Imported from Ngoson2004/Face-Recognition-System (AGENTS.md). Install upstream with npx skills add Ngoson2004/Face-Recognition-System. Copyright stays with the author.

AGENTS.md

Behavioral guidelines to reduce common LLM coding mistakes. These instructions are copied into this repository so Jarvis can start from this folder on any machine without depending on the parent directory.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

• State assumptions explicitly. If uncertain, ask.
• If multiple interpretations exist, present them instead of picking silently.
• If a simpler approach exists, say so. Push back when warranted.
• If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

• No features beyond what was asked.
• No abstractions for single-use code.
• No flexibility or configurability that was not requested.
• No error handling for impossible scenarios.
• If 200 lines could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

• Do not improve adjacent code, comments, or formatting.
• Do not refactor things that are not broken.
• Match existing style, even if you would do it differently.
• If you notice unrelated dead code, mention it instead of deleting it.

When your changes create orphans:

• Remove imports, variables, and functions that your changes made unused.
• Do not remove pre-existing dead code unless asked.

The test: every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

• "Add validation" -> "Write tests for invalid inputs, then make them pass"
• "Fix the bug" -> "Write a test that reproduces it, then make it pass"
• "Refactor X" -> "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] -> verify: [check]
2. [Step] -> verify: [check]
3. [Step] -> verify: [check]

Strong success criteria let you loop independently. Weak criteria like "make it work" require clarification.

Repository Scope

Work in this repository by default:

C:\Users\Admin\Uni\AppliedML\final_group_project\Face-Recognition-System

Jarvis durable memory is intentionally fixed to:

C:\Users\Admin\Uni\AppliedML\final_group_project\Face-Recognition-System\app_memory

Use C:\Users\Admin\Knowledge-Base-vault only when needed. Needed means the user explicitly asks for that vault, the task requires broader personal/project knowledge not present in this repo or app_memory, or local context is insufficient to answer safely.

Do not make the vault a runtime dependency. Do not copy unrelated vault content into this repo. Do not edit the vault unless the user explicitly asks.

Keep code changes surgical and scoped to the request. Prefer existing project patterns over new abstractions.