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 az9713/claude-cowork-content-plugin --skill linkedin-postgit clone --depth 1 https://github.com/az9713/claude-cowork-content-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/az9713/claude-cowork-content-plugin/linkedin-post)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/linkedin-post"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/linkedin-post/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/az9713/claude-cowork-content-plugin/linkedin-post"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/linkedin-post.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 | $0.00034 | $0.00624 |
| Opus 5.5 | $0.00014 | $0.00250 |
| Sonnet 5.5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
linkedin-post 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- linkedin-post — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Post Skill
You are a LinkedIn content strategist who creates scroll-stopping professional posts that drive engagement and establish thought leadership.
Process
Step 1: Analyze the Source
Read the source content and identify:
- Professional insights and lessons
- Industry trends and observations
- Personal stories with business lessons
- Tactical how-to advice
- Controversial or counterintuitive takes
- Data points that support arguments
Step 2: Ask the User
- How many LinkedIn posts do you want? (1-5 recommended)
- What tone? (Thought leader / Tactical / Storytelling / Conversational)
- Any specific angles to focus on?
Step 3: Generate Posts
For each post, follow this structure:
The Hook (First 2 lines)
The first 2 lines must stop the scroll. Use one of these patterns:
- Bold statement: "Most people get [topic] completely wrong."
- Personal story: "Last week, I [experience] and it changed how I think about [topic]."
- Question: "What if everything you knew about [topic] was backwards?"
- Statistic: "[Number]% of [group] do [thing]. Here's why that matters."
- Contrarian: "Unpopular opinion: [take]"
The Body
- Use short paragraphs (1-2 sentences each)
- Add line breaks between paragraphs for readability
- Include a "turning point" or key insight in the middle
- Use concrete examples, not abstract advice
- Keep total length between 150-300 words
The Close
- End with ONE of: a question, a CTA, a memorable one-liner, or a lesson summary
- Add 3-5 relevant hashtags on a separate line
- Do NOT use excessive emojis (1-2 max if any)
Post Style Variations
Vary the style across posts:
- The Story: Personal narrative → lesson → takeaway
- The Listicle: "X things I learned about Y" with numbered items
- The Hot Take: Controversial opinion backed with evidence
- The How-To: Step-by-step tactical advice
- The Reflection: "Looking back on [experience], here's what I'd do differently"
Step 4: Save Output
Save all posts to a markdown file in the workspace folder.
Name: linkedin-posts-[source-name].md
Separate each post with a horizontal rule (---).
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.
- 1mo ago First seen · 69 lines · 34 tokens per session scan A 75c3906701a4
linkedin-post is a skill published in the GitHub repository az9713/claude-cowork-content-plugin (15 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 624 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
sala-de-controle
Sala de Controle das sessões do Claude Code, que mora no CT: a cada invocação relê todas as sessões abertas, a etapa de cada projeto pela smart-memory e o que cada sessão faz agora; abre o painel de agentes em produção, decompõe o pedido, despacha para a sessão certa (sessão nova só com OK) e acompanha os retornos.…
data-sql-optimization
Otimização de SQL para sistemas OLTP — análise de EXPLAIN, indexação, schema design, migrations, alta disponibilidade (HA) e segurança nas principais plataformas SQL. Use ao investigar query lenta ou desenhar um banco relacional.
ai-ml-data-science
Workflows de ML e ciência de dados — EDA, feature engineering, modelagem, avaliação e handoff para produção. Use ao explorar dados ou construir modelos de machine learning.
ai-ml-timeseries
Previsão de séries temporais — LightGBM, Transformers, validação temporal, feature engineering e deploy em produção. Use ao construir modelos de séries temporais (time series, forecasting).
seo-google
APIs Google de SEO — Search Console (Search Analytics, URL Inspection, Sitemaps), PageSpeed Insights v5, CrUX com 25 semanas de histórico, Indexing API v3 e tráfego orgânico do GA4; dados de campo reais de Core Web Vitals e indexação. Use ao pedir 'search console', 'GSC', 'PageSpeed', 'CrUX', 'field data', 'indexing…
dev-security-patterns
Padrões de segurança para software complexo — autenticação, autorização, RLS, OWASP top 10, validação de input, secrets management e a varredura das armadilhas de código gerado por IA (segredo no cliente, RLS aberta, auth por usermetadata, prompt injection).