Darin Gordon Dowwie

How to Use Codex from Claude Code

Codex is an AI-powered CLI tool that can help with complex debugging, code analysis, and technical questions. When you encounter difficult problems that would benefit from a second perspective or deep analysis, use Codex.

When to Use Codex

Debugging subtle bugs (e.g., bitstream alignment issues, off-by-one errors)
Analyzing complex algorithms against specifications
Getting a detailed code review with specific bug identification
Understanding obscure file formats or protocols

Update Elixir Dependencies

Update all outdated dependencies in this Elixir project, handling both safe updates and breaking changes.

Workflow

1. Identify Outdated Dependencies

Run mix hex.outdated to get a list of all outdated dependencies. Parse the output to identify:

Safe updates: Dependencies where only the patch or minor version has changed (no major version bump)

Claude Code TeammateTool - Source Code Analysis

This is not a proposal. This documents existing but hidden functionality found in Claude Code v2.1.19 binary, plus speculation on how it could be used.

Executive Summary

TeammateTool already exists in Claude Code. We extracted this from the compiled binary at ~/.local/share/claude/versions/2.1.19 using strings analysis. The feature is fully implemented but gated behind feature flags (I9() && qFB()).

name	description
orchestrating-swarms	Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

Inferal Workspace Architecture

Your org's brain that AI can use

This document describes the conceptual architecture of the Inferal Workspace - a text-based, version-controlled knowledge and operations hub designed to replace tools like Notion and Webflow while being natively accessible to AI assistants.

Why We Built This

As an engineering-driven organization, we found ourselves fighting our tools instead of using them. Notion couldn't keep up with how we actually work - context scattered across pages, no version control, and AI that could read but not act. Webflow meant our website lived in a silo, disconnected from our codebase and deployment pipelines. Every tool was another tab, another context switch, another place where knowledge went to die.

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

	Here are important documents to review:
	1. Source Systems Guide:
	<source_systems_guide>
	{source_systems_guide}
	</source_systems_guide>
	2. Database Schema:
	<database_schema>
	{database_schema}
	</database_schema>

	# train_grpo.py
	import re
	import torch
	from datasets import load_dataset, Dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import LoraConfig
	from trl import GRPOConfig, GRPOTrainer

	# Load and prep dataset

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference