odin-claude-plugin
Enables Claude to follow outline-driven development patterns, reducing rework by structuring agent decisions around predefined task breakdowns rather than fr…
Outline-Driven Development (ODIN) — a Claude Code plugin that turns Claude into a structured code agent: diagram-first engineering (five required diagrams before non-trivial implementation), AST-based surgical edits with ast-grep, confidence-driven execution, mandatory investigation before code changes, and atomic Conventional Commits. Ships 89 skills spanning planning, exploration, and TDD/type-driven/proof-driven methodologies. Formerly branded the ODIN Claude Plugin; sibling plugins exist for Codex CLI and Gemini CLI.
- Breaking down complex features into outlined subtasks before code generation
- Maintaining consistency across multi-file refactoring projects
- Generating code scaffolds from architectural outlines
Enables Claude to follow outline-driven development patterns, reducing rework by structuring agent decisions around predefined task breakdowns rather than free-form code generation.
Development teams using agentic AI for larger codebases where explicit task decomposition and structured workflows improve code quality and debugging speed.
https://github.com/OutlineDriven/odin-claude-plugin
By OutlineDriven
How to Get It
claude plugin marketplace add OutlineDriven/odin-claude-plugin && claude plugin install odin@odin-marketplace
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me breaking down complex features into outlined subtasks before code generation
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 27 GitHub stars; contributors unknown; last commit 2d ago; license Apache-2.0.
Things to check
- The README's recommended 'full install script' starts by overwriting ~/.claude/CLAUDE.md with the project's version — back up your global CLAUDE.md first, or run only the marketplace add/install commands. Large surface (89 skills plus agents and commands); the diagram-first workflow adds process overhead on small tasks.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 27 GitHub stars; contributors unknown; last commit 2d ago; license Apache-2.0.