skill-migrate

skill-migrate is a cursor rule for Cursor from dewtech-technologies/dare-method. It costs 0 tokens per session (860 once invoked), scanned A, original, MIT.

Camada semântica da migração (Fase 2 brownfield). Roda depois do comando dare migrate e escreve a estratégia de migração + cenários Gherkin de paridade reais no DARE/MIGRATION/, garantindo reimplementação fiel ao legado.

Cursor rule for Cursor

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 rules/dewtech-technologies/dare-method/skill-migrate
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Cursor.

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 skill-migrate

README.md
[![agentmods](https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-migrate.svg)](https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-migrate)
Your own site
<a href="https://agentmods.dev/rules/dewtech-technologies/dare-method/skill-migrate"><img src="https://agentmods.dev/badge/rules/dewtech-technologies/dare-method/skill-migrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 860 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00000 $0.00860
Opus 5 $0.00000 $0.00430
Sonnet 5 $0.00000 $0.00172
Haiku 4.5 $0.00000 $0.00086

Measured today against content hash 22511fa6f70a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-migrate 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 today.

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.

implementations/cursor/.cursor/rules/skill-migrate.mdc · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Migrate — Migração com paridade (brownfield Fase 2)

Camada semântica da migração. Roda depois do comando dare migrate, que já leu os artefatos do reverse/dna e gerou os esqueletos. Sua função é escrever a estratégia de migração e os cenários Gherkin de paridade reais — o contrato comportamental que garante reimplementação fiel.

Pré-requisito: rodar dare migrate --to <stack> antes (gera DARE/MIGRATION/MIGRATION.md, migration-facts.json, parity/*.feature). Que por sua vez exige dare reverse já feito.

Quando usar

  • Projeto legado entendido (reverse + dna) que será reimplementado em outra stack.
  • Acabou de rodar dare migrate e há seções <!-- AGENT --> / # AGENT em aberto.

O que fazer

1. Carregar contexto (não re-varrer)

Leia migration-facts.json (origem/alvo/módulos/blocking gaps), IDEIA.md + REVERSE/module-*.md e PROJECT-DNA.md. Abra arquivos-chave do legado só o necessário.

2. Preencher MIGRATION.md

  • Decisão de Paradigma — mudou (procedural→OO, monólito→serviços)? Decisão + justificativa.
  • Estratégia — big-bang vs. strangler/parallel-run; ordem dos módulos; feature flags.
  • Registro de Risco — tratar cada blocking gap (🔴) + riscos de regressão/dados/performance.
  • Arquitetura-alvo — na stack-alvo, alinhada ao DNA quando o paradigma for preservado.
  • Cutover & Rollback — passos, validação de paridade (rodar .feature), go/no-go, rollback.

3. Gherkin de paridade (parity/<módulo>.feature)

Um Scenario por fluxo observável, derivado do comportamento legado real: GivenWhenThen idêntico ao legado. Inclua bordas/formatos (arredondamento, máscaras). É o contrato de aceite.

4. Apresentar ao usuário

Resumo: paradigma, estratégia, nº de cenários, blocking gaps a resolver.

Regras de ouro

  1. Paridade primeiro — todo fluxo crítico vira Scenario.
  2. Blocking gaps são bloqueantes — 🔴 não resolvido é risco; trate ou registre.
  3. Respeite o DNA — arquitetura-alvo segue as convenções da casa.
  4. Não invente comportamento — cenário sem base no legado = regressão silenciosa.
  5. Strangler quando possível — incremental com parallel-run reduz risco.

Read the full file on GitHub · 59 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. today First seen · 59 lines · 0 tokens per session scan A 22511fa6f70a

Subscribe to this mod's changes

skill-migrate is a cursor rule published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 860 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 2026-09-03.