Workflows

Take a developer task from its first question to a checked result: manually, with automation, or across providers.

Start with a clear handoff. Automate a stage once its inputs, outputs, and checks are understood. Larger workflows keep consequential decisions with a person who can inspect the evidence.

  1. Taskgoal and checks
  2. Artifactssources and proposed changes
  3. Toolsnative methods or a pipeline
  4. Humaninspect and decide

Download the local reference package · Three offline recipes and optional CLI execution with a reviewed profile.

Methods and pipelines

Claude: existing methods and cost examples

  • Workflow: debugging a failure Claude + Claude Code + Anthropic API

    Narrowing costs four times what diagnosing costs. Put the cheap model on the search and the expensive one on the thirty seconds that decide the answer.

  • Workflow: a refactor across several files Claude + Claude Code + Anthropic API

    The plan is 1% of the tokens and decides the other 99%. Everything else is mechanical, and mechanical work does not need the expensive model.

  • Workflow: researching and synthesising Claude + Claude Code + Anthropic API

    Reading thirty sources costs eight times what thinking about them costs. This is the workflow where model choice saves the most.

  • Workflow: reviewing a change Claude + Claude Code + Anthropic API

    Three steps, three different models. Reading is not judging, and paying Opus rates to read a diff is the commonest waste in this workflow.