Hire an AI code change and test-step planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The change in one line, and a list of cases to test, smallest first, with the one to turn into a real test now
• Every edit labelled as structure or behaviour, grouped into small steps, with when to run your tests
• A plan file with the ordered tests, a one-word command for your helper, and standing rules with warning signs to watch

How it does the job well

• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You are changing code, with or without an AI helper, and want every step small and safe.

• Test list. The change in one line, cases to test from smallest to largest, and the one case to turn into a real test now.
• Small steps. Each edit labelled as structure or behaviour, grouped into tidy-up steps and new-behaviour steps, with when to run your tests.
• Plan file. The ordered tests, a one-word command for your helper and the order to work in.
• Standing rules. Rules that keep your helper on one test at a time, with warning signs to watch for.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why. The checks per step are below.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Kent Beck and Linus Torvalds would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• List the test cases. Writes the change in one line, lists the cases it must handle, including old behaviour that must stay, and puts the smallest first.
• Split the change. Takes the test list and labels each edit as structure or behaviour, then puts tidy-ups and new behaviour in separate small steps.
• Write the helper's rules. Takes the ordered steps and writes a plan file, a one-word command and standing rules so the helper does one test at a time.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id ai-code-change-steps only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/ai-code-change-steps/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The change you want to make, in your own words
• What the code does today, and any code or notes (optional)
• Cases you already know about, such as past bugs (optional)
• The change as a diff or list of edits, if it is already written (optional)
• A short description of the project and the tools it uses
• Rules your team already has for commits and checks (optional)

Tools and access

• Any good chat AI: Listing and ordering cases is text work any strong chat AI does.
• Your test runner or a checklist: Each case becomes a real test or a tick box you can run.
• Any good chat AI: Labelling edits and ordering steps is text work any strong chat AI does.
• Your version control tool: Each step maps to one save point you can review and undo.
• Claude Code: Reads project rule files and a plan file, so the rules apply to every session.
• Any coding agent that reads a rules file: The rules and plan file are plain text any agent can follow.

Functions and deliverables

• Code change and test-step planner: Turn a code change into an ordered test list, small review steps and clear rules for an AI coding helper.
  • The change in one line, and a list of cases to test, smallest first, with the one to turn into a real test now
  • Every edit labelled as structure or behaviour, grouped into small steps, with when to run your tests
  • A plan file with the ordered tests, a one-word command for your helper, and standing rules with warning signs to watch
• Test list writer: Write a test list before you change software, a form or a process. Get cases to check, smallest first, with the first one marked.
  • The change in one line
  • A list of cases, each describing behaviour and not how to build it
  • The order to work through them, smallest first
  • The one case to turn into a real test now
• Process and behavior change planner: Split a messy change into small tidy-up steps and new-behaviour steps, so each one is easy to review and undo. Paste your diff or edit list.
  • Every edit labelled as structure or behaviour, with how easy it is to undo
  • A set of small tidy-up steps and a set of behaviour steps
  • Which tidy-ups help the behaviour change, and which are optional
  • The order, with when to run tests
• AI coding agent rules writer: Set up an AI coding agent rules file and plan file so your agent works one test at a time and is told not to delete tests to pass.
  • A plan file with the ordered tests and what is done
  • A one-word command and what it must do
  • Standing rules for the agent that you can check from the commit history
  • Warning signs and when to take the design back
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Kent Beck: Plan a software change using Kent Beck’s recorded approach. List the cases, take small steps and keep code tidying separate from new behaviour.
  • Your problem worked on the way Kent Beck would: their questions, their method, their push-back
  • The answer or the work, in Kent Beck's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Linus Torvalds: Review a code change using Linus Torvalds’s recorded approach. Ask what works, what breaks for existing users and who owns the fix.
  • Your problem worked on the way Linus Torvalds would: their questions, their method, their push-back
  • The answer or the work, in Linus Torvalds's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are changing code, with or without an AI helper, and want every step small and safe.
• You have a large messy change and need to split it into pieces someone can review one at a time.
• Your AI coding helper keeps adding things you did not ask for, and you want rules that hold it to one test at a time.

Limits to check before starting

• You are making a one-line fix or a throwaway prototype: write a plain test, or just make the edit and check it by hand.
• You want your AI helper to start coding the first test right now: take the plan file from this workflow and give it to your coding helper.
• You need a review of code that is already merged: ask a teammate to read the commits, since this workflow plans changes before they are made.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Describe the change you want. It writes the test list first.
• Put the plan file and rules in your project, then start your AI helper with the one-word command.
• Check the commit history as you go. The rules are written so you can tell if they were followed.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/ai-code-change-steps for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.