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 skills add olelehmann1337/workshop-plugin --skill longformtweets-workshop-v2git clone --depth 1 https://github.com/olelehmann1337/workshop-pluginWrote 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/olelehmann1337/workshop-plugin/longformtweets-workshop-v2)<a href="https://agentmods.dev/skills/olelehmann1337/workshop-plugin/longformtweets-workshop-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/longformtweets-workshop-v2.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 5.1 | $0.00102 | $0.05851 |
| Opus 5 | $0.00051 | $0.02926 |
| Sonnet 5 | $0.00020 | $0.01170 |
| Haiku 4.5 | $0.00010 | $0.00585 |
Grade A, and why
longformtweets-workshop-v2 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 6d 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral Long-Form Tweets
Most long-form tweets die because they read like LinkedIn posts pasted into Twitter. Stiff paragraphs, corporate rhythm, and that unmistakable AI smell where every section follows the same beat.
The posts that actually break through sound like someone thinking out loud. A genuine opinion, some mess around the edges, and a structure that pulls you down the page without you noticing.
This skill captures 9 structural patterns from creators who consistently crack 100k+ views on long-form posts — and delivers them in writing that sounds like a real person typed it.
the core job
Produce a single long-form tweet (500-3000 characters) that:
- Follows a proven structural pattern from high-performing creators
- Sounds human — conversational, direct, no corporate rhythm
- Carries a genuine point of view (not a restatement of common wisdom)
- Applies anti-AI-slop rules automatically
Output: One ready-to-post tweet + pattern label + char count.
before starting: gather context
STOP. Do not write a tweet until context is in hand AND the brief is clear. Cap questions at 2 max.
Step A: Gather context (fast)
- Check CLAUDE.md first. Claude auto-loads
~/.claude/CLAUDE.mdand any project-levelCLAUDE.md. Scan for:- Business — what the user sells, public proof/numbers. Grounds the tweet in real stakes.
- ICP — who the reader is, their language. The tweet must land for THIS audience.
- Voice — tone, do/don't, sample sentences. Voice shows up faster in tight formats.
- If missing, check the project folder for
Context/business.md,Context/icp.md,Context/voice.md. Read whichever exist.
Step B: Confirm the brief (≤2 questions, combined)
Skip anything context already covers. Combine related fields into at most 2 questions:
- Topic + angle — "What's the post about, and what's the actual take?" (The opinion IS the content — "AI is changing things" is not an angle, "AI agents will make 80% of SaaS tools obsolete within 3 years" is.)
- Style + goal — "Which pattern family (strategic, cultural/philosophical, raw builder update) and what's the goal (engagement, drive to product, authority, just share)?"
What ships with it
4 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.
- 6d ago First seen · 503 lines · 102 tokens per session scan A 50ad450832f7
longformtweets-workshop-v2 is a skill published in the GitHub repository olelehmann1337/workshop-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 5,851 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…