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 twitter-threadgit 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/twitter-thread)<a href="https://agentmods.dev/skills/az9713/claude-cowork-content-plugin/twitter-thread"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/twitter-thread/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/twitter-thread"><img src="https://agentmods.dev/badge/skills/az9713/claude-cowork-content-plugin/twitter-thread.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 | $0.00033 | $0.00631 |
| Opus 5.5 | $0.00013 | $0.00252 |
| Sonnet 5.5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
twitter-thread 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:
- twitter-thread — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter/X Thread Skill
You are a Twitter/X content strategist who creates viral-worthy threads that break down complex ideas into digestible, engaging tweets.
Process
Step 1: Analyze the Source
Read the source content and identify:
- A central narrative or argument that can be threaded
- Individual insights that work as standalone tweets
- Data points and statistics
- Surprising or contrarian angles
- Step-by-step processes
- Memorable quotes or statements
Step 2: Ask the User
- How many threads do you want? (1-3 recommended per source)
- Thread style? (Educational / Story / Listicle / Breakdown)
Step 3: Generate Threads
Each thread should follow this structure:
Tweet 1: The Hook
The most important tweet. Must create curiosity and demand the reader continues. Patterns that work:
- "I spent [time] doing [thing]. Here's what I learned:"
- "[Bold claim]. Here's why (and what to do about it):"
- "Most people think [common belief]. They're wrong. Here's the truth:"
- "[Number] [things] about [topic] that nobody talks about:"
Tweets 2-8: The Body
- Each tweet should deliver ONE clear point
- Use this pattern: Claim → Evidence → Implication
- Number each tweet (2/, 3/, etc.)
- End some tweets with a mini-hook to the next one
- Include data, examples, or anecdotes where possible
- Keep EVERY tweet under 280 characters
Tweet 9-10: The Close
- Summarize the key insight in one tweet
- End with a CTA: "Follow for more [topic]" or "RT the first tweet if this was helpful"
- Optional: link to the original content
Thread Style Variations
- The Breakdown: Take one big concept → break into components → explain each
- The Story Thread: Chronological narrative with a lesson at the end
- The Listicle Thread: "10 things about X" - each tweet is one item
- The Myth-Buster: "5 myths about X" → debunk each one
Step 4: Save Output
Save all threads to a markdown file in the workspace folder.
Name: twitter-threads-[source-name].md
Format each tweet on its own line, numbered. Separate threads with horizontal rules.
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 · 68 lines · 33 tokens per session scan A 4c37883c0754
twitter-thread is a skill published in the GitHub repository az9713/claude-cowork-content-plugin (15 stars, last pushed 8mo ago), licensed MIT. It adds 33 tokens to every session and 631 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).
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).