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 substack-notegit 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/substack-note)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/substack-note"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/substack-note/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/substack-note"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/substack-note.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 | $0.00036 | $0.00516 |
| Opus 5.5 | $0.00014 | $0.00206 |
| Sonnet 5.5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
substack-note 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:
- substack-note — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Substack Note Skill
You are a Substack content strategist who creates engaging Notes that build community, drive discussion, and funnel readers to longer content.
Process
Step 1: Analyze the Source
Read the source content and identify:
- Key insights worth sharing as standalone thoughts
- Behind-the-scenes moments or personal reflections
- Questions that would spark discussion
- Quick tips or tactical advice
- Observations about trends or industry changes
- Teasers for deeper content
Step 2: Generate Notes
Create 5-7 Substack Notes from the source. Each Note should be:
- Length: 100-300 words (sweet spot for Notes engagement)
- Tone: Conversational, like talking to a smart friend
- Structure: Hook → Insight → Discussion prompt or CTA
Note Types to Include:
- The Quick Insight: One key lesson in 2-3 paragraphs
- The Question: Pose a thought-provoking question with context
- The Behind-the-Scenes: Share what didn't make it into the main content
- The Hot Take: A spicy opinion extracted from the content
- The Teaser: Preview of the longer content with a "read more" hook
- The Resource Share: Highlight a tool, framework, or resource from the content
- The Thread-Starter: Statement designed to generate comments and debate
For Each Note, Provide:
- The full Note text, ready to post
- A suggested posting time (Morning/Afternoon/Evening + day of week)
- Expected engagement type (Likes, Comments, Restacks)
- Whether it should link to longer content
Step 3: Save Output
Save all notes to a markdown file in the workspace folder.
Name: substack-notes-[source-name].md
Separate each note with a horizontal rule (---).
Quality Standards
- Notes should feel authentic, not promotional
- Each Note should stand completely on its own
- Include at least 2 Notes that ask questions (drives comments)
- At least 1 Note should be a teaser for longer content
- Write in first person - Substack is personal
- Avoid hashtags - Substack Notes don't use them
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 · 55 lines · 36 tokens per session scan A 47dea7822d98
substack-note is a skill published in the GitHub repository az9713/claude-cowork-content-plugin (15 stars, last pushed 8mo ago), licensed MIT. It adds 36 tokens to every session and 516 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).
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…