v2.0.0 · MIT
Claude Code skills for the work that keeps a design system alive
v1.1.2 · MIT
Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.
v0.2.5 · MIT
Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
v5.1.0 · MIT
You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.
v1.4.15 · MIT
Usage billing dashboard plugin for DeepSeek Harness: sidebar cost metrics, real usage aggregation from session logs, current multi-provider pricing catalog
v1.1.3 · no license
Public Solana MCP registry metadata for Vybe Solana API
v0.3.0 · MIT
🌊 Persistent dock & fully-customizable balance/usage panel for DeepSeek Harness — activity heatmap, dual-channel comparison, local-only & privacy-first
v9.7.0 · MIT
Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 112 public repos, reads React and web components (Stencil, Lit), hands you a copy-paste fix prompt for each top finding, writes ru
— · MIT
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
v2.2.0 · MIT
Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.
v3.1.1 · MIT
A local MCP server with full Figma REST API coverage.
v0.3.13 · MIT
DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制
v2.0.0 · MIT
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
v0.8.2 · MIT
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
v2.0.0 · MIT
Real-time cost tracking and budget management for Claude Code. Zero setup. No Docker. No Grafana. Just install and go.
v1.3.0 · MIT
deepSeek 余额监控与用量统计(DSH 动态 Cordis 插件):余额监控 · 官方充值入口 · 用量统计 · 三方插件管理
v1.3.4 · MIT
Reverse-engineer design systems from any website, repo, or project. Extracts colors, fonts, spacing, animations, and components - packaged as a .skill file for Claude. Pure static analysis, zero AI, zero API keys.
v1.2.0 · MIT
Pith is the hook that makes Claude Code sessions last 3x longer.
— · Apache-2.0
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
— · Apache-2.0
LeanCTX — Context Gateway for AI systems.
v9.7.0 · MIT
Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 112 public repos, reads React and web components (Stencil, Lit), hands you a copy-paste fix prompt for each top finding, writes ru
— · MIT
Real-time execution trace and cost intelligence for Claude Code
— · no license
Claude Code plugin that offloads large outputs to filesystem and retrieves when required.
— · no license
Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.