keep-the-why
Reduces redundant code review cycles and decision replay by capturing architectural reasoning directly in the repository, lowering context-switching overhead…
Keep the Why: a repo-native convention and agent skill that preserves the reasoning behind a codebase as a byproduct of working with your agent — so it stops re-suggesting rejected approaches, gives better answers, speeds up onboarding, and makes legacy projects tractable again.
- Ask Claude to review a rejected code approach and document why it won't work for future reference
- Generate onboarding documentation by extracting reasoning from past development decisions in your codebase
- Prevent Claude from re-suggesting architectural patterns your team already dismissed with documented rationale
Reduces redundant code review cycles and decision replay by capturing architectural reasoning directly in the repository, lowering context-switching overhead and accelerating onboarding on complex or legacy systems.
Engineering teams maintaining large codebases or legacy systems where institutional knowledge loss and repeated rejections of similar approaches create friction.
https://github.com/oliver-zehentleitner/keep-the-why
By oliver-zehentleitner
How to Get It
claude plugins install oliver-zehentleitner/keep-the-why
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Review a rejected code approach and document why it won't work for future reference
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 81 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
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): 81 GitHub stars; contributors unknown; last commit 0d ago; license MIT.