nightshift
Reduces cognitive overhead and context loss during extended AI-assisted coding sessions by organizing work state persistently, enabling teams to resume compl…
Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results a clear view of what’s done, in progress, parked, or blocked—without scrolling a marathon chat.
- Ask Claude to refactor a large codebase over multiple sessions without losing context or progress.
- Generate a status dashboard showing which coding tasks are done, blocked, or still in progress.
- Automate multi-hour code development shifts with safe checkpoints and automatic recovery if interrupted.
Reduces cognitive overhead and context loss during extended AI-assisted coding sessions by organizing work state persistently, enabling teams to resume complex tasks without regenerating context or losing progress tracking.
Engineering teams using Cursor, Codex, or Claude Code for multi-hour development sprints requiring clear audit trails and state recovery.
https://github.com/orwa-mahmoud/nightshift
By orwa-mahmoud
How to Get It
claude plugins install orwa-mahmoud/nightshift
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:
Refactor a large codebase over multiple sessions without losing context or progress
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Infinite loop in macOS Night Shift in the summer near the Arctic Circle — Hacker News · 588 pts
- Night Shift compared to f.lux — Hacker News · 430 pts
- Some Night-Shift Workers May Have a 300% Higher Risk of Car Crashes — Hacker News · 156 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 76 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): 76 GitHub stars; contributors unknown; last commit 0d ago; license MIT.