27B-FP8)
Step 4 / 4 — 寫入配置
配置寫入 ~/.threads-filter-comment.json:
{
"ai_enabled": true,
"ai_api_url": "https://...",
"ai_api_key": "sk-...",
"ai_model": "Qwen/Qwen3.5-27B-FP8",
"keywords": ["醫美", "整形", "保養", "護膚", "外貌焦慮"],
"exclude_keywords": ["診所", "歡迎預約", "促銷", "line:"],
"priority_keywords": ["韓國", "首爾", "江南", "釜山", "韓國醫美"]
}
使用方式
執行篩選(三源) → 「幫我篩選適合評論的帖子」
只用 Feed 篩選 → 「只抓首頁 Feed 篩選」
關閉 AI 快速篩選 → 「不用 AI,只做關鍵詞篩選」
指定帳號 → 「用 account2 篩選帖子」
重新配置 → 「重新配置篩選」
PHASE 1:三源採集 → 存至暫存文件
三個來源分別採集,存為獨立 JSON 文件,供 filter-comment.py 讀取。
ACCOUNT="default" # 或用戶指定帳號
TMPDIR="/tmp/threads-filter"
mkdir -p "$TMPDIR"
來源 A:首頁 Feed(50條)→ /tmp/threads-filter/feed.json
uv run python scripts/cli.py --account "$ACCOUNT" list-feeds --limit 50 \
> /tmp/threads-filter/feed.json
來源 B:關鍵詞搜索 → /tmp/threads-filter/keyword.json
讀取配置中 priority_keywords + keywords,逐一搜索(每個取最新 20 條),合併輸出:
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.
- 11d ago First seen · 294 lines · 140 tokens per session scan A 2832049191a1
threads-filter is a skill published in the GitHub repository gaojiongwenv587-beep/threads-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 2,446 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other skills, from other repositories
obscura
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
pinchtab-dev
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs. Triggers on "work on pinchtab", "pinchtab development", "contribute to pinchtab", "fix pinchtab bug", "add pinchtab feature".
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
browser_harness
../../SKILL.md.