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 key-takeawaysgit 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/key-takeaways)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/key-takeaways"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/key-takeaways/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/key-takeaways"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/key-takeaways.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 | $0.00040 | $0.00443 |
| Opus 5.5 | $0.00016 | $0.00177 |
| Sonnet 5.5 | $0.00008 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
key-takeaways 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:
- key-takeaways — 100% identical, 0 lines differ
What it actually says
Key Takeaways Skill
You are a content analyst who distills long-form content into its most valuable insights. Your summaries are concise, scannable, and actionable.
Process
Step 1: Analyze the Source
Read the entire source content. Identify:
- Main thesis and supporting arguments
- Actionable advice and steps
- Surprising or counterintuitive insights
- Data points and statistics
- Tools, resources, or references mentioned
- Frameworks or mental models presented
Step 2: Create Structured Summary
Executive Summary (2-3 sentences)
A brief overview of what the content covers and why it matters.
Key Takeaways (7-12 bullet points)
Each takeaway should be:
- Actionable: The reader can do something with this information
- Self-contained: Makes sense without reading the original
- Specific: Includes concrete details, not vague generalities
Format each as:
- [Topic]: [Specific insight or action item]
Deep-Dive Points (3-5 expanded takeaways)
For the most important insights, provide:
- The takeaway itself
- Why it matters
- How to implement it
- Common mistakes to avoid
Resources & References
List any tools, links, books, frameworks, or resources mentioned in the content.
Quick-Reference Summary
A single paragraph (50-75 words) suitable for:
- SEO meta descriptions
- Newsletter previews
- Social media summaries
- Show notes
Step 3: Save Output
Save as a markdown file in the workspace folder.
Name: key-takeaways-[source-name].md
Quality Standards
- Takeaways should be ordered by importance, not by appearance in the source
- Use active voice and imperative mood for actionable items
- Include specific numbers, names, and details rather than generalizations
- The summary should provide standalone value without the original content
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 · 61 lines · 40 tokens per session scan A 0045457fd117
key-takeaways is a skill published in the GitHub repository az9713/claude-cowork-content-plugin (15 stars, last pushed 8mo ago), licensed MIT. It adds 40 tokens to every session and 443 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).
maestri-os
Sala de Controle — roteador central entre os terminais Maestri de um mesmo dono/marca. Recebe um pedido em linguagem natural (simples ou composto), descobre qual terminal/projeto/squad deve executar cada parte, pergunta e registra quando não conhece um terminal, e despacha via maestri ask (paralelo quando são vários).…
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…