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-batch-replyWrote 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-batch-reply)<a href="https://agentmods.dev/skills/gaojiongwenv587-beep/threads-skills/threads-batch-reply"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-batch-reply/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-batch-reply"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-batch-reply.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 | $0.00068 | $0.01626 |
| Opus 5.5 | $0.00027 | $0.00650 |
| Sonnet 5.5 | $0.00014 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
threads-batch-reply 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
threads-batch-reply — 批量回覆助手
透過 GUI 弹窗逐條填寫評論,自動執行 reply-thread,結果匯總回報。
🚫 內容禁區(最高優先級)
絕對禁止生成、分析或互動任何政治相關內容。遇到政治相關帖子直接跳過。
語言規則(強制)
所有 AI 生成的回覆內容一律使用繁體中文,不得使用简体中文。
工作流程
第一步:拉取目標帖子
# 從首頁 Feed 取帖
python scripts/cli.py list-feeds --limit 30
# 或按關鍵詞搜尋
python scripts/cli.py search --query "設計系統" --type recent --limit 20
第二步:篩選帖子,寫入臨時文件
從 CLI 輸出中取出目標帖子(按互動量、話題等篩選),寫成 JSON 文件:
import json, tempfile, pathlib
posts = [...] # 篩選後的帖子子集,格式同 CLI 輸出的 posts 陣列
tmp = pathlib.Path(tempfile.mktemp(suffix=".json", prefix="threads_batch_"))
tmp.write_text(json.dumps(posts, ensure_ascii=False), encoding="utf-8")
print(tmp) # 輸出臨時文件路徑供下一步使用
每條帖子需包含以下欄位(直接使用 CLI 輸出即可):
{
"postId": "DVxppvZCAAl",
"url": "https://www.threads.net/@user/post/DVxppvZCAAl",
"author": { "username": "someuser", "displayName": "顯示名稱" },
"content": "帖子正文",
"likeCount": "1,234",
"replyCount": "56"
}
第三步:啟動批量回覆助手
啟動前先確保 tkinter 可用(不可用則自動安裝):
python3 -c "import tkinter" 2>/dev/null || brew install [email protected]
GUI 可用時(有彈窗界面):
uv run python scripts/reply_assistant.py --posts-file /tmp/threads_batch_xxx.json
# 多帳號:
uv run python scripts/reply_assistant.py --posts-file /tmp/threads_batch_xxx.json --account myaccount
tkinter 不可用時(終端交互):
uv run python scripts/reply_assistant_cli.py --posts-file /tmp/threads_batch_xxx.json
# 多帳號:
uv run python scripts/reply_assistant_cli.py --posts-file /tmp/threads_batch_xxx.json --account myaccount
⚠️ 腳本路徑固定為
scripts/reply_assistant.py和scripts/reply_assistant_cli.py,不要去其他目錄找。
兩個版本的 --posts-file、--account、--port 參數完全相同,輸出的摘要 JSON 格式也一致。
第四步:讀取結果 JSON,匯報給用戶
腳本完成後向 stdout 輸出摘要:
{
"total": 10,
"replied": 3,
"skipped": 5,
"already_replied": 2,
"replied_ids": ["DVxppvZCAAl", "DVxHauYk1YQ", "DVxWF-hiayK"]
}
向用戶報告:成功回覆 N 條、跳過 M 條、已回覆過 K 條。
GUI 弹窗操作說明
┌──────────────────────────────────────────┐
│ 批量回覆 3 / 10 @bigbigburger1 │
├──────────────────────────────────────────┤
│ 帖子正文(可滾動) │
│ ❤️ 1,234 💬 56 │
├──────────────────────────────────────────┤
│ ┌────────────────────────────────────┐ │
│ │ 在此輸入評論... │ │
│ └────────────────────────────────────┘ │
│ 字符: 0 / 500 │
├──────────────────────────────────────────┤
│ [ 發布 ] [ 跳過 ] [ 結束 ] │
└──────────────────────────────────────────┘
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 · 176 lines · 68 tokens per session scan A 7fc9bcc3d1f1
threads-batch-reply is a skill published in the GitHub repository gaojiongwenv587-beep/threads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 1,626 once invoked, about $0.0003 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-batch-reply compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threads-batch-replygaojiongwenv587-beep/threads-skills | Skill | 5 | 4mo ago | MIT | A | 68 | 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 |
| browser_harnessbrowser-use/browser-harness | Skill | 19k | yesterday | MIT | A | 0 | Claude Code |
| agent-browser-clisleepinginsummer/agent-browser-cli | Skill | 646 | 5d ago | MIT | A | 32 | Claude Code, Codex |
| browser-use-terminalbrowser-use/terminal | Skill | 660 | 7d ago | MIT | A | 41 | Claude Code, Codex |