Deep Dive

7 Codex & Claude Tricks That Turn You Into a One-Person Engineering Team

Seven documented Codex and Claude Code features that help one developer plan, build, test and review like a small team.

Researched & written October 2026 · ~10 min read · Sources cited throughout

🧑‍💻 The problem with building alone

When you build software alone, you do every job yourself. You plan, write the code, test it and review it. Nobody checks your work. And when you open an old project, you can lose hours just working out how it fits together.

An AI coding agent can take some of that load. It's an AI that works inside your project: it reads your files, changes code and runs commands, such as your tests. You tell it what you want in plain English.

This article covers the two best-known agents, Codex from OpenAI and Claude Code from Anthropic, with seven tricks and six smaller tips. Every feature comes from the official docs.

Key points
In this article
  1. Codex and Claude Code side by side
  2. Seven tricks, one at a time
  3. One day, two agents
  4. Six more tips
  5. Staying safe and common mistakes
  6. Where to start and the cheat sheet

📖 Words you'll see in this article

TermWhat it means
TerminalThe text window where you type commands. A CLI is a tool you use there.
IDEThe app you write code in, such as VS Code.
BranchA separate line of work in Git, the tool that tracks code changes.
Pull request (PR)A request to add a branch's changes to the main code, so they can be reviewed first.
TokensSmall chunks of text an AI reads and writes. The more tokens a task uses, the more of your plan's usage it takes.
CITools that run checks automatically every time code changes.

⚖️ Codex and Claude Code side by side

Most features exist in both, under different names. Figure 1 lines them up.

Comparison table of OpenAI Codex and Anthropic Claude Code. Codex: included in every ChatGPT plan, with Codex Cloud on Plus or higher, AGENTS.md with a 32 KiB default cap, /plan, subagents on by default, skills in .agents/skills called with $name, hooks.json trusted via /hooks, worktrees and cloud tasks with up to 4 attempts, /review and @codex review, codex exec. Claude Code: Pro, Max, Team, Enterprise or API key, CLAUDE.md or AGENTS.md, Shift+Tab or /plan, built-in Explore and Plan subagents, skills in .claude/skills called with /name, hooks in settings.json, claude --worktree and claude --cloud, /code-review and /security-review, claude -p.
Figure 1. Each feature's name in both tools, from the official docs (October 30, 2026). The "reach for" lines are our advice. Tap any figure to open it full size.
Which one should I start with?

🛠️ Seven tricks, one at a time

Each trick explains the idea first, then shows how to do it in each tool.

1. Give the agent a notes file

Both tools read a notes file from your project at the start of every session. Think of it as onboarding docs for the AI: how to run the tests, and what not to touch.

Start with the command that runs your tests. Anthropic calls it "the single most useful line" in the file.

## Commands
- Run tests: npm test

## Rules
- Never edit files in /migrations by hand.

2. Ask for a plan before any code

In plan mode, the agent researches your code and writes a plan for you to approve. In Claude Code, it can't edit your files until you approve the plan. You fix the plan first, then let it start. Fixing a plan takes a minute; undoing wrong changes takes much longer.

It's also the easiest way into a project you didn't write. The agent reads all the code; you read a short summary.

Try this/plan Explain how an order moves from the cart to payment. Then propose how to add discount codes, and list the files you'd change.

3. Give the agent a test it can run

An agent can't tell whether its work is right unless it can check. Tests give it that check, because they pass or fail. Anthropic's advice: "Give Claude something it can run that comes back pass or fail."

For bugs, ask for the test first. A test that fails before the fix and passes after it proves the bug is gone.

Try thisCheckout shows a 500 error when the cart is empty. Error message: [paste]. Write a failing test that shows the bug, fix it, then run all the tests.

4. Hand side jobs to subagents

In a long session, the AI has more to keep in mind and can forget early details. A subagent is a helper the main agent sends off to do one focused job, like searching the code. It works separately and reports back only its answer.

Good to know: OpenAI says subagents "consume more tokens than comparable single-agent runs," so they use up your limits faster.

5. Run several agents at the same time

Two agents in the same folder can overwrite each other's changes. The fix is a Git worktree: a second copy of your project on its own branch.

You can also send work to the cloud, so it runs on the provider's computers instead of your laptop:

Figure 2. One person doing five jobs in a row, then agents sharing the middle jobs. Illustrative, not measured timings. Can't see the video? Open the GIF version.

Your job becomes writing clear tasks and checking results (Figure 3). Before letting agents run alone, read our guide to AI agent guardrails.

Workflow diagram. Step 1: you plan the work with /plan. Step 2: three jobs run side by side: Claude Code builds the login page in a worktree (claude --worktree feature-auth), a Codex Cloud task fixes a flaky test (codex cloud exec --env my-app --attempts 3), and a read-only Claude Code Explore subagent maps the payments code. Step 3: tests and hooks check the code changes. Step 4: the other agent reviews each pull request (@codex review, /code-review). Step 5: you read and merge.
Figure 3. Plan, split the work, let tests check it, cross-review, merge. An example, not measured data.

6. Automate chores with skills and hooks

A skill is a saved set of instructions for a job you repeat, like "prepare a release." It's a folder with a SKILL.md file inside.

A skill only needs a name, a description that says when to use it, and the steps. This one works in either tool, saved as release-notes/SKILL.md in the folder above:

---
name: release-notes
description: Writes release notes from the commits since the last tag. Use when preparing a release.
---
1. List the commits since the last Git tag.
2. Group them into Features, Fixes and Other.
3. Add the notes to the top of CHANGELOG.md.

An agent can still skip a skill's advice. A hook can't be skipped: it's a small script that runs automatically at a set moment, every time. Anthropic says hooks make "certain actions always happen rather than relying on the LLM to choose to run them." For example, a hook can run your code formatter after every edit, or block edits to .env, the file that usually holds passwords.

Here's Anthropic's documented formatter hook. It goes in .claude/settings.json and needs jq and Prettier installed:

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "jq -r '.tool_input.file_path' | xargs npx prettier --write"
          }
        ]
      }
    ]
  }
}

Claude Code keeps hooks in its settings file. Codex has hooks too, in hooks.json, and asks you to trust each one before it runs. Both agents also run inside scripts and CI, without a chat window, using codex exec or claude -p.

7. Let one agent review the other

Mistakes are hard to spot in your own code, because you know what you meant. So ask the agent that didn't write a change to review it.

Good to know: Anthropic's Code Review "never approves or blocks the pull request." The agents point out problems; you decide what gets merged.

Matrix of seven tricks against six roles. Project notes file: mainly onboarding, also tech lead. Plan mode: mainly tech lead, also onboarding. A check it can run: mainly QA, also developer. Subagents: mainly developer, also reviewer and onboarding. Parallel agents: mainly developer, also tech lead. Skills and hooks: mainly DevOps, also developer and QA. Cross review: mainly reviewer, also QA. Each row lists a task to try it on.
Figure 4. Which team role each trick helps you cover. Our own mapping, not measured data.

📅 Putting it together: one day, two agents

Here's how the tricks fit together on a normal working day. It's an example, not a recorded session.

  1. Tech lead. You open Claude Code in plan mode and ask how sign-up works today, then for a plan to add Google login. You fix one step and approve the plan.
  2. Developer. Claude Code builds the feature in its own worktree. Meanwhile, a Codex Cloud task fixes the flaky test you've been ignoring for weeks.
  3. QA. Both agents run the test suite before saying they're done, and a hook formats every file Claude Code touched.
  4. Reviewer. You comment @codex review on Claude's pull request and run /code-review on Codex's.
  5. Decision maker. You read both reviews and the changes, ask for one fix, and merge.

That's four roles covered in one day, and you still made every decision.

⚡ Six more tips worth knowing

🔒 Stay safe while agents work

An agent runs real commands on your computer. So decide how much it may do without asking you first.

⚠️ Common beginner mistakes

🚀 Where to start

  1. Run /init to create a notes file, and add your test command.
  2. Use plan mode for your next feature, and fix the plan before you say yes.
  3. For every bug, ask for a failing test first.
  4. Run one task in a worktree or the cloud, and have the other agent review it before you merge.

📋 Cheat sheet

The main commands from this article in one place.

JobCodexClaude Code
Create a notes file/init (writes AGENTS.md)/init (writes CLAUDE.md)
Plan first/planShift+Tab until plan mode shows, or /plan
Work in parallelWorktreesclaude --worktree <name>
Send a task to the cloudcodex cloud exec --env <id> "<task>"claude --cloud "<task>"
Use a skill$skill-name/skill-name
Review changes/review, @codex review/code-review, /security-review
Run in scripts and CIcodex execclaude -p
Connect a toolcodex mcp addclaude mcp add
Set permissions/permissionsShift+Tab (modes), /permissions (rules)
Undo an editUse GitEsc twice or /rewind

And the three prompts to copy:

/plan Explain how an order moves from the cart to payment. Then propose how to add discount codes, and list the files you'd change.

Checkout shows a 500 error when the cart is empty. Error message: [paste]. Write a failing test that shows the bug, fix it, then run all the tests.

Use a subagent to find every place this app sends an email, and list the files.

✅ Conclusion

These tools don't replace a team's judgment. What changes is where your time goes: less typing, more planning and checking.

Use Codex for clear jobs you can hand to the cloud, and Claude Code for work you want to guide closely on your own machine. Then let each review the other. That gives a solo developer what's usually missing: a second pair of eyes on every change.