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-exploreWrote 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-explore)<a href="https://agentmods.dev/skills/gaojiongwenv587-beep/threads-skills/threads-explore"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-explore/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-explore"><img src="https://agentmods.dev/badge/skills/gaojiongwenv587-beep/threads-skills/threads-explore.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 | $0.01178 |
| Opus 5.5 | $0.00035 | $0.00471 |
| Sonnet 5.5 | $0.00017 | $0.00236 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
threads-explore 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
license: MIT-0 acceptLicenseTerms: true
threads-explore — 内容发现
浏览首页 Feed、搜索内容、查看帖子详情和用户主页。
命令
首页 Feed
python scripts/cli.py list-feeds
python scripts/cli.py list-feeds --limit 30
实测返回示例:
{
"posts": [
{
"author": { "username": "user1", "displayName": "User One", "isVerified": false },
"content": "帖子正文内容",
"likeCount": "3,819",
"replyCount": "42",
"repostCount": "8",
"quoteCount": "",
"createdAt": "2025-03-10T12:34:56",
"url": "https://www.threads.net/@user1/post/xxx"
}
]
}
说明:
createdAt优先返回 ISO 时间戳,DOM 解析时可能返回相对时间(如 "3小时")likeCount为 Threads 显示格式(含逗号分隔)postId在首页 Feed 中可能为空,使用url传给互动命令- 批量抓取:
--limit 50会自动滚动多次直到凑满,耗时约 1-3 分钟;连续 3 次无新帖自动停止 - 定时任务:
list-feeds每次结果高度重叠(For You 算法池稳定);若需增量抓新帖,改用search --query 关键词 --type recent
搜索
# 默认搜索(热门内容)
python scripts/cli.py search --query "AI"
# 最近发布的帖子
python scripts/cli.py search --query "Python" --type recent
# 只搜用户
python scripts/cli.py search --query "tech" --type profiles
# 限制结果数
python scripts/cli.py search --query "設計" --limit 10
--type 可选值:all(默认热门)、recent(最新)、profiles(用户)
帖子详情
python scripts/cli.py get-thread --url "https://www.threads.net/@user/post/xxx"
返回帖子原文 + 回复列表。
用户主页
python scripts/cli.py user-profile --username "@someuser"
python scripts/cli.py user-profile --username "someuser" # @ 可选
python scripts/cli.py user-profile --username "someuser" --limit 20
返回用户基本信息(粉丝数、简介)和最近帖子列表。
用户历史回复
python scripts/cli.py user-replies --username "@someuser"
python scripts/cli.py user-replies --username "someuser" --limit 30
抓取 /@用户名/replies Tab 的历史回复列表,字段与 user-profile 帖子相同。
决策逻辑
- 用户说"首页" / "刷一下" / "看看推荐" →
list-feeds - 用户提供关键词说"搜索" →
search --query 关键词,热门用默认,最新加--type recent,找人加--type profiles - 用户提供 Thread URL →
get-thread --url URL - 用户提供用户名 →
user-profile --username 用户名 - 用户说"历史回复" / "回复记录" / 用户名 + "回复" →
user-replies --username 用户名
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 · 127 lines · 87 tokens per session scan A c19c1478cf22
threads-explore 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 1,178 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-explore compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| threads-exploregaojiongwenv587-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 |
| 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 |