As a developer, you’ve gone into software likely because you enjoy writing code. This isn’t a chore for you, and you get some degree of fulfillment from it. If you’re reading this, you’re probably using agentic devtools to improve your productivity, and take away some of the toil that comes with dev work.
Why should agents get to do all the fun parts of software dev, like writing code? Claude Code (the world’s favorite AI coding agent) has a feature that allows you to make agentic dev more active.
Here’s how you can write code alongside Claude Code, instead of through pure natural language prompts.
Why pair program with AI agents?
Agents can generate code incredibly fast, and at volumes that are tough for humans to truly digest. Many devs end up turning off their brains at a certain point, because understanding the agent’s code is much slower than prompting fast and getting a working result.
This leads to devs accepting agentic code suggestions blindly. It’s a slippery slope for sure: if 90% of an LLM’s suggestions are good, why should you have to sift through all of them with a fine-toothed comb, especially if you hardly find anything off? Then next thing you know, your agent accidentally corrupts your database or changes your file permissions.
Pair programming with an agent keeps you, as the developer, engaged and in the driver’s seat. You’re actively thinking through every choice, being intentional. It’s more akin to the mindset you get into when you’re 100% writing code.
Plus, AI agents are good for many things beyond picking up coding tickets. Thanks to their LLMs' wide knowledge bases, they can explain things pretty well, and pick up on niche software patterns. They can step into that “pair” role and guide you. This brings them closer to human-human pair programming
Claude Code output styles
In August 2025, Anthropic introduced a new feature for changing how Claude Code interacts with a user. Output styles can help extend CC beyond its popular use cases, and Anthropic suggests this can make CC act as any kind of agent (with the same core read/write/execute/list capabilities).
An output style for Claude Code is functionally the same as a system prompt. Claude’s default output style is concise, and targeted mainly at solving software engineering tasks.
CC includes two other built-in output styles, which are (in our opinion) more conducive to pair programming.
Explanatory output style
To set: /output-style explanatory
Claude Code’s explanatory mode is similar to the default system prompt, but offers educational insights along the way. This is a good mode for newer devs who don’t want CC to do all the thinking for them, and are hoping to stay engaged during agentic dev tasks.
CC will add little “insight” blocks within its responses. These are kind of like pro tips, or just extra background info. Since default CC is concise, this is helpful for getting more complete, detailed answers.
Sample prompt:
look at the CLI docs, and tell me what can be improved in the scope of DevEx
CC explanatory mode response (excerpt):
...
Strategic Long-term Enhancements
7. **Progressive disclosure with expandable sections**
8. **Integration examples with popular IDEs and tools**
9. **Video walkthroughs for complex workflows**
10. **Interactive CLI tutorial or guided setup**
★ Insight ─────────────────────────────────────
The current documentation is comprehensive but lacks the user-centric
design principles that make modern developer tools delightful to use. The
biggest opportunities are in restructuring content around workflows and
reducing friction in the getting-started experience.
──────────────────────────────────────────
Learning output style
To set: /output-style learning
Learning mode is more interactive than default or explanatory mode. It gives the user small programming tasks to complete during development, so they can contribute code. It’s really beneficial for junior engineers looking for a pair programming setup, as it will break down tasks, assign them, and then give feedback on the completed snippet.
This was our favorite CC output style, since it let us pick up fun coding tasks and walked us through the why/how of every action.
Sample prompt:
look at the CLI docs, and tell me what can be improved in the scope of DevEx
CC learning mode response (excerpt):
Your Task: In docs/CLI.mdx, create a new “Quick Start” section`
that should appear right after line 13 (after the opening description).
Look for TODO(human). This section should provide developers with the
fastest possible path from installation to their first successful CLI
interaction.
Guidance: Consider what a developer most wants to accomplish when they`
first install the CLI - probably seeing their environments and confirming
everything works. Think about the psychological impact of early success
vs. getting stuck on setup details. The section should be concise (3-5
commands max) and include a verification step that shows success.
Creating your own custom output style
Claude Code is super customizable, and most of this can be done via natural language in Markdown files. You can create your own output style (which is a system prompt for CC) by running:
/output-style:new [name] [verbose description]
Remember, everything that CC knows about software engineering lives in the default output style. You’ll need to re-enlighten it here if you want it to be a strong software engineering pair.
Once you provide a description of what output style you’d like, Claude will generate a markdown file, inferring what other characteristics it should have. You can find it in your ~/.claude/output-styles/ directory. You’ll want to tweak this to fit what you had in mind.
Changing Claude Code’s system prompt
There are a few ways to change/augment CC’s system prompt.
Option 1: with output styles (recommended)
Claude’s output styles are system prompts. If you want to completely override Claude’s default personality, skillset, and behavior, this is how you can do it.
This means you’ll need a super high-quality, detail-oriented prompt. Claude Code can help you write one, but don’t expect it to be as optimized as CC’s default prompt. This is still a great exercise for prompt engineers, and also valuable for those who want to use a terminal-based agent for miscellaneous non-dev tasks.
To recap: you’ll do this by launching a Claude Code session and running:
/output-style:new [name] [verbose description]
Option 2: with append-system-prompt
If you want to keep the general behavior of Claude Code’s system prompt, but add a few more high-priority instructions, you can use the --append-system-prompt flag. As part of the system prompt, CC will prioritize this over any other config settings (e.g. CLAUDE.md) or prompts.
You can append your own instructions by running:
claude --append-system-prompt "Never commit to main. Alert me when a new feature does not have unit tests written for it"
Option 3: with CLAUDE.md
Your CLAUDE.md file is not a system prompt. Rather, it’s a prioritized instruction that Claude Code will refer to one tier below the instructions in the system prompt.
Usually, A CLAUDE.md file is stored at the project level, and is automatically pulled into context when you launch a session. It’ll typically store instructions and context relevant to a project, which will save you tokens and guarantee better outputs.
You can run the /init slash command to create it, or add one manually to your project’s root directory.
Keep your dev skills sharp
A hybrid of agentic and human dev can be a really refreshing balance for many programmers. You can keep learning good patterns, stay engaged during a dev session, and use your brain in a different way (vs. pure agentic dev). Thankfully, you’ve got plenty of ways to customize this to your liking with Claude Code’s output styles. You can get a more fulfilling dev experience just by toggling system prompts.
Happy coding!
