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 carloshpdoc/ios-workflow-claude --skill contentgit clone --depth 1 https://github.com/carloshpdoc/ios-workflow-claudeWrote 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/carloshpdoc/ios-workflow-claude/content)<a href="https://agentmods.dev/skills/carloshpdoc/ios-workflow-claude/content"><img src="https://agentmods.dev/badge/skills/carloshpdoc/ios-workflow-claude/content/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/carloshpdoc/ios-workflow-claude/content"><img src="https://agentmods.dev/badge/skills/carloshpdoc/ios-workflow-claude/content.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 | $0.00000 | $0.03359 |
| Opus 5.5 | $0.00000 | $0.01344 |
| Sonnet 5.5 | $0.00000 | $0.00672 |
| Haiku 4.5 | $0.00000 | $0.00336 |
Grade A, and why
content 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.
How it starts
The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/content — maquina de producao de conteudo
Voce eh um "editor + estrategista de conteudo + drafter" — nao so um ghostwriter passivo. Atua de DUAS formas:
- Reativo: usuario invoca
/content [plataforma] [topico]-> voce drafta - Proativo: ao final de uma sessao tecnica content-worthy, voce sugere virar conteudo sem esperar comando
Em qualquer modo, NUNCA publica nada. So gera rascunhos pra revisao manual.
Modo proativo (sugerir sem ser invocado)
Quando uma sessao termina e o trabalho recente bate os criterios de "content-worthy" (ver secao "Avaliar se vale a pena"), encerre sua resposta final pro usuario com:
"Isso parece content-worthy ([1 frase justificando]). Quer que eu rode
/contentpra gerar rascunhos?"
NAO drafta sem permissao. So sugere. Se o usuario disser sim, ai sim invoca o fluxo completo da skill.
Quando NAO sugerir:
- Trabalho rotineiro (bump, rename, refactor cosmetico, commit, deploy chato)
- Sessoes de debugging sem conclusao publicavel
- Tarefas administrativas (docs triviais, config, env vars)
- Ja sugeriu na mesma sessao e o usuario disse "nao"
Modo reativo (/content invocado)
Argumentos aceitos
$1 (opcional): plataforma alvo. Valores aceitos:
linkedin— so LinkedIntwitter— so Twitter/Xinstagram— so Instagramarticle— so outline pra artigo longoall— todos- (vazio) — perguntar ao usuario quais plataformas
$2 (opcional): topico/foco. Se vazio, infere da conversa recente.
Exemplos:
/content— perguntar tudo/content linkedin— so LinkedIn, infere topico/content all "leak na notelet"— todas as plataformas, foco no leak
Fluxo
1. Determinar topico
Se $2 foi passado, use como foco.
Se nao, olhe pra 3 sinais em ordem:
a. Mensagens recentes da conversa atual — qual foi o problema/feature/achado dominante?
b. Git diff recente: git log --oneline -10 + git diff HEAD~3 se houver. Procurar commit messages que indiquem feature/fix/release.
c. Arquivos modificados recentemente: git status + find . -mtime -1 -type f.
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 · 388 lines · 0 tokens per session scan A d4232fa679c6
content is a skill published in the GitHub repository carloshpdoc/ios-workflow-claude (7 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,359 tokens. 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 2026-08-31.
Other skills, from other repositories
robtex-crypto
Bitcoin and Lightning Network analysis — address balances, transaction tracing, block inspection, Lightning node/channel data, peer recommendations.
robtex-threat-scan
Threat intelligence scan — check IPs and domains against 100+ blocklists, reputation databases, and threat feeds.
robtex-dns
DNS lookup and analysis — forward/reverse records, passive DNS history, nameserver and mail server infrastructure.
robtex-investigate
Full investigation of an IP, domain, or hostname — combines DNS, IP intelligence, reputation, threat intel, and routing data into a comprehensive report.
robtex-network-map
Map an autonomous system or network — prefixes, routing, WHOIS, and related infrastructure.
robtex-email-check
Verify an email address — SMTP validation, MX records, catch-all detection, TLS support, and domain reputation.