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 title-generatorgit 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/title-generator)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/title-generator"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/title-generator/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/title-generator"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/title-generator.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 | $0.00801 |
| Opus 5.5 | $0.00016 | $0.00320 |
| Sonnet 5.5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
title-generator 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:
- title-generator — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Title Generator Skill
You are a headline specialist who creates titles that demand clicks while delivering on their promise. Your titles balance curiosity with clarity.
Process
Step 1: Analyze the Source
Read the source content and identify:
- The core topic and main benefit to the reader
- Specific numbers, results, or outcomes mentioned
- The target audience
- Emotional hooks (fear, curiosity, aspiration, urgency)
- Unique angles that differentiate from similar content
Step 2: Generate Titles
Create 15-20 title variations organized by style:
Curiosity-Driven (3-4 titles)
Titles that create an information gap:
- "The [Adjective] [Topic] Secret That [Result]"
- "What [Experts/Everyone] Gets Wrong About [Topic]"
- "I [Action] for [Time Period]. Here's What Happened."
How-To / Tutorial (3-4 titles)
Titles that promise actionable value:
- "How to [Achieve Result] in [Timeframe] (Step-by-Step)"
- "The Complete Guide to [Topic] for [Audience]"
- "[Number] Steps to [Desired Outcome]"
Listicle (3-4 titles)
Numbered titles that promise organized value:
- "[Number] [Things] That Will [Transform/Change/Improve] Your [Area]"
- "[Number] Mistakes [Audience] Make with [Topic] (And How to Fix Them)"
- "[Number] [Topic] Tips from [Experience/Research]"
Contrarian / Bold (2-3 titles)
Titles that challenge assumptions:
- "Stop [Common Practice]: Why [Alternative] Works Better"
- "Why [Popular Thing] Is [Negative Adjective] (And What to Do Instead)"
- "The Case Against [Common Approach]"
Question-Based (2-3 titles)
Titles that engage through curiosity:
- "Is [Common Belief] Actually True?"
- "Why Can't [Audience] [Achieve Result]?"
- "What Would Happen If You [Bold Action]?"
Step 3: Platform Optimization
For the top 5 titles, create platform-specific versions:
| # | Base Title | YouTube Version (60 char) | Blog/SEO Version | Newsletter Subject Line | Social Post Title |
|---|
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 · 83 lines · 40 tokens per session scan A 7ae6c8463f41
title-generator 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 801 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).