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-content-opsWrote 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-content-ops)<a href="https://agentmods.dev/skills/gaojiongwenv587-beep/threads-skills/threads-content-ops"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-content-ops/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-content-ops"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-content-ops.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 | $0.00087 | $0.01808 |
| Opus 5.5 | $0.00035 | $0.00723 |
| Sonnet 5.5 | $0.00017 | $0.00362 |
| Haiku 4.5 | $0.00009 | $0.00181 |
Grade A, and why
threads-content-ops 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
license: MIT-0 acceptLicenseTerms: true
threads-content-ops — 复合运营
通过组合基础命令完成复杂运营工作流。
🚫 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 生成的發文、回覆內容一律使用繁體中文撰寫,不得使用简体中文。
工作流示例
推廣型評論(定時任務場景)
"每 X 分鐘用 account2 在推薦頁抓帖子,篩選一條適合推廣醫美的帖子評論"
完整步驟:
# 第一步:確認賬號登入狀態
python scripts/cli.py --account account2 check-login
# 第二步:抓取首頁推薦帖子(15條足夠篩選,速度快)
python scripts/cli.py --account account2 list-feeds --limit 15
第三步:兩層篩選(規則優先,AI 只用一次)
⚠️ 禁止對每條帖子單獨調用 AI 判斷——50 條帖子 × 每次 5-10 秒 = 超時且浪費。 正確做法:先用關鍵詞規則瞬間篩出 1 條,再對這 1 條調用 AI 生成評論。
第一層:關鍵詞規則篩選(在內存中完成,零延遲)
按優先級從 posts 列表中找第一條命中的帖子:
優先級 1 — 韓國醫美場景(最匹配推廣目標):
韓國、首爾、江南、弘大、梨泰院、韓式、韓國診所、Olive Young、
皮膚科、整形、醫美、雷射、光療、玻尿酸、肉毒、微整、縮鼻、
隆鼻、雙眼皮、埋線、抗老、拉提
優先級 2 — 一般保養/外貌話題:
皮膚、保養、護膚、底妝、素顏、毛孔、痘痘、斑點、美白、
遮瑕、防曬、精華、面膜、卸妝、氣墊、變美、外貌
優先級 3 — 無命中時:選 likeCount 數值最大的帖子(曝光高)
跳過條件(直接從列表移除,不考慮):
- 政治相關
- 帖子含診所名稱、價格、電話(同業廣告)
- 已回覆過(
reply-thread自動防重,會返回skipped)
第二層:只對選出的 1 條帖子調用 AI 生成評論
根據帖子內容生成一條自然融入對話、不硬廣的繁體中文評論:
- 先呼應帖子內容 1 句(顯得真實),再帶出醫美相關話題 1 句
- 語氣:親切、口語,像真實用戶留言
- 長度:50–150 字符,避免過長顯得像廣告
- 絕對禁止:診所名稱、電話、價格、"私訊我"等硬廣詞彙
評論示例風格(根據帖子內容靈活調整,禁止直接照抄):
呼應帖子 + "最近也在研究醫美保養,皮膚狀態真的差很多"
呼應帖子 + "這讓我想到之前去做了一次光療,整個膚質改善超明顯"
呼應帖子 + "好有共鳴!我最近也開始注重抗老,微整形真的是現代人的新保養"
# 第五步:發布評論
python scripts/cli.py --account account2 reply-thread \
--url "https://www.threads.net/@user/post/xxx" \
--content "生成的評論內容"
執行後回報:
- 選中的帖子 URL 和作者
- 發布的評論內容
- 執行結果(success / skipped / error)
竞品分析
"分析 @competitor 最近 10 条帖子的互动情况"
python scripts/cli.py user-profile --username "@competitor" --limit 10
步骤:获取帖子列表 → 提取 likeCount / replyCount / repostCount → 汇总平均互动量、最高互动内容、发帖频率
热点追踪
"搜索 'AI' 最近的高互动帖子"
# 获取最新帖子
python scripts/cli.py search --query "AI" --type recent --limit 20
# 获取热门帖子
python scripts/cli.py search --query "AI" --limit 20
步骤:搜索帖子 → 按 likeCount 排序 → 提取热门内容和话题标签
内容创作
"根据最热的 5 条 AI 帖子,帮我写一条新 Thread"
步骤:
search --query "AI" --limit 20— 获取热帖- 分析热帖特征(长度、語氣、話題角度)
- 生成繁體中文新内容(≤ 500 字符)
fill-thread --content "..."— 预览- 等待用户确认后
click-publish
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 · 178 lines · 87 tokens per session scan A 2ead11ca63d4
threads-content-ops is a skill published in the GitHub repository gaojiongwenv587-beep/threads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,808 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-content-ops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threads-content-opsgaojiongwenv587-beep/threads-skills | Skill | 5 | 4mo ago | MIT | A | 87 | 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 |