By cnaught-inc
Token efficiency skill for Claude Code. Reduces output tokens by ~15% and speeds up responses by ~15%, with bigger gains on multi-turn sessions with large codebases.
A Claude Code plugin that reduces token waste by ~15% and speeds up responses — without sacrificing output quality.
git clone https://github.com/CNaught-Inc/pithy.git ~/.claude/plugins/cache/pithy/pithy/1.0.0
Or copy just the skill:
mkdir -p ~/.claude/skills/pithy
curl -o ~/.claude/skills/pithy/SKILL.md \
https://raw.githubusercontent.com/CNaught-Inc/pithy/main/skills/pithy/SKILL.md
Pithy teaches Claude Code to be token-efficient through two strategies:
/pithy on — enable (default)
/pithy off — disable
When active, {pithy} appears in the status bar.
Quality comes first. Pithy will never:
Aspirational target is ~10-20% output reduction. If it's cutting too deep, just say "expand" or "say more."
MIT
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimTrack and offset carbon emissions from your Claude Code usage
Sustainability-first design for Claude Code. Audit code for environmental impact and get eco-friendly recommendations during planning.
npx claudepluginhub cnaught-inc/pithyMinimize token waste in all bash, file, and data processing operations
Token optimization for Claude Code. Automatic tool output compression (40-60% reduction), token meter in statusline, auto-compact at 70% context, structured output formats, self-building project wiki, URL ingestion, Karpathy compile pass, and semantic lint.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Governor: always-on compact professional output, telemetry, context slimming, tool-output filtering, prompt guidance, and drift guardrails for Claude Code Max users.
Cost-conscious mode for Claude Code. Saves 30-60% on costs through concise responses, model routing, and efficient workflow patterns.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.