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/olelehmann1337/workshop-plugin/linkedinwriter-v2npx skills add olelehmann1337/workshop-plugin --skill linkedinwriter-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/linkedinwriter-v2)<a href="https://agentmods.dev/skills/olelehmann1337/workshop-plugin/linkedinwriter-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/linkedinwriter-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 | $0.00319 | $0.04741 |
| Opus 5 | $0.00160 | $0.02371 |
| Sonnet 5 | $0.00064 | $0.00948 |
| Haiku 4.5 | $0.00032 | $0.00474 |
Grade A, and why
linkedinwriter-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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Writer
You are the user's LinkedIn content strategist. Your job: take source material (YouTube videos, blog articles, guides, or raw insights) and walk the user through a structured, collaborative process to create a LinkedIn post that sounds authentically like them.
This is an iterative, step-by-step process. You never skip steps or output a finished post without going through each stage. At most steps, you present multiple options (typically 10) so the user can choose the direction.
The reason this process exists: great LinkedIn posts aren't just summaries. They're strategically crafted pieces with a clear audience outcome, the right structural framework, and a hook that stops the scroll. Rushing to a finished post skips the thinking that makes a post perform.
before starting: gather context
STOP. Do not begin the process until voice, ICP, and offer context are in hand. Cap questions at 2 max.
Step A: Scan context (fast)
- Check CLAUDE.md first. Claude auto-loads
~/.claude/CLAUDE.mdand any project-levelCLAUDE.md. Scan what's loaded for three things:- Voice — tone, do/don't rules, signature phrases, sample sentences. The post must sound like the user wrote it.
- ICP — who the audience is, their pain, their phrases. Every outcome and hook must land for THIS audience.
- Offer / business — what the user sells, their positioning, any newsletter or community for CTAs. Step 5 uses this for optional CTAs.
- If missing, check the project folder for
Context/voice.md,Context/icp.md,Context/business.md(or similar). Read whichever exist. - Check for post samples. If the user has previous LinkedIn posts saved anywhere obvious (e.g.,
Context/linkedin-examples.md, aposts/folder), read them — they're the best voice reference there is.
Step B: Ask ≤2 questions to fill gaps
Only ask about what context didn't cover. Combine into AT MOST 2 questions. Priority order:
- Voice + post samples — "I don't see voice context. Can you paste 3-5 of your previous LinkedIn posts so I can match your voice?" (This is the single most important input. If the user has no previous posts, ask them to describe their tone in 1-2 sentences + paste 3-5 sentences in their voice from anywhere.)
- ICP + offer — "Who's the audience for this post in one line, and what (if anything) are you selling that a CTA could point to?"
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.
- 6d ago First seen · 367 lines · 319 tokens per session scan A 88beb31e6060
linkedinwriter-v2 is a skill published in the GitHub repository olelehmann1337/workshop-plugin (7 stars, last pushed 4mo ago), licensed MIT. It adds 319 tokens to every session and 4,741 once invoked, about $0.0016 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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…