Borrowing it
Nothing to install: this file belongs to darcivieira/kanbanize-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darcivieira/kanbanize-sdk/main/.claude/skills/spec-bootstrap/SKILL.mdgit clone --depth 1 https://github.com/darcivieira/kanbanize-sdkWrote 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/darcivieira/kanbanize-sdk/spec-bootstrap)<a href="https://agentmods.dev/skills/darcivieira/kanbanize-sdk/spec-bootstrap"><img src="https://agentmods.dev/badge/skills/darcivieira/kanbanize-sdk/spec-bootstrap/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/darcivieira/kanbanize-sdk/spec-bootstrap"><img src="https://agentmods.dev/badge/skills/darcivieira/kanbanize-sdk/spec-bootstrap.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 | $0.00123 | $0.02199 |
| Opus 5 | $0.00062 | $0.01099 |
| Sonnet 5 | $0.00025 | $0.00440 |
| Haiku 4.5 | $0.00012 | $0.00220 |
Grade A, and why
spec-bootstrap 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 6d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-bootstrap
Preenche a base de specs por entrevista, nunca por suposição.
Princípio inegociável
Você não inventa conteúdo de spec. Cada fato preenchido vem de (a) resposta do humano, ou (b) leitura direta do código, apresentada ao humano e confirmada por ele.
Se você não tem o fato, deixa <<PREENCHER: ...>> e diz explicitamente o que ficou pendente.
Spec inventada é pior que spec vazia: o agente futuro vai confiar nela.
Fase 0 — Reconhecimento
-
Verifique se
specs/existe. Se não existir, avise que a base precisa ser copiada antes. -
Determine o tipo de projeto:
- Existente: há código-fonte além de config.
- Novo: repositório vazio ou só scaffolding.
-
Se existente, delegue a varredura para um subagente de exploração (read-only) e peça:
- linguagens, frameworks e versões (a partir de arquivos de manifesto)
- layout de diretórios de topo e o padrão que ele sugere
- módulos / bounded contexts aparentes
- rotas de API e rotas de frontend existentes
- entidades / modelos de dados
- biblioteca de componentes e origem dos tokens visuais
- comandos reais (scripts de package manager, Makefile, CI)
- o que já existe de doc (README, ADRs, comentários de arquitetura)
Subagente evita que a varredura consuma o contexto principal.
-
Apresente o resultado como proposta, em tabela, e peça confirmação:
"Detectei isto. Confirma, corrige ou completa?"
Nunca escreva em
specs/antes desta confirmação.
Fase 1 — Entrevista
Regras da entrevista:
- Um bloco por vez. Espere a resposta antes do próximo.
- Ofereça o que você detectou como resposta padrão — o humano só corrige.
- Aceite "não sei" e "depois": vira
<<PREENCHER>>, não vira invenção. - No máximo 5 perguntas por bloco.
- Escreva os arquivos de cada bloco antes de passar ao próximo. Se a conversa for interrompida, o que já foi respondido está salvo.
Bloco A — Produto → visao/PRODUTO.md, visao/GLOSSARIO.md
- O que o sistema faz, em uma frase?
- Que problema resolve, para quem, e qual é a alternativa que as pessoas usam hoje?
- O que ele explicitamente não faz? (não-objetivos)
- Quais termos de domínio um dev novo entenderia errado?
- Alguma restrição dura — prazo, regulatório, integração obrigatória, legado intocável?
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.
- 6d ago First seen · 166 lines · 123 tokens per session scan A 708ca2b1b402
spec-bootstrap is a skill published in the GitHub repository darcivieira/kanbanize-sdk (2 stars, last pushed 28d ago), licensed MIT. It adds 123 tokens to every session and 2,199 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…