Merge pull request #37 from dadwadw233/add-claude-code-harness

Add Claude Code Harness

Author: internet-dot

README.md

@@ -80,6 +80,7 @@ Third-party plugins built by the community. [PRs welcome](#contributing)!
 - [AgentOps](https://github.com/boshu2/agentops) - DevOps layer for coding agents with flow, feedback, and memory that compounds between sessions.
 - [Blueprint](https://github.com/JuliusBrussee/blueprint) - Specification-driven development pipeline that turns natural language into domain blueprints with testable acceptance criteria, generates parallel build plans, and implements them with automated validation and cross-model adversarial review.
 - [Brooks Lint](https://github.com/hyhmrright/brooks-lint) - AI code reviews grounded in six classic engineering books — decay risk diagnostics with book citations, severity labels, and four analysis modes (PR review, architecture audit, tech debt, test quality).
+- [Claude Code Harness](https://github.com/dadwadw233/claude-code-harness) - Harness blueprint skill for turning vague agent ideas into concrete designs for request assembly, control loops, memory, permissions, recovery, and extension planes.
 - [Claude Code Skills](https://github.com/alirezarezvani/claude-skills) - 223 production-ready skills, 23 agents, and 298 Python tools across 9 domains — engineering, marketing, product, compliance, and more.
 - [Claude Octopus](https://github.com/nyldn/claude-octopus) - Multi-LLM orchestration dispatching to 8 providers (Codex, Gemini, Copilot, Qwen, Perplexity, OpenRouter, Ollama, OpenCode) with Double Diamond workflows, adversarial review, and safety gates.
 - [Codex Agenteam](https://github.com/yimwoo/codex-agenteam) - Specialist AI agents (researcher, PM, architect, developer, QA, reviewer) orchestrated as a configurable team pipeline.