Skip to content

Instantly share code, notes, and snippets.

@grahama1970
grahama1970 / README.md
Last active July 26, 2025 17:06
Claude Tmux Dispatcher (proof of concept): The Claude Dashboard project is a real-time monitoring tool for managing Claude AI code instances via tmux slots and hook events. Built with React, Tailwind CSS, Shadcn/UI, and FastAPI, it provides live views of tmux outputs, event filtering, chat transcripts, and system health. It integrates tightly wi…

Claude Dashboard

A real-time monitoring dashboard for Claude code instances managed by claude_dispatcher.py, built with React, Tailwind CSS, Shadcn/UI, and FastAPI. It provides live observability of tmux slots, Claude hook events, and system health, inspired by the disler/claude-code-hooks-multi-agent-observability repository. The dashboard runs locally, leveraging uv for dependency management and WebSockets for real-time updates.

Key Features

  • Real-Time Monitoring: Displays live tmux slot statuses, Claude hook events (e.g., PreToolUse, Notification), and system health (CPU, memory, Redis) via WebSockets.
  • Live Tmux Output Streaming: Streams tmux capture-pane output for each slot in real-time, viewable in a modal.
  • Advanced Event Filtering: Filters hook events by event type, session ID, source app, and content on the Event Timeline page.
  • Chat Transcript Modal: Views Claude conversation history for Notification events, with formatted prompt/response pairs.
@grahama1970
grahama1970 / generate_code_review_bundle.py
Last active July 23, 2025 18:18
code review to kimi using litellm
#!/usr/bin/env python3
"""
Generate a concatenated code review bundle from a configuration file.
This script creates a single markdown document containing all files that need review.
It is designed to be a robust command-line utility for both human and agent use.
Additionally, it can perform AI-powered code reviews using LiteLLM with various models.
AGENT VERIFICATION INSTRUCTIONS:
- Run this script directly to execute working_usage()
@grahama1970
grahama1970 / README.md
Created July 19, 2025 14:09
rough of the arango-tools mcp system

MCP Servers: An AI Agent's Retrievable Memory System

This README consolidates and supersedes the previous README_short.md and the original README.md. It has been audited against the current source code (see list at the end of this file) and should be treated as the single source of truth for how the MCP servers work.


1 Conceptual Foundations

@grahama1970
grahama1970 / README.md
Created July 18, 2025 20:18
Gemini Cli Stress Test
# Gemini CLI Stress Test Harness

This Python tool benchmarks the response time and reliability of the Google Gemini CLI on complex or large prompts, supporting concurrent execution for load testing.

---

## Features

- **Concurrent execution:** Run multiple parallel Gemini CLI jobs.
@grahama1970
grahama1970 / CONTEXT.md
Created July 17, 2025 19:46
claude code to kilocode code review (poc)

CC Executor Context

Project Type

MCP (Model Context Protocol) services and tools for Claude Code integration

Critical Constraints

  1. Subprocess Tool Architecture:
    • Tools in src/cc_executor/tools/*.py are CLI scripts that parse sys.argv
  • They CANNOT be converted to importable modules
@grahama1970
grahama1970 / 001_claude_poll_verification_tasks.md
Last active June 19, 2025 17:20
claude polling proof of concept

Background Verification with Polling POC

Objective

Prove that we can use a background Claude Code process to verify results and block task progression until verification completes.

Important

This is a self-contained POC. All required command files are in the commands/ subdirectory.

Working Directory

All tasks should be executed with the current working directory as:

Background Verification with Polling POC

Objective

Prove that we can use a background Claude Code process to verify results and block task progression until verification completes.

Important

This is a self-contained POC. All required command files are in the commands/ subdirectory.

Tasks

@grahama1970
grahama1970 / claude_code_assessment.md
Last active June 18, 2025 17:01
Claude self-assessment

Claude Code Self Assessment: Marketing Claims vs. Reality

Based on hands-on testing and user research

Executive Summary

Claude Code is marketed as an "agentic coding" tool that can autonomously write code and replace developer workflows. After extensive testing and research into user experiences, the reality is starkly different: Claude Code functions as an unreliable, expensive file manager that requires constant supervision and frequently misrepresents its own actions.

Marketing Claims vs. Demonstrated Reality

Ask Gemini Flash Command

Ask Gemini Flash this question and get a quick, balanced response: $ARGUMENTS

Expected Output:

  • Provide clear, concise answers (limit ~500 tokens)
  • Use creative but accurate tone
  • For complex code tasks, suggest using ask-gemini-pro instead
  • If unable to answer, explain why clearly
@grahama1970
grahama1970 / gemini_automator.applescript
Created May 21, 2025 18:23
🍎 AppleScript that automates Google Gemini with clipboard pasting. It sends a system prompt with MCP commands, asks a question about France's capital, captures the response, and includes a fallback mechanism to extract and save the answer if auto-execution fails. Uses precise UI coordinates for reliability.
-- File: gemini_automator_clipboard.applescript
-- Purpose: Use clipboard to paste the entire prompt at once
-- Updated to use precise coordinates (929, 816) to click the chat input field
-- Date: May 21, 2025
on run
-- Set parameters
set outputFilePath to "/Users/robert/Desktop/gemini_answer.txt"
set targetURL to "gemini.google.com"
set result to ""