token-saver-meta
v0.1.1
Published
Token Saving for the Masses — zero-config token-saving toolkit for AI coding agents
Maintainers
Readme
Token Saver Meta
"Token Saving for the Masses"
A meta-package that bundles token-saving tools across ALL layers of LLM token consumption — with zero configuration.
Architecture
Hybrid across 4 layers:
| Layer | Capabilities | Install | |-------|-------------|---------| | Agent Behavior | Prose terseness, code minimalism, operational efficiency, structured output | Instant, zero config | | Code Intelligence | Smart navigation, context mapping, repo packing | Auto-install | | Output Compression | Shell filtering, CLI optimization | Auto-install | | Power Tools | Schema compression, cross-session memory, prompt optimization, skill tuning | One-click enable |
Covers all 7 token consumption types: exploration, shell output, agent output, prompt input, repeated knowledge, tool schemas, and instructions.
Quick Start
# npm
npx token-saver-meta
# Python
uvx token-saver-metaFull architecture: docs/architecture-v2.md
License
Apache-2.0
