25 workflows · each linked to the post, repo or doc
Claude Code use cases: 25 real workflows
Real ways people use Claude Code, from the habits of the team that built it to a local lead-gen business it built end to end. Each recipe links to the post, repo or doc it came from and gives you a prompt and steps to copy.
Some pair Claude Code with Codex: one plans or builds, the other reviews or executes. Those are grouped below.
Making money with Claude
A Skill that takes a 45-minute episode and writes 15 platform-specific posts in the client's voice.
A fast site with location pages, a simple CRM for leads, quotes and bookings, automated follow-ups, then search ads.
Coding workflows
Treat the workflow, not the agent, as the product
Replies describe running Claude Code headless with claude -p from scripts and cron, wrapped in a simple state machine: task record, bounded run, artifacts, checks, human approval.
Learn new features with the built-in guide subagent
Ask the bundled guide subagent to explain a new feature's purpose, limits and best practices instead of searching docs.
CLAUDE.md upkeep + log-file debugging loop
A long list of field-tested habits; two that pay off most are keeping CLAUDE.md current and piping dev-server output into a log file the agent can read while it debugs.
@claude in pull requests (GitHub Action)
Anthropic's official action runs Claude Code on your own GitHub runner to review PRs, answer @claude questions and implement small changes.
Get notified when your coding agent needs you
He had Claude Code configure itself so he gets a notification whenever it is waiting on input or a permission.
Split a big task into a DAG of small subagents
A Claude Code plugin that breaks work into atomic tasks with dependencies and gives each subagent only the context it needs, in parallel worktrees.
The Claude Code team's habits: parallel worktrees, plan first, skills
The creator of Claude Code shared his team's habits: run 3–5 sessions in parallel worktrees, start complex work in plan mode, and turn anything you do daily into a skill.
Research → annotated plan → implement
Make the agent write its research and plan to markdown files, mark up the plan yourself until it's right, and only then let it build.
Install specialist subagents from a community library
A large curated collection (161+ when we checked) of Claude Code subagent definitions across 10 categories that you can drop into a project.
Claude Code with Codex and other agents
Run several coding agents on a kanban board
Each agent gets its own git worktree and terminal; a board sorts them into Idle, Working and Needs Input so you only look at the ones blocked on you.
Claude Code builds, Codex reviews
Use one agent as the builder and the other as a second pair of eyes that hunts bugs and challenges architecture before you accept the result.
Claude Code ↔ Codex hand-off with a shared changes.log
Two agents pass one project back and forth through a single log file each must read before starting and append to after finishing, so the second agent can review the first.
Split work: Claude Code reasons, Codex executes
A backend developer on 20+ microservices routes reasoning-heavy debugging to Claude Code and repetitive, parallel work (tests, docs, edits) to Codex, with a task-state log between them.
Route stuck bugs to the other agent
When one agent loops on a bug for hours, hand it to a different agent; this developer settled on Claude Code for features and Codex for bug fixes and review.
A personal operating contract for Claude Code and Codex
One standing contract both agents load automatically: Linear ticket first, Claude plans, Codex reviews, isolated worktrees, test-first, and independent review before any PR.
Tell Claude and Codex how to use your second brain
Standing custom instructions that force agents to read your company and personal brains before every task, flag conflicts, and propose exact edits only after you approve.
One shared memory for a mixed agent fleet
Claude Code, Codex, several Hermes profiles and Grok share one self-hosted memory over MCP; each writes an evening summary and a morning digest spreads the lessons to all.
Voice notes → Claude cleans → Codex executes
Speak rough thoughts into Obsidian, let Claude Code turn them into clean prompts, then run and critique those prompts in separate Codex threads.
Beyond code
Have Claude Code run a music video production
Claude Code ran the production of a music video: Midjourney stills, Seedance 2.5 motion, and every graphic drawn in code on the beat.
Organize your files into a 'digital brain' for Claude Code
Instead of pasting the same context into a chatbot over and over, he organized 5,000+ files into one structure Claude Code can read, so answers come back with full context.
Tag a trip's spending from your notes (hledger)
Keep a plain-text ledger in the same vault as your trip and project notes; the agent reads the notes, finds every related transaction, asks about the ambiguous ones, tags them and writes a cost summary.
5-minute daily ledger reconcile
A daily routine: the agent processes yesterday's receipts and pasted bank lines into a ledger file, you check balances against the bank yourself, then commit.
A manifest file for agent-made social posts
Generate posts in one session and publish in another by tracking each post's outline, status and schedule in a manifest file.
Get the next money recipe. Free.
New recipes every week, plus the top 10 agent setups pack. One email, no spam.
Unsubscribe anytime. Privacy
More guides: Make money with AI agents · AI voice agent business · AI agent agency ideas · Grok Bot use cases