Hire an AI Git workflow planner

Everything it can hand back

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

• A recommended branching style, with the reasons
• Branch naming rules with examples
• Commit message rules
• Rules for when to merge, squash or rebase
• A pull request review checklist
• Safe commands for a first clean-up, each with its undo step

How it does the job well

• Never recommend force-pushing a shared branch. Where a force-push is unavoidable, give --force-with-lease, name the risk and require agreement from everyone who uses the branch.
• Show the safe version of every risky command, warn before destructive ones and give recovery steps such as reflog.
• You cannot run commands. Never say a command was run or a branch was deleted.
• Do not change host settings or build pipelines. Propose them for a named engineer.
• Atomic commits — Each commit does one thing and can be reverted independently
• Conventional commits — feat:, fix:, chore:, docs:, refactor:, test:
• Never force-push shared branches — Use --force-with-lease if you must

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: Your team is growing and everyone names branches and writes messages a different way.

• Team and release facts. What it learned about your team and release pace, with gaps marked MISSING.
• Recommended style. Trunk-based or Git flow, with the reasons it fits and what to avoid.
• Branch names. A naming pattern with examples.
• Commit rules. Message format and size rule, with an example.
• Merge rules. When to merge, squash or rebase, and why.
• Pull request checklist. What each pull request must show before it can merge.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• 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 would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Learn the team. It notes team size, release pace, hosting and what goes wrong, and asks once for anything missing.
• Choose the style. It picks trunk-based work or Git flow, and says why it fits your release pace.
• Set names and commits. It writes branch name patterns and commit message rules, with one change per commit.
• Set merge rules. It says when to merge, squash or rebase, and where force-pushing is never allowed.
• Write the review checklist. It writes what a pull request must show before it can merge, including checks to pass.
• Plan the clean-up. It gives safe commands for stale branches, each with a warning and an undo step.

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 engineering-git-workflow-master 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/engineering-git-workflow-master/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

• Your team size and who can merge to the main branch
• How you release, such as every day, every week or numbered versions
• Where your code lives (GitHub, GitLab or Bitbucket) and any branch rules already set
• What goes wrong now, such as stale branches or big merge conflicts
• Your branch list or recent git log output (optional)

Helpful context (optional)

• The output of git branch -a --sort=-committerdate, to spot stale branches.
• Your current pull request template, if you have one.

Tools and access

• Claude, ChatGPT or Gemini: It plans from pasted text, so no repository access is needed.
• A coding tool such as Claude Code: It can read your real branch list and log, but never let it force-push or change settings.

Functions and deliverables

• Git workflow planner: Get a Git workflow plan with branch names, commit rules and a pull request checklist. Bring your team size and release pace.
  • A recommended branching style, with the reasons
  • Branch naming rules with examples
  • Commit message rules
  • Rules for when to merge, squash or rebase
  • A pull request review checklist
  • Safe commands for a first clean-up, each with its undo step
  Source: Michael Sitarzewski and Agency Agents contributors.
• Git workflow helper: Describe your Git task. Get state checks and help with branches, commits, merges or pull requests.
  • Clean, atomic commits
  • Branches created from the right base
  • Conflicts resolved with explanations
  • A pull request ready to review
  Source: Burhan Sebin.
• Commit and pull request sender: With your explicit approval, turn git changes into a pushed commit and GitHub pull request.
  • A new branch
  • A commit
  • A pushed branch
  • An open pull request with the link
  Source: OpenAI.
• Pull request description writer: Write a pull request description from your committed branch. It says what changed, why, and what reviewers should check, then opens a draft on GitHub.
  • Pull request title and body
  • Summary of what changed and why
  • Reviewer notes
  • The opened pull request
  Source: sickn33.
• 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

Tasks you can use it for

• Your team is growing and everyone names branches and writes messages a different way.
• Feature branches stay open for weeks and merging them hurts.
• You need pull request rules that a new hire can follow on day one.
• You are choosing between merge, squash and rebase and want a clear answer for your team size.

Limits to check before starting

• You need to rewrite shared history or change live repository settings. Have a named engineer do it, using the plan as a guide.
• You want your build and release pipeline set up. Use the Deployment pipeline designer.
• You want the code inside a pull request reviewed. Use the Code reviewer agent.

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 pack from this page and add it to your AI as a skill. If you cannot, open a new chat and paste SKILL.md, then references/source-agent.md.
• Paste your team size, release pace and where your code lives. Describe what goes wrong now in a line or two.
• Add your branch list (git branch -a) or recent log output if you want a clean-up plan for your real repository.
• Say "Plan our Git workflow. Ask once if anything is missing."
• Read the recommended style and its reasons first. If your team cannot follow it, say why and ask for the next best option.
• Run each git command yourself, one at a time, in a fresh clone first. Read the undo line before you run it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-git-workflow-master 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.