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-publishWrote 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-publish)<a href="https://agentmods.dev/skills/gaojiongwenv587-beep/threads-skills/threads-publish"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-publish/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-publish"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-publish.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 | $0.00056 | $0.00856 |
| Opus 5.5 | $0.00022 | $0.00342 |
| Sonnet 5.5 | $0.00011 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
threads-publish 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.
What it actually says
license: MIT-0 acceptLicenseTerms: true
threads-publish — 内容发布
发布 Thread 到 Threads.net，支持纯文字和图文。
🚫 內容禁區（最高優先級）
絕對禁止發布任何政治相關內容（政黨、選舉、兩岸、統獨、社會運動等），遇到此類需求直接拒絕。
語言規則（強制）
所有 AI 生成的發文內容一律使用繁體中文撰寫，不得使用简体中文。
Threads 内容规则
- 字符上限：500 字符（中英文均计 1 字符）
- 图片：最多 10 张，支持 JPG/PNG/GIF/WEBP，路径必须为绝对路径
分步发布（推荐）
用户可在浏览器中预览内容后再确认发布。
# 第一步：填写内容（打开撰写框，填入内容，不发布）
python scripts/cli.py fill-thread --content "今天天氣真好 ☀️"
# 含图片
python scripts/cli.py fill-thread \
--content "今天的風景" \
--images "/absolute/path/photo.jpg"
# 从文件读取长文本
python scripts/cli.py fill-thread --content-file /absolute/path/content.txt
# 第二步：用户在浏览器确认后，执行发布
python scripts/cli.py click-publish
注意：fill-thread 执行后不关闭浏览器标签页，click-publish 会复用该标签页完成发布。
一步发布
内容已确认、无需预览时使用：
python scripts/cli.py post-thread --content "Hello Threads！"
# 含图片
python scripts/cli.py post-thread \
--content "今天的照片" \
--images "/path/photo1.jpg" "/path/photo2.jpg"
实测返回示例
{ "status": "success", "message": "Thread 发布成功" }
{ "error": "内容长度 523 超过上限 500 字符" }
决策逻辑
- 用户提供内容 → 默认使用分步流程：先
fill-thread展示内容，询问用户确认后再click-publish - 用户明确说「直接发」/ 「一步发布」 → 使用
post-thread，无需再次确认 - 内容超过 500 字符 → 提示用户精简，或拆分为多条 Thread
- 含图片 URL（非本地路径） → 先用
image_downloader.py下载到本地再上传
失败处理
| 错误 | 原因 | 处理 |
|---|---|---|
| 未登录 | Cookie 失效 | 执行 threads-auth 登录流程 |
| 内容超长 | 超过 500 字符 | 精简内容后重试 |
| 找不到发布入口 | Threads 界面更新 | 检查 scripts/threads/selectors.py 中的选择器 |
| 上传图片失败 | 路径非绝对路径或文件不存在 | 确认路径正确，使用绝对路径 |
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 · 96 lines · 56 tokens per session scan A a507f5c5dd72
threads-publish is a skill published in the GitHub repository gaojiongwenv587-beep/threads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 856 once invoked, about $0.0002 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-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threads-publishgaojiongwenv587-beep/threads-skills | Skill | 5 | 4mo ago | MIT | A | 56 | 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 |