token-usage

token-diet

Shell

53

Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.

benjamin-plus-skill

Shell

77

Benjamin-Plus: a measured token-efficiency skill for coding agents (−17.9% cost median, quality unchanged). Inject it, don't install it.

agentacct

Python

77

See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

Token-Saver

Python

72

A local Claude Desktop extension to query large PDFs with 92–98% fewer tokens. Performs local hybrid search, cites exact page numbers, and keeps your documents private on your machine

vomit

Go

68

Clean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless

Core-Framework

TypeScript

72

A visual CSS framework and design-token builder for the web, WordPress, and Figma.

OptMem

Python

72

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

waggle

Rust

67

Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.

img2threejs

Python

95

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

dao-code

TypeScript

82

Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.

MTPLX

Python

90

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

ratel

TypeScript

77

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

MoonEP

Python

85

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

MAGI-2-preview

Python

82

MAGI-2-preview: Scaling Video Generation Models Efficiently

hermes-control-interface

JavaScript

85

A self-hosted web dashboard for the Hermes AI agent stack. Provides a browser-based terminal, file explorer, session overview, cron management, system metrics, and an agent status panel — all behind a single password gate.

cc-switch

Rust

95

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

backpass

JavaScript

77

You don't write AGENTS.md. You train it with gradient descent.

unity-ui-document-design-system

C#

77

Drop-in design system for Unity 6 UI Toolkit (UIDocument + PanelRenderer, UXML + USS): tokens, fx shader material support, 42 components, 120 icons, mobile-responsive, dark-themed. One stylesheet, zero dependencies. Battle-tested in a shipping cross-play game.

codebase-memory-mcp

C

95

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

mdflux

Python

72

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

microlighter

JavaScript

77

A zero-dep syntax highlighter that uses the CSS Highlights API

spec-ptc

Python

72

Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.

filetree-skill

Python

57

A Claude Code plugin that maintains `FILETREE.md`.