By thomasrohde
Autonomous agent-driven optimization loop — iteratively modify an artifact, evaluate against a scalar metric, and keep improvements. Works with any domain: code performance, prompt engineering, config tuning, SQL, builds, and more.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub thomasrohde/marketplace --plugin autoresearchAugment existing Execution Plans with agent-first CLI design requirements and project scaffolding guidance
ArchiMate enterprise architecture modeling assistance - element selection, relationships, patterns, and model quality guidance
Apply EAROS rubrics to architecture artifacts using the three-pass agent evaluation pattern (Extractor, Evaluator, Challenger) with optional parallel evaluators for comprehensive artifacts
Create, scaffold, and configure GitHub Copilot customizations for VS Code projects, including instructions, prompts, agents, skills, hooks, and MCP integration
Create architecture evaluation rubrics (profiles and overlays) conforming to the Enterprise Architecture Rubric Operational Standard (EAROS)
Generate architecture diagrams and technical design documents
Autonomous research loops with 10 commands. Generalizes Karpathy's autoresearch loop to any domain with mechanical evaluation, overnight persistence, and zero dependencies.
🏗️ Architect — System Architect + Technical Design Leader
Knowledge production: project bootstrap, project init, generation of context artifacts (skills, agents, rules, commands, hooks), mermaid diagrams, learn, discovery
Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Autonomous experimentation skill — your AI coding agent designs experiments, tests hypotheses, discards failures, keeps wins. Runs overnight while you sleep.