hush
Reduces token consumption in Claude sessions through compression and filtering, lowering inference costs and latency for development workflows without sacrifβ¦
π€« Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.
- Reduce API costs by compressing verbose logs before sending to Claude.
- Run longer coding sessions without hitting token limits on large projects.
- Customize output formatting to get cleaner, more concise Claude responses.
Reduces token consumption in Claude sessions through compression and filtering, lowering inference costs and latency for development workflows without sacrificing context quality.
Engineering teams managing high-volume Claude API calls or long-running development sessions with budget constraints.
https://github.com/V-Songbird/hush
By V-Songbird
How to Get It
claude plugins install V-Songbird/hush
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:
Help me reduce API costs by compressing verbose logs before sending to Claude
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good β 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): 33 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 β
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): 33 GitHub stars; contributors unknown; last commit 0d ago; license MIT.