A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions and commands that work seamlessly across Claude, Gemini, Copilot, and local AI models. See also: https://github.com/JacobPEvans/claude-code-plugins
This repository also configures its own agents. See what ai-assistant-instructions tells them →
dryvist/ai-assistant-instructions
Agent Claude Code
Default executor for scoping, bulk reads, triage, mechanical shipping and implementation chunks delegated by a lead session. Runs at xhigh effort, never below high; reports evidence to the file the prompt names. Brief it completely: it knows only its prompt.
dryvist/ai-assistant-instructions
Agent Claude Code
Strong-reasoning executor for architecture, cross-system design and security judgment delegated by a lead session; never for read-only scouting or routine implementation (use haiku-xhigh). Runs at medium effort; proves claims with source and live evidence; reports to the file the prompt names. Brief it completely: it…