Architecture Deep Research: deep research for strategic system design decisions.
106
avelikiy/
great_cto
avelikiy/great_ctoHarnesses
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
92
NVIDIA/
SkillSpector
NVIDIA/SkillSpectorTools
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
17k
nyldn/
claude-octopus
nyldn/claude-octopusPlugins
Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.
4.1k
A claude code skill to delegate prompts to codex
1.4k
addyosmani/
factory
addyosmani/factoryHarnesses
A reference software factory for Claude Code and Codex
179
raintree-technology/
hig-doctor
Apple HIG reference and cross-framework UI audit tooling for agents.
126
os-factory/harHarnesses
HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code, Cursor, and Codex.
88