#agentic-coding Repositories
64 repositories total
MCP tool: let you point at DOM elements for your favorite agentic coding tool. Let AI see what you see.
A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context โ EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES.
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results: a clear view of whatโs done, in progress, parked, or blockedโwithout scrolling a marathon chat.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
AI pair programming in your terminal โ one static binary, sub-ms startup, any model
A curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School, or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills, and agent instructions instead of spelling out methods yourself.
Where terminal agents work together. Claude Code, Codex, Copilot CLI, and pi on the same task, in one mission, each keeping its own TUI in a real terminal.
Info about many of my Terraform, AWS, DevOps, and AI (tada!) projects.
Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop โ plan, act, verify โ with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.
Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.