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 elisaterumi-ai/agent-skills-in-practice --skill radar-ia-brgit clone --depth 1 https://github.com/elisaterumi-ai/agent-skills-in-practiceWrote 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/elisaterumi-ai/agent-skills-in-practice/radar-ia-br)<a href="https://agentmods.dev/skills/elisaterumi-ai/agent-skills-in-practice/radar-ia-br"><img src="https://agentmods.dev/badge/skills/elisaterumi-ai/agent-skills-in-practice/radar-ia-br/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/elisaterumi-ai/agent-skills-in-practice/radar-ia-br"><img src="https://agentmods.dev/badge/skills/elisaterumi-ai/agent-skills-in-practice/radar-ia-br.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 | $0.00826 |
| Opus 5 | $0.00016 | $0.00413 |
| Sonnet 5 | $0.00007 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
radar-ia-br 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radar Notícias IA BR
Objetivo
Busca e resume as principais notícias recentes de Inteligência Artificial a partir de fontes curadas.
A skill:
- busca notícias recentes
- remove duplicatas
- categoriza os tópicos
- traduz/resume em português
- retorna:
- título
- link
- categoria
- resumo curto
Uso
Invoke com:
/radar-ia-br- "últimas notícias de IA"
- "resumo IA"
- "o que aconteceu em IA hoje"
- "AI briefing"
Opcionalmente o usuário pode informar quantidade:
- "me mostre 5 notícias de IA"
- "top 10 notícias de IA"
Fontes preferenciais
Use estas fontes:
Fontes primárias
- Anthropic News — Company announcements
- Claude Blog — Product updates and guides
- Google AI — Gemini/DeepMind
Fontes de curadoria
- TLDR AI — Daily AI industry digest
- The Decoder — AI-focused site
- Last Week in AI — Weekly roundup
Instruções
Determinar quantidade
Se o usuário informar quantidade:
- usar quantidade solicitada
Caso contrário:
- usar 10 notícias por padrão
Máximo:
- 20 notícias
Critérios de seleção
Priorize notícias:
- Recentes (,ax 72 horas)
- Relevantes para IA generativa, modelos, produtos, pesquisa, agentes, ferramentas ou mercado
- Publicadas ou destacadas nas fontes
- Com impacto potencial para profissionais, criadores, desenvolvedores ou empresas
Remoção de duplicadas
Se a mesma notícia aparecer em mais de uma fonte:
- mantenha apenas uma entrada
- escolha como link principal a fonte mais original ou mais direta
- mencione fontes adicionais no campo “Também apareceu em”
- não repita a notícia na lista
Categorias possíveis
Classifique cada notícia em uma destas categorias:
- Lançamento (launch, release, announce, GPT, Claude, Gemini, model)
- Pesquisa (paper, benchmark, study, research)
- Ferramenta para desenvolvedores
- Produto (feature, API, update, tool)
- Mercado (funding, startup, acquisition)
- Segurança em IA (safety, alignment, red team)
- Opinião (opinion, future, prediction)
- Outros
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 145 lines · 33 tokens per session scan A 8bb28f718d33
radar-ia-br is a skill published in the GitHub repository elisaterumi-ai/agent-skills-in-practice (133 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 826 once invoked, about $0.0002 per session on Opus 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
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-blocking-guardrails
Configure and use feedback functions as runtime blocking guardrails.
trulens-dataset-curation
Create and curate evaluation datasets with ground truth for TruLens.