Claude Code 플러그인

@rashomon · shinpr/rashomon

21

Evaluate prompts and skills through parallel execution comparison in git worktrees

@quiver · yagizdo/quiver

16

Skills and agents for the feature cycle: brainstorm a spec, plan tasks, build with tests (in parallel worktrees for larger plans), run a multi-agent code review that checks each finding against the code, debug from hypotheses, write commit messages and PR descriptions, build UI from Figma, and hand over context between sessions

@sdlc-graph-engineering · RonMizrahi/ai-sdlc-graph

19

The SDLC as a guarded graph, with the milestone loop delegated to a milestone agent per milestone (per worktree under strategy C) whose bundle the orchestrator verifies against git before recording it. A run is one gitignored directory — state, per-milestone journals, and with --trace every state it passed through. Ships a run reviewer that turns a finished run into the evals it should have had, and an advisory onboarding skill that reports which third-party tools this session can invoke and what a run does without each. Command-invoked.