26-incremental-changes

A development rule that requires features, migrations, and refactors to be completed in small, separate stages. Each stage must remove related old code and pass linting, builds, and tests before the next begins.

In plain words
What is it for?
Use it to structure incremental repository changes and create one descriptive commit for each verified stage.
Why use it?
It prevents half-finished changes, duplicate implementations, unused code, and broken checks from accumulating.

Cursor rule

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/joaonic/agentkit/26-incremental-changes
Clone the repo
git clone --depth 1 https://github.com/Joaonic/agentkit
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 303 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 $0.00000 $0.00303
Opus 5 $0.00000 $0.00151
Sonnet 5 $0.00000 $0.00061
Haiku 4.5 $0.00000 $0.00030

Measured yesterday against content hash 881c934f37af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

26-incremental-changes 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 yesterday.

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.

src/core/rules/26-incremental-changes.mdc · 35 lines

What it actually says

Implementação Incremental

Toda nova feature, migração ou refactor DEVE ser feita incrementalmente:

Regras

  1. Trabalhar por partes isoladas: Quebrar em etapas pequenas e independentes.
  2. Completar cada parte antes de avançar: Implementar totalmente; remover TODOS os vestígios antigos; sem código morto, imports não usados ou referências antigas.
  3. Validar antes de continuar: lint, build, testes. Zero warnings.
  4. Zero tolerância a código intermediário: Não avançar se há código antigo coexistindo, imports não usados, erros de lint/build, ou funcionalidade pela metade.
  5. Commits incrementais: Um commit por etapa completa; mensagem descritiva.

Fluxo por Etapa

  1. Implementar a mudança específica
  2. Remover código antigo relacionado
  3. Lint fix
  4. Build
  5. Testar
  6. Commit
  7. Só então avançar

Anti-Pattern

  • Criar novo mantendo antigo "por enquanto"
  • Deixar limpeza "para depois"
  • Múltiplas partes em um único commit
  • Avançar com build/lint quebrado
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. yesterday First seen · 35 lines · 0 tokens per session scan A 881c934f37af

Subscribe to this mod's changes

26-incremental-changes is a cursor rule published in the GitHub repository Joaonic/agentkit (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 303 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 2026-08-31.