grahama1970

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

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:

grahama1970

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

# 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

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

#!/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

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

---

name: code-reviewer description: Proactively triggered for comprehensive code reviews and security analysis. If they say 'review code', 'check security', 'code quality', or mention pull requests, use this agent. When you prompt this agent, provide the code location and review focus areas (security, performance, style). Remember, this agent has no context about your standards, so specify coding conventions and acceptable risk levels. tools: python type: reviewer capabilities:

• code_review_bundle
• git_context_integration
• security_analysis
• performance_review

grahama1970

Here is the final clear and concise estimate with math for how many full-time developers a 16 Nvidia H200 GPU cluster can support running Grok’s Kimi-k2, based purely on token throughput:

Given:

• Average tokens per developer per day: ~5,800,000 tokens
• Seconds per day: 86,400 seconds
• Per-GPU token throughput (prefill + decode combined) from Grok Kimi-k2 benchmarks: ~4,000 tokens/sec
• Number of GPUs in cluster: 16

Step 1: Calculate tokens per second per developer

grahama1970

#!/usr/bin/env python3
"""
Codebase Indexer for Semantic Code Search

A tool for indexing code repositories into ArangoDB with semantic embeddings,
enabling intelligent code search beyond simple text matching.

Key Features:
- Extracts functions/classes using tree-sitter AST parsing
- Generates semantic embeddings using nomic-embed-code model (1024-dim)