Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/sergebulaev/threads-skills/threads-hook-extractornpx skills add sergebulaev/threads-skills --skill threads-hook-extractorgit clone --depth 1 https://github.com/sergebulaev/threads-skillsWrote 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/sergebulaev/threads-skills/threads-hook-extractor)<a href="https://agentmods.dev/skills/sergebulaev/threads-skills/threads-hook-extractor"><img src="https://agentmods.dev/badge/skills/sergebulaev/threads-skills/threads-hook-extractor.svg" alt="Measured on agentmods" 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 | $0.00116 | $0.00951 |
| Opus 5 | $0.00058 | $0.00476 |
| Sonnet 5 | $0.00023 | $0.00190 |
| Haiku 4.5 | $0.00012 | $0.00095 |
Grade A, and why
threads-hook-extractor 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threads Hook Extractor
Paste a viral Threads post or thread URL. Get back: which hook formula it uses, the exact structure, why it worked, and a blank template you can fill with your own voice.
When to use
- User finds a viral post or thread they want to study
- User wants to replicate a specific creator's pattern
- Before
threads-post-writer, to seed a draft with a proven shape
Input
A Threads post or thread URL (threads.net or threads.com, /@handle/post/).
For a thread, the URL of the first post is best.
Output
- Formula identified (T1-T10 from
../../references/hook-formulas.md) with a confidence score - Container: single post vs thread, and why that container fit the idea
- Structural breakdown:
- The hook line (and for a thread, how post 1 opens the loop)
- Body architecture (per-post roles for a thread)
- The close (what earns the repost or the reply)
- Reaction-triggering devices (numbers, named entities, the open loop, the warm invite)
- Primary goal the original chased (replies / reposts / likes / quotes)
- Why it worked psychologically and algorithmically
- Blank template with
{slot}markers matched to the original, ready for the user's topic - Cautions: anything in the original that would fail a 2026 audit (em dashes, AI vocab, 2+ hashtags, link in post 1, a cold X tone)
Steps
- Parse the URL.
lib.url_parser.parse_threads_url(url)returnshandle,post_id,url_type. - Get the text. This bundle has no built-in post reader, so ask the user to paste the post or the full thread text. (If they later wire an Apify post-read actor, read it automatically.)
- Detect the container. One self-contained post, or a multi-post thread.
- Classify against the 13 formulas using features:
- Single post: a warm contrarian claim (T1)? one hard number (T2)? a personal metric/confession (T3)? a quote post adding a layer (T4)? a one-line-per-item list (T5)? a relatable shared moment (T6)?
- Thread: a numbered teaching promise (T7)? a story starting at the tension (T8)? a surprising result with the mechanism withheld (T9)? a first-person "how I" teardown (T10)?
- Score confidence. If two formulas fit, return the top 2 with fit scores.
- Extract structure. Label each part by its role. For a thread, map post 1 (the loop), the front-loaded payoff, the body beats, and the closer.
- Name the primary goal the original optimized for.
- Generate a blank template with
{slot}markers matched to the original shape and the user's topic. - Audit the source. Flag any AI tells in the original so the user does not copy them.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 84 lines · 116 tokens per session scan A d2f50f81d36d
threads-hook-extractor is a skill published in the GitHub repository sergebulaev/threads-skills (20 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 951 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
x-marketing
Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…
x-humanizer
Scrub AI tells from any tweet or thread draft, or audit a finished draft against the 2026 X (Twitter) checklist. Strips em dashes, AI vocabulary (leverage, fundamentally, delve, harness), rule-of-three lists, and uniform tweet rhythm, then adds human fingerprints. Includes a --mode audit pre-publish check (280-char…
facebook-marketing
Plan, draft, audit, and publish posts for a Facebook Page. Use when the user wants to write a short punchy Page post or a longer story post, remove AI tells from a draft, reverse-engineer the hook from a high-share Page post, draft replies to comments on their Page, or plan a week of Facebook Page content. Page posts…
fb-humanizer
Scrub AI tells from any Facebook Page post draft, or audit a finished draft against the 2026 Facebook checklist. Strips em dashes, AI vocabulary (leverage, delve, harness), "We are thrilled to announce" openers, and corporate auto-pilot, then adds human fingerprints. Includes a --mode audit pre-publish check (under-80…
tiktok-marketing
Plan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound…
x-post-writer
Draft a single tweet or short auto-thread for X (Twitter) using a 2026 X hook formula (one-liner contrarian, data-point, build-in-public, mini-list, relatable cold-open), picked by goal (replies, reposts, likes, bookmarks). Respects the 280-char limit (25,000 on Premium), runs the humanizer pass, and publishes via…