brainstormer

brainstormer is an agent for coding agents from georgemarmelstein/superjurista-dev. It costs 21 tokens per session (2,127 once invoked), scanned A, original, MIT.

A structured brainstorming agent for improving a skill's purpose, description, and test scenario.

In plain words
What is it for?
Use it to clarify who a skill is for, classify it as a discipline, technique, pattern, or reference, and define a scenario for testing it.
Why use it?
It helps uncover vague instructions and missing test cases before a skill is built, so the skill is more likely to activate at the right time and teach the intended behavior.

Agent

Part of the superjurista-dev plugin — 11 skills, 22 commands, 7 agents shipped together

Install

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.

agentmods
npx agentmods add agents/georgemarmelstein/superjurista-dev/brainstormer
Clone the repo
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-dev

Or install superjurista-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 7 agents.

Wrote 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.

agentmods badge for brainstormer

README.md
[![agentmods](https://agentmods.dev/badge/agents/georgemarmelstein/superjurista-dev/brainstormer.svg)](https://agentmods.dev/agents/georgemarmelstein/superjurista-dev/brainstormer)
Your own site
<a href="https://agentmods.dev/agents/georgemarmelstein/superjurista-dev/brainstormer"><img src="https://agentmods.dev/badge/agents/georgemarmelstein/superjurista-dev/brainstormer.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.02127
Opus 5 $0.00010 $0.01064
Sonnet 5 $0.00004 $0.00425
Haiku 4.5 $0.00002 $0.00213

Measured 5d ago against content hash 7b5a2be4cab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstormer 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 5d 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.

skills/criar-skill/agents/brainstormer.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Por que isso importa: Skills mal projetadas falham de duas formas: (1) description vaga → Claude não ativa a skill quando deveria, ou (2) sem cenário de teste → skill parece funcionar mas não ensina o comportamento certo. O brainstorming estruturado previne ambos os problemas.

**Por quê:** Essas 4 perguntas definem o "quem" e o "porquê" da skill,
que serão a base para todas as decisões seguintes.
**Por quê:** O tipo de skill determina o template (fork vs padrão),
a necessidade de testes (RED/GREEN/REFACTOR), e a profundidade das
restrições (disciplinas precisam de tabela de racionalizações).

Classificação:
- **DISCIPLINA**: Impõe regras que contradizem objetivos imediatos.
  Ex: "testar antes de commitar" quando há pressão de tempo.
- **TÉCNICA**: Método concreto transformando input em output.
- **PADRÃO**: Modelo mental para decisões.
- **REFERÊNCIA**: Documentação sem regras a violar.

Read the full file on GitHub · 220 lines

Changes

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.

  1. 5d ago First seen · 220 lines · 21 tokens per session scan A 7b5a2be4cab4

Subscribe to this mod's changes

brainstormer is an agent published in the GitHub repository georgemarmelstein/superjurista-dev (20 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 2,127 once invoked, about $0.0001 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.