CompCode Academy

Lesson 29 of 65 · Free to read

Day 29 ΓÇö Git workflows with agents

Month 2 · Week 6 — Claude Code & Agentic CLI Coding Audience: Final-year students & early-career engineers (0–3 years) Format: Self-paced study + optional live clinic · Suggested time: 4–6 focused hours Key tools: Claude Code, GitHub

Overview

Agents can branch, commit, and open PRs — but you must keep secrets out of AI config commits and write honest commit messages.

Learning objectives

By the end of this session, you can:

  • Explain the core ideas behind: Git workflows with agents: branches, commits, and pull requests.
  • Apply the ideas using Claude Code, GitHub on a realistic task (capstone, internship, or first-job style)
  • Produce the exercise deliverable with clear success criteria
  • Identify common failure modes and how to recover
  • Capture at least one reusable prompt, rule, or checklist for your personal library
  • Decide what must remain human-reviewed for this class of work

Core concepts

Git agent etiquette

Feature branches, atomic commits, PR bodies with test plan.

Version the AI config

Commit CLAUDE.md, Cursor rules, and prompt cookbook — review for tokens/secrets first.

Tooling for today

Primary tools: Claude Code, GitHub. Prefer official docs when APIs change. When a model invents a symbol, verify against source or docs immediately.

Practice posture

You are a final-year or early-career engineer pairing with a very fast teammate (the model): clear intent, grounded context, inspect consequential changes, keep a paper trail (commits, prompts, decisions).

Process diagram

Watch & learn

Study these free videos before or during the exercise. Each embed is chosen to reinforce today's objectives.

Course video

Open on YouTube
Git and GitHub for Beginners (freeCodeCamp) — Commit, branch, push — the baseline every AI workflow needs.

Course video

Open on YouTube
GitHub Actions Tutorial — CI/CD Pipeline — Pipelines that gate AI-generated changes.

Worked example / case study

Scenario

Agent creates branch, implements change, commits, opens PR; you verify the diff includes AI config safely.

Step-by-step

  1. Clarify the outcome in one sentence tied to the exercise below.
  2. Gather grounding context (files, docs, schema, acceptance checks).
  3. Run the primary tool(s): Claude Code, GitHub.
  4. Produce the smallest vertical slice that proves the idea.
  5. Verify with a command, test, screenshot, or side-by-side comparison.
  6. Write down one steering note — what you told the AI when it went wrong.

Sample prompt you can adapt

Role: Senior engineer mentoring an early-career developer (pairing with me).
Task: Git workflows with agents: branches, commits, and pull requests.
Context: Final-year / early-career project (capstone, internship, or junior role).
Constraints:
- Match existing project patterns
- No new dependencies unless justified
- Include tests or a verification checklist
- Call out assumptions explicitly
Output: step plan first, then code/files, then verification commands.

Hands-on exercise

Primary task. Have the agent create a branch, implement a change, write commit messages, and open a PR. Commit your CLAUDE.md, Cursor rules, and prompt cookbook into the same repo so AI configuration is versioned alongside the code it governs — review the diff to verify nothing sensitive was included.

Coaching notes

Add a secret-scan step before pushing.

Steps

  1. Set up or open the workspace required by: Claude Code, GitHub.
  2. Skim today's core concepts and watch the video(s) before prompting.
  3. Execute the task in small commits (or saved artifacts if no-code).
  4. Fill the success checklist below.
  5. Note one surprise and one process improvement for tomorrow.

Success criteria

  • Deliverable matches the exercise description
  • You can explain every AI-generated change in plain language
  • Verification ran (tests, manual check, or published URL)
  • At least one pitfall from this lesson was consciously avoided
  • Artifact saved (repo commit, doc, or published link)

Timebox

Suggested: 90–150 minutes of focused build time after study.

Templates & checklists

AssetPurpose
Prompt stubReuse today's structure (role → task → constraints → format)
Verification checklistTests / manual QA / security skim
Decision logWhat you delegated vs kept human

Copy-paste prompt skeleton

## Goal
Git workflows with agents: branches, commits, and pull requests.

## Context files
- (list paths)

## Constraints
- Stack: (fill)
- Do not: (secrets, drive-by refactors)

## Definition of done
- Have the agent create a branch, implement a change, write commit messages, and open a PR. Commit your CLAUDE.md, Cursor rules, and prompt cookbook into the same repo so AI configuration is versioned alongside the code it governs — review the diff to verify nothing sensitive was included.

Daily reflection (3 minutes)

  • What did AI do well?
  • Where did it confidently fail?
  • What rule will you add to your cookbook/rules file?

Common pitfalls

  • Force-pushing with an agent
  • Committing .env because the agent 'needed it'
  • Useless commit messages ('updates')

Key takeaways

  • PR is the unit of review
  • AI config is code
  • Secrets never belong in prompts or commits
  • Tools (Claude Code, GitHub) change; the judgment skills transfer.

Resources

  • Official docs for: Claude Code, GitHub
  • Course cookbook: keep prompts in a versioned Markdown file in your repo
  • Prior days this week — skim objectives if you skipped ahead

Self-paced lesson — Mastering AI-Assisted Development & Vibe Coding — Day 29 of 65.

New free lessons and course updates. Unsubscribe from any email.