Claude省钱版 — 效果基本一致的情况下可以节约Token消耗约90%，超级省Token，支持OpenAI及国产大模型(DeepSeek/GLM/通义千问)的AI编程助手。本项目基于ClaudeCode源码实现。
-
Updated
Apr 1, 2026 - JavaScript
#
token-saving
Here are 15 public repositories matching this topic...
Claude Code 委派 plugin:把任务派给换脑的子 agent(也可 --codex 委派给本机 codex),既省主 Claude 的 token,也借不同模型/harness 的视角。
delegation multi-agent glm gpt codex kimi brainstroming deepseek claude-code subagents claude-code-plugin agent-harness token-saving
-
Updated
Jul 21, 2026 - JavaScript
DeepSeek 峰谷提醒插件：北京时间梁文峰/梁文谷实时播报、切换前提前提醒、省 token 小贴士、自由拖动
javascript plugin productivity web-ui dsh deepseek token-saving deepseek-harness dsh-plugin peak-valley-pricing
-
Updated
Aug 19, 2026 - JavaScript
🎭 Talk to Claude in 100% emoji. A stylized communication mode for Claude Code.
emoji ai tokens claude llm prompt-engineering anthropic claude-code claude-code-plugin claude-skill token-saving
-
Updated
Apr 26, 2026 - JavaScript
TDD-first AI dev pipeline for Claude Code, Cursor, Codex, Gemini CLI & Antigravity. /dev /fix /quick + token-saving hooks. npx aicrew install
cli open-source hooks workflow tdd mcp developer-tools cursor codex sdlc ai-agents guardrails ai-workflow gemini-cli antigravity agent-skills claude-code token-optimization context-engineering token-saving
-
Updated
Jun 29, 2026 - JavaScript
Codex多智能体skill，主Agent规划，Subagent执行，让coding更省钱、更高效。A Codex CLI multi-agent orchestration skill that enables token saving subagent workflows. Let the main agent act as an architect while delegating code search, file reading, implementation and testing to specialized subagents. Reduce token usage and improve coding efficiency.
agent workflow skill multi-agent codex money-saver money-saving subagent agent-orchestration token-saving token-saver
-
Updated
Aug 13, 2026 - JavaScript
人脑式上下文压缩逻辑，大幅减少长任务上下文占用以及token消耗
llm-optimization context-compression selective-forgetting token-saving memory-vault deepseek-harness dsh-plugin deepseek-harness-plugin
-
Updated
Sep 11, 2026 - JavaScript
基于 RTK、专为 DSH 打造的薄层适配插件：让 DSH agent 的 pwsh 命令自动走 RTK（Rust Token Killer）压缩输出、节省 LLM token。A thin DSH adapter built on RTK that auto-routes DSH agents' pwsh commands through RTK to cut token usage.
-
Updated
Aug 16, 2026 - JavaScript
The TokenSaver family in one install - nine context-saving tools for coding agents, packaged as a Claude Code plugin with skills and MCP servers.
-
Updated
Sep 29, 2026 - JavaScript
Send one-liner questions to DeepSeek's web chat instead of burning your DSH context. Composer button + global hotkey palette, with history.
-
Updated
Sep 24, 2026 - JavaScript
Delegate simple text-only subtasks to free web AIs through your own Edge/Chrome. 把简单文本子任务外包给网页版免费 AI，省下主模型的 token。
mcp browser-automation codex cline playwright ai-agent chatgpt qwen deepseek agent-skill token-saving
-
Updated
Sep 20, 2026 - JavaScript
DeepSeek Harness agent preset: full Standard tools plus an extreme compact-output expert prompt
-
Updated
Aug 17, 2026 - JavaScript
Claude Code を品質を落とさずに自動でトークン節約させる設定キット（Opus 5.5 / Sonnet 5.5 世代・Mac / Windows / Linux 対応・node install.cjs 1回で導入）
-
Updated
Oct 1, 2026 - JavaScript
TypeSafe Jev System One decision and aggressive token-saving plugin for OpenCode and OmO
-
Updated
Sep 29, 2026 - JavaScript
DSH 插件：让每轮对话互相独立——每轮只把「本轮输入 + 长期设定」交给模型，历史自动折叠，显著降低上下文占用与费用；界面历史仍完整可回看。
-
Updated
Sep 29, 2026 - JavaScript
Add this topic to your repo
To associate your repository with the token-saving topic, visit your repo's landing page and select "manage topics."