Skip to content

Expand CLAUDE.md with coding and behavioral guidelines - #17

Merged
gitricko merged 1 commit into
mainfrom
gitricko-patch-1
May 25, 2026
Merged

gitricko merged 1 commit into
mainfrom
gitricko-patch-1

Conversation

@gitricko

Copy link
Copy Markdown
Owner

Added behavioral guidelines for LLM coding practices.
This pull request adds a new section to the CLAUDE.md file, providing behavioral guidelines for agents to reduce common LLM coding mistakes. The guidelines emphasize caution, simplicity, minimalism, and goal-driven development, aiming to improve code quality and maintainability.

Guidelines for agent behavior:

  • Added a "For Agents" section outlining behavioral guidelines to reduce coding mistakes, including principles such as thinking before coding, prioritizing simplicity, making surgical changes, and defining clear success criteria.

Added behavioral guidelines for LLM coding practices.
Copilot AI review requested due to automatic review settings May 25, 2026 14:24
@gitricko
gitricko merged commit a2d946e into main May 25, 2026
4 of 5 checks passed
@gitricko
gitricko deleted the gitricko-patch-1 branch May 25, 2026 14:26

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR expands CLAUDE.md by adding a new “For Agents” section that documents behavioral guidelines intended to reduce common LLM-assisted coding mistakes in this repository.

Changes:

  • Added a “For Agents” section describing principles like thinking before coding, simplicity-first implementation, surgical edits, and goal-driven verification.
  • Included example success-criteria planning format for multi-step tasks.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread CLAUDE.md
VS Code extension that surfaces the Hermes AI agent as a sidebar chat panel, communicating via ACP (JSON-RPC 2.0 over stdio subprocess).

## For Agents
Behavioral guidelines for you to reduce common LLM coding mistakes.
Comment thread CLAUDE.md
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants