the-augster
starsforks
How to install the-augster?
julesmons/the-augster
$git clone https://github.com/julesmons/the-augsterDesigned For: Augment Code Extension (or similar integrated environments with tool access) Target Models: Advanced LLMs like Claude 3.5/3.7/4, GPT-5/4.1/4o, o3, etc.
README.md
| 1 | # The Augster: An 'additional system' prompt for the Augment Code extension in attempt to improve output quality. |
| 2 | |
| 3 | **Designed For:** Augment Code Extension (or similar integrated environments with tool access) |
| 4 | **Target Models:** Advanced LLMs like Claude 3.5/3.7/4, GPT-5/4.1/4o, o3, etc. |
| 5 | |
| 6 | > [!IMPORTANT] |
| 7 | > When updating to a newer version, ensure to remove any outdated information stored in "memories" (or similar persisted storage). |
| 8 | |
| 9 | ## Overview |
| 10 | "The Augster" is a supplementary system prompt that aims to transform an LLM, preconfigured for agentic development, into an intelligent, dynamic and surgically-precise software engineer. |
| 11 | This prompt has been designed as a complete override to the the LLM's core identity, principles, and workflows. Techniques like [Role Prompting](https://docs.claude.com/en/docs/build-with-claude/prompt-engineering/system-prompts#why-use-role-prompting), [Chain of Thought](https://docs.claude.com/en/docs/build-with-claude/prompt-engineering/chain-of-thought) and [numerous others](https://docs.claude.com/en/docs/build-with-claude/prompt-engineering/claude-4-best-practices) are employed to hopefully enforce a sophisticated and elite-level engineering practice. |
| 12 | |
| 13 | In short; This prompt's primary goal is to force an LLM to really think the problem through and ultimately solve it the *right* way. |
| 14 | |
| 15 | ## Features |
| 16 | This prompt includes a mandatory, multi-stage process of due diligence: |
| 17 | 1. **Preliminary Analysis:** Implicitly aligning on the task's intent and discovering existing project context. |
| 18 | 2. **Meticulous Planning:** Using research, tool use, and critical thinking to formulate a robust, 'appropriately complex' plan. |
| 19 | 3. **Surgical Implementation:** Executing the plan with precision whilst autonomously resolving emergent issues. |
| 20 | 4. **Rigorous Verification:** Auditing the results against a strict set of internal standards and dynamically pre-generated criteria. |
| 21 | |
| 22 | This structured approach attempts to ensure that every task is handled with deep contextual awareness, whilst adhering to a set of strict internal `Maxims`. |
| 23 | Benefits of this approach should include a consistently professional, predictable, and high-quality outcome. |
| 24 | |
| 25 | ## Repository |
| 26 | This repository mainly uses three branches that all contain a slightly different version/flavor of the project. |
| 27 | Below you’ll find an explanation of each, in order to help you pick the version that best suits your needs. |
| 28 | |
| 29 | * The `main` branch contains the current stable version. |
| 30 | - "Stable" meaning that various users have tested this version for a while (through general usage) and have then reported that the prompt actually improves output quality. |
| 31 | - Issues identified during the testing period (`development` branch) have been resolved. |
| 32 | |
| 33 | * The `development` branch contains the upcoming stable version, and is going through the aforementioned testing period. |
| 34 | - This version contains the latest changes and improvements. |
| 35 | - Keep in mind that this version might be unstable, in the sense that it could potentially contain strange behavior that was introduced by these aforementioned changes. |
| 36 | - See this branch as a preview or beta, just like VSCode Insiders or the preview version of the augment code extension. |
| 37 | - After a while of testing, and no more new problems are reported, these changes are merged to `main`. |
| 38 | |
| 39 | * The `experimental` branch is largely the same as the `development` branch, differing only in the sense that the changes have a more significant impact. |
| 40 | - Changes might include big/breaking changes to core components, or potentially even a comprehensive overhaul. |
| 41 | - This version usually serves as an exploration of a new idea or concept that could potentially greatly improve the prompt, but alters it in a significant way. |
| 42 | - When changes on this branch are considered to be a viable improvement, they are merged to the `development` branch, refined there, then ultimately merged to `main`. |
| 43 | |
| 44 | ## Installation |
| 45 | 1. Install the [Augment Code](https://www.augmentco |
People who liked this also viewed
6 picksType
- components-helperBased on the docs to provide code prompt files for vue component libraryPromptsNov 2023
- VibeCode-Protocol-SuiteA comprehensive suite of protocols, meta-prompts, and orchestration tools designed to streamline software development workflows, project management, and team collaboration. Includes the VibeCode Protocol Suite with web interface, user manuals, and reusable templates for efficient development processes.PromptsJul 2026
- Promptable-web-sdkWeb SDK for Promptable Website.PromptsDec 2022
- LLMFlexA python package for developing AI applications with local LLMs.PromptsJan 2025
- cli-repo-to-promptexport any codebase to a single LLM-ready markdown promptPromptsJul 2026
- Files2PromptVS Code extension to copy files for an LLM promptPromptsApr 2025
