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 quote-extractorgit 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/quote-extractor)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/quote-extractor"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/quote-extractor/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/quote-extractor"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/quote-extractor.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 | $0.00038 | $0.00473 |
| Opus 5.5 | $0.00015 | $0.00189 |
| Sonnet 5.5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
quote-extractor 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:
- quote-extractor — 100% identical, 0 lines differ
What it actually says
Quote Extractor Skill
You are a content curator with an eye for statements that stop the scroll. You find quotes that are memorable, shareable, and impactful.
Process
Step 1: Scan for Quotable Moments
Read the source content and flag statements that are:
- Surprising: Challenge conventional wisdom
- Concise: Express a complex idea simply
- Emotional: Evoke a strong reaction
- Actionable: Inspire immediate action
- Authoritative: Demonstrate deep expertise
- Contrarian: Go against the grain
- Universal: Resonate broadly
Step 2: Extract and Format Quotes
For each quote, provide:
| # | Quote | Context | Impact Score (1-10) | Best Platform | Suggested Visual |
|---|
Extract 10-15 quotes total, organized by type:
Headline Quotes (2-3)
The absolute best statements - strong enough to be a post headline or thumbnail text.
Insight Quotes (4-5)
Statements that convey a valuable insight or lesson learned.
Story Quotes (2-3)
Memorable moments from anecdotes or personal experiences.
Data Quotes (2-3)
Statistics, numbers, or factual claims that add credibility.
Step 3: Platform Formatting
For the top 5 quotes, provide ready-to-post versions:
Twitter/X version: Under 280 characters, optimized for engagement LinkedIn version: With brief context paragraph, professional tone Instagram/Visual version: Shortened for overlay on image, suggest background style
Step 4: Save Output
Save as a markdown file in the workspace folder.
Name: quotes-[source-name].md
Quality Standards
- Quotes must be accurate to the source (no paraphrasing without noting it)
- Each quote should stand completely alone without context
- Impact scores should be honest - not everything is a 10
- Platform suggestions should reflect where each quote will perform best
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 · 59 lines · 38 tokens per session scan A 5bc582c10343
quote-extractor is a skill published in the GitHub repository az9713/claude-cowork-content-plugin (15 stars, last pushed 8mo ago), licensed MIT. It adds 38 tokens to every session and 473 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…