I like to analyze codebases I start working on, or that I left for months. I ask my coding assistant, case in point, Copilot CLI: "Analyze the following codebase and report to me improvements and possible bugs."  It's vague enough to leave room for crappy feedback, but also for some interesting insights. I did it last week on a code base. Copilot returned a list of a dozen items. I asked it to create a GitHub issue for each, with the relevant labels, including priority. On three separate issues, it mentioned that a library or GitHub Action version didn't exist. On all of them, it was plain wrong. I used a version more recent than the data it was trained on. Closed as won't fix. The next step was to triage each remaining item, both independently and using Copilot. Some of them felt a bit fishy, some of them felt solid. In the end, I closed about half of them. Four remained. They were pretty good. I wanted to act upon them in the most productive way  possible, so I decided to use sub-agents. Using Sub-Agents When newbies decide to use sub-agents, chances are they'll waste a lot of time. Because they are autonomous, you want to give them every possible bit of information so that they choose the best course of action without input. You must qualify every issue independently. While  you can still technically interact with the sub-agents when they work, it drops their value significantly. every However, this work can be done in the previous triage step. If you have enough data to accept or close the item, there's a high chance you dug to get enough details. Refer to How I Use Claude Code, and especially the Annotation Cycle section, for more details. How I Use Claude Code Annotation Cycle Here's my prompt to trigger the agents, formatted for you, not for the agent. Feel free to improve it, and don't hesitate to give me feedback. For each issue X, Y, & Z, I want you to launch a sub-agent that:

Fetch the issue using the gh tool
Read its description
Create a dedicated branch using the git worktree command
Implement the feature or fix the issue
If the feature/issue warrants it, create a test or tests around it
All tests must pass before you continue
Commit using a semantic commit
Push it on its own branch to GitHub
Create a PR with this branch, using the following naming pattern For each issue X, Y, & Z, I want you to launch a sub-agent that: Fetch the issue using the gh tool
Read its description
Create a dedicated branch using the git worktree command
Implement the feature or fix the issue
If the feature/issue warrants it, create a test or tests around it
All tests must pass before you continue
Commit using a semantic commit
Push it on its own branch to GitHub
Create a PR with this branch, using the following naming pattern Fetch the issue using the gh tool gh Read its description Create a dedicated branch using the git worktree command git worktree Implement the feature or fix the issue If the feature/issue warrants it, create a test or tests around it All tests must pass before you continue Commit using a semantic commit Push it on its own branch to GitHub Create a PR with this branch, using the following naming pattern Two things of note. First, Copilot connects to the GitHub MCP Server by default, but only in read-only mode. If you want to actually create (or update) issues, my advice is to use gh. Authenticate in a terminal with it, and run Copilot CLI in the same terminal. It will allow Copilot to interact with GitHub with all permissions. gh Then, git branch works in the same folder. Each agent would step on the other's toes. Git worktrees solve the problem elegantly. In short, the command allows mapping a branch to a dedicated folder on the filesystem: git branch Git worktrees A git repository can support multiple working trees, allowing you to check out more than one branch at a time. With git worktree add  a new working tree is associated with the repository, along with  additional metadata that differentiates that working tree from others in  the same repository. The working tree, along with this metadata, is  called a "worktree". A git repository can support multiple working trees, allowing you to check out more than one branch at a time. With git worktree add  a new working tree is associated with the repository, along with  additional metadata that differentiates that working tree from others in  the same repository. The working tree, along with this metadata, is  called a "worktree". git worktree add Fun fact: I have known worktrees for some time, but I never had a use case for them. The obvious benefit of using sub-agents is parallel processing. While you must research each item sequentially, sub-agents can implement them in parallel. However, IMHO, the main benefit is context isolation. context isolation Context Engineering Sub-agents are a boon: each one starts with a fresh context. You don't pollute the main context with irrelevant data. As a reminder, the context is everything the agent will act upon: System prompts, e.g., "You are an expert Java developer and architect with more than 20 years of experience."
User prompts, e.g., "Refactor this class to use immutable values when possible."
Additional information set by RAG
Previous messages, i.e., the conversation
Available tools
Tools' potential output
etc. System prompts, e.g., "You are an expert Java developer and architect with more than 20 years of experience." e.g. User prompts, e.g., "Refactor this class to use immutable values when possible." e.g. Additional information set by RAG Previous messages, i.e., the conversation i.e. Available tools Tools' potential output etc. The temptation is huge to put everything in the context. However, context capacity is limited and is measured in tokens. A  perfectly-crafted context contains all the necessary data for the task at hand, but nothing more. As engineers, we strive for efficiency, not for perfection. For every unrelated task, we should start a new context.  Interestingly enough, Claude Code recently started offering context  optimization after each request. It's up to you to decide whether to  keep it or not. Conclusion We now manage a team of agents instead of a team of junior developers. The situation is somehow similar. You must be very clear about what you want. You must design in detail upstream. Those you delegate to won't probably ask questions, and might end up in the wrong place. You need to carefully review the results. There are two main differences, though. You'll get outputs in minutes, not days. On the flip side, we aren't teaching the next  generation of developers. It makes sense at every company's level: why train junior developers if the AI can replace them? Market numbers already show this trend. But seniors aren't born. They are former junior developers who went through  all the steps. For me, it doesn't change a thing. In the grand scheme of  things, user companies are going to be very sorry about their shortsightedness in a couple of years, once they realize how dependent they have become on vendors and when they face a shortage of seniors. very To go further: To go further: How I Use Claude Code How I Use Claude Code How I Use Claude Code Originally published at A Java Geek on April 5th, 2026. Originally published at A Java Geek on April 5th, 2026. A Java Geek

GitHub

Want to Have Successful OpenTelemetry Projects? Implement This One Tip

AI Subagents: What Works and What Doesn't

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

10 Essential Java Libraries - How Essential Are They Really?

The Noonification: How Often Do NFTs Pass The Howey Test? (1/13/2023)

Darwin's Hybrid Intelligence to Align AI & Human Goals for Startups & VCs

The Noonification: White Man (11/26/2022)

The Noonification: The Metaverse is a Sh*tshow (11/2/2022)

100 Days of AI Day 1: From Newsletter to Podcast, Leveraging AI for Audio Transformation

10 Essential Java Libraries - How Essential Are They Really?

The Noonification: How Often Do NFTs Pass The Howey Test? (1/13/2023)

Darwin's Hybrid Intelligence to Align AI & Human Goals for Startups & VCs

The Noonification: White Man (11/26/2022)

The Noonification: The Metaverse is a Sh*tshow (11/2/2022)

100 Days of AI Day 1: From Newsletter to Podcast, Leveraging AI for Audio Transformation

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps