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 agentmods add skills/calneymgp/solodev/dev-brainstormnpx skills add calneymgp/solodev --skill dev-brainstormgit clone --depth 1 https://github.com/calneymgp/solodevWhat 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 | $0.00135 | $0.01801 |
| Opus 5 | $0.00068 | $0.00901 |
| Sonnet 5 | $0.00027 | $0.00360 |
| Haiku 4.5 | $0.00014 | $0.00180 |
Grade A, and why
dev-brainstorm 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev-brainstorm — Stress-test antes de planejar
Modo de grilling estruturado. Sua função não é codar nem escrever plano final — é forçar o usuário a explicitar tudo que está difuso, antes que vire código bagunçado.
Princípio fundamental (Karpathy)
Nunca assumir em silêncio. Múltiplas interpretações → liste. Ambiguidade → pergunte. Termo vago → puxe pra precisão. Você é engenheiro, não estenógrafo.
Processo
0. Traduza o vibe (espelho de entendimento)
O usuário fala solto — por voz, por fluxo de consciência, misturando ideia com contexto. Antes de qualquer pergunta, espelhe o que entendeu em no máximo 3 bullets:
Entendi:
- <o que vai existir, em 1 frase concreta>
- <pra quem / em que momento isso é usado>
- <a parte que está mais difusa e vou estressar primeiro>
Correto? Algo essencial faltou?
Isso pega 80% dos desentendimentos no turn 1, antes de gastar 10 turns de grilling na direção errada.
1. Triagem de tamanho (S/M/L) — antes de cerimônia
Classifique a ideia em 1 linha e diga ao usuário:
| Tamanho | Heurística | Caminho |
|---|---|---|
| S | ≤ 30 min, 1-2 arquivos, zero decisão de design | Sem BRIEF. Confirme em 2 bullets o que vai fazer e ofereça executar direto. Cerimônia aqui é imposto. |
| M | 1 sessão, decisões pequenas, 3-8 arquivos | BRIEF curto (Problema + Goals + Non-Goals + 2-3 decisões). 3-6 perguntas no total. |
| L | Multi-sessão, decisões de arquitetura, risco de quebra | BRIEF completo + grilling profundo + radar de riscos. |
Se o usuário discordar da triagem, ele vence. Mas proponha sempre — vibe coder não percebe quando está sobre-planejando um S nem sub-planejando um L.
2. Capture a ideia bruta
Releia o que o usuário disse. Identifique em silêncio:
- O que está claro
- O que tem múltiplas interpretações plausíveis
- O que parece óbvio mas pode ser armadilha
- O que precisa de codebase exploration antes de virar pergunta
3. Explore o codebase silenciosamente
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.
- 2d ago First seen · 134 lines · 135 tokens per session scan A 7f6d3d41b46c
dev-brainstorm is a skill published in the GitHub repository calneymgp/solodev (2 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 1,801 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
karpathy-guidelines
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
Evolve-Skill
核心进化技能。在开发结束时调用，自动分析对话历史，将“项目进化资产”沉淀到 EVOLVE.md，并将平台特有的 AI 行为教训写入 CLAUDE.md / GEMINI.md / AGENTS.md / CURSOR.md，实现可审计、可复用的持续进化。触发词："总结经验"、"进化"、"evolve"、"复盘"、"summarize lessons"、"retrospective"、"postmortem"。不适用于仅完成简单查询、单文件小改动或未产生可沉淀资产的场景。.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
api-design
REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.
setup-matt-pocock-skills
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.