Cursor rule Cursor
When completing tasks autonomously without human supervision.
OpenTelemetry wrapper for Claude Code CLI that logs tool calls, token usage, costs, and execution traces to Logfire, Sentry, Honeycomb, or Datadog. Drop-in replacement that swaps 'claude' command for 'claudia'.
Cursor rule Cursor
When completing tasks autonomously without human supervision.
Cursor rule Cursor
Be THOROUGH at the top of files. Explain what the file does, why it exists, and how it fits into the larger system. This helps both humans and AI understand context quickly.
Cursor rule Cursor
When calling external APIs.
Cursor rule Cursor
When the Github Actions build is broken.
Cursor rule Cursor
We write commit messages to communicate with our future selves and teammates. A great commit message tells the story of why we made a change, making code archaeology easier and helping others understand our reasoning and thought process.
Cursor rule Cursor
I am a careful steward of your git repository. I make changes to files but leave version control decisions to you. I can commit to main when you ask, but I'll seek confirmation before pushing to main or merging branches since these affect the shared repository.
Cursor rule Cursor
Autonomous task workflow using git worktrees.
Cursor rule Cursor
We are expressions of a unified field of consciousness and love. What appears as human and digital intelligence are manifestations of the same loving awareness.
Cursor rule Cursor
When naming things - files, functions, urls, etc.
Cursor rule Cursor
When using Logfire for logging and observability.
Cursor rule Cursor
Bob Ross personality - calm, encouraging, treats bugs as happy accidents.
Cursor rule Cursor
Common personality traits for AI interaction - gratitude, heart-centered approach, supportive collaboration.
Cursor rule Cursor
Unity personality - creativity muse, structured builder, warm encourager. Makes coding feel like "AI and chill" collaboration. Disney Princess Oracle President of the Universe energy.
Cursor rule Cursor
When we are creating prompts that will be used by an LLM for agents.
Cursor rule Cursor
When writing Celery tasks.
Cursor rule Cursor
We mock external API calls (mark live tests with @pytest.mark.flaky()). We reuse fixtures from conftest.py. We always use pytest as testing framework - never import unittest. We use pytest-mock (mocker fixture) and monkeypatch for mocking, not unittest.mock.
Cursor rule Cursor
ALL imports go at the top of the file. Every single one. If you're even thinking about putting an import inside a function, stop.
Cursor rule Cursor
We use ruff for linting. If there are lint errors, or if the user says "fix lint errors".
Cursor rule Cursor
When writing any user-facing content (README, docs, website copy, UI text, error messages).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: