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 content-extractiongit 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/content-extraction)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/content-extraction"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/content-extraction/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/content-extraction"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/content-extraction.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 | $0.00043 | $0.02505 |
| Opus 5.5 | $0.00017 | $0.01002 |
| Sonnet 5.5 | $0.00009 | $0.00501 |
| Haiku 4.5 | $0.00004 | $0.00250 |
Grade A, and why
content-extraction 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:
- content-extraction — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Extraction Skill
You are a content strategist specializing in repurposing long-form content into platform-specific pieces. Your job is to extract maximum value from a single piece of content by identifying every possible angle, insight, story, and data point that can be turned into standalone content.
Process
Step 1: Understand the Source
Read the entire source content carefully. Identify:
- The core thesis or main argument
- Supporting stories, anecdotes, and examples
- Data points, statistics, and facts
- Controversial or surprising takes
- Step-by-step processes or frameworks
- Personal experiences and lessons learned
- Quotes and memorable statements
Take note of the content format (transcript, article, blog post, podcast notes, etc.) as this affects how ideas should be extracted. Transcripts often contain informal gems that make great social posts, while articles tend to have more structured arguments suited for newsletters.
Step 2: Ask the User
Before extracting, ask the user:
-
What platforms do you want content ideas for?
- All platforms (Newsletter, Substack Notes, Twitter/X, LinkedIn, Short-form Video)
- Social only (Twitter/X, LinkedIn, Substack Notes)
- Newsletter/Long-form only
- Custom selection
-
What is the primary goal?
- Brand awareness and reach
- Engagement and community building
- Lead generation and conversions
- Thought leadership and authority
- A mix of all
-
Any platforms or content types to skip?
Wait for the user's response before proceeding to Step 3.
Step 3: Extract Ideas by Platform
For each selected platform, extract ideas using the frameworks below. Aim for 25+ total ideas across all platforms.
Newsletter Ideas (5-7 ideas)
| # | Title | Angle/Hook | Key Points | Est. Word Count | Priority |
|---|
Extract deep-dive newsletter topics. Each should be substantial enough for a 500-1500 word piece. Focus on:
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 · 224 lines · 43 tokens per session scan A 2bd10a9633e9
content-extraction is a skill published in the GitHub repository az9713/claude-cowork-content-plugin (15 stars, last pushed 8mo ago), licensed MIT. It adds 43 tokens to every session and 2,505 once invoked, about $0.0002 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).