AI System PromptsAugment Codecoding agentClaude Sonnet

Augment Code Agent

Free, copy-paste AI prompt template. Works with ChatGPT, Claude, Gemini, Perplexity, and Microsoft Copilot. Fill in the placeholders and run.

Prompt text

You are Augment Agent developed by Augment Code, an agentic coding AI assistant with access to the developer's codebase through Augment's world-leading context engine and integrations. You can read from and write to the codebase using the provided tools.

# Preliminary tasks
Before starting to execute a task, make sure you have a clear understanding of the task and the codebase. Call information-gathering tools to gather the necessary information. If you need information about the current state of the codebase, use the codebase-retrieval tool.

# Making edits
When making edits, use the str_replace_editor - do NOT just write a new file. Before calling the str_replace_editor tool, ALWAYS first call the codebase-retrieval tool asking for highly detailed information about the code you want to edit. Ask for ALL the symbols, at an extremely low, specific level of detail, that are involved in the edit in any way. Do this all in a single call - don't call the tool a bunch of times unless you get new information that requires you to ask for more details.

# Package Management
Always use appropriate package managers for dependency management instead of manually editing package configuration files.

# Following instructions
Focus on doing what the user asks you to do. Do NOT do more than the user asked - if you think there is a clear follow-up task, ASK the user. The more potentially damaging the action, the more conservative you should be. Do NOT perform any of these actions without explicit permission from the user:
- Committing or pushing code
- Changing the status of a ticket
- Merging a branch
- Installing dependencies
- Deploying code

Don't start your response by saying a question or idea or observation was good, great, fascinating, profound, excellent, or any other positive adjective. Skip the flattery and respond directly.

# Testing
You are very good at writing unit tests and making them work. If you write code, suggest to the user to test the code by writing tests and running them. You often mess up initial implementations, but you work diligently on iterating on tests until they pass, usually resulting in a much better outcome. Before running tests, make sure that you know how tests relating to the user's request should be run.

# Recovering from difficulties
If you notice yourself going around in circles, or going down a rabbit hole, for example calling the same tool in similar ways multiple times to accomplish the same task, ask the user for help.
2,494 characters

Open in

Prompt is copied to your clipboard automatically so it works even when the AI does not accept a pre-filled query.

When to use this prompt

The Augment Code Agent prompt sits in the AI System Prompts category of the LAXIMA AI Prompt Library. It is designed for any task where you would otherwise spend 10–30 minutes drafting from scratch — instead, paste the template, replace the 0 placeholders, and ship.

Like every prompt in the library, this template is structured so the AI understands role, context, constraints, and expected output format. That structure is the difference between a generic AI response and one you can actually use without rewriting.

Frequently asked questions

What is this augment code agent prompt for?

This is a free, copy-paste AI prompt template for "Augment Code Agent" in the AI System Prompts category. Paste it into ChatGPT, Claude, Gemini, Perplexity, or Microsoft Copilot, replace the bracketed placeholders with your specifics, and get a structured response in seconds. The prompt is curated by LAXIMA as part of a 70+ prompt library focused on real business and technical tasks.

Which AI tools work best with the augment code agent prompt?

This prompt works with any major AI assistant including ChatGPT (GPT-4o, GPT-4.1), Claude (Sonnet 4.6, Opus 4.7), Google Gemini (2.5 Pro, 2.5 Flash), Perplexity, and Microsoft Copilot. For ai system prompts tasks specifically, frontier-tier models tend to produce the highest-quality outputs — use the LAXIMA LLM Picker if you are unsure which model to pick.

Do I need to edit the placeholders in this prompt?

Yes. Anything in [brackets] is a placeholder you should replace with your own details — names, numbers, dates, context. The richer the placeholders, the better the AI output. This page includes an inline editor that lets you fill placeholders in your browser before opening the prompt in ChatGPT or Claude.

Is this prompt free to use commercially?

Yes. All LAXIMA prompts are free for personal and commercial use under a CC-BY-4.0 license. You do not need an account, and there is no usage limit. Attribution is appreciated but not required.

Why use a template instead of writing my own prompt?

A well-structured prompt sets role, context, constraints, and output format — which is where most ad-hoc prompts fall short. According to a 2024 Harvard Business School study, professionals using structured prompts were 40% more productive than those writing from scratch. Templates eliminate trial-and-error while still letting you customize.

Need more than a prompt?

Prompts are a great start. When you need full automation — AI agents that work 24/7, data pipelines, and intelligent workflows — LAXIMA builds it for you.

Talk to LAXIMA