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 5.5 | $0.00056 | $0.00978 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 4mo ago), licensed MIT. It adds 140 tokens to every session and 2,446 once invoked, about $0.0006 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 2026-08-31.
threads-filter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threads-filtergaojiongwenv587-beep/threads-skills | Skill | 5 | 4mo ago | MIT | A | 140 | Claude Code, Codex |
| obscurah4ckf0r0day/obscura | Skill | 30k | yesterday | Apache-2.0 | A | 100 | Claude Code, Codex |
| pinchtabpinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 94 | Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| pinchtab-devpinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 77 | Claude Code, Codex |
| pinchtab-stealth-scorepinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 168 | Claude Code, Codex |
| browser_harnessbrowser-use/browser-harness | Skill | 19k | yesterday | MIT | A | 0 | Claude Code |