BrowserSkill
Tencent
让 AI 助手直接接管你已登录的真实浏览器,自动操作网页又不打断你手头的事。
vibe-any805更新于 19 天前
自动精简过大的工具输出,在不牺牲模型能力的前提下大幅降低Token消耗,省钱又省心。
实用分
83 / 100
配置门槛
开箱即用
协议
MIT
语言
JavaScript
复制命令,或者把整个安装任务交给你的 Harness 智能体。
git clone https://github.com/vibe-any/dsh-plugin-save-token.git请帮我安装 DeepSeek Harness 插件「dsh-plugin-save-token」: - GitHub 仓库:vibe-any/dsh-plugin-save-token(https://github.com/vibe-any/dsh-plugin-save-token) - 类型:cordis 插件(装到 DSH profile) - 该插件开箱即用,无需额外配置。 请先查看仓库 README 确认安装步骤,然后按官方方式安装。装完后告诉我怎么使用。
来自项目自身文档的清洗摘录。
dsh-plugin-save-token English 简体中文 In one sentence: a DeepSeek Harness (dsh) dynamic plugin that cuts token cost without cutting model intelligence. Codex user? The same token-optimization brain ships as a standard Codex CLI plugin (MCP stdio server) in codex-plugin-save-token/ — see its README. It slims down oversized tool outputs at the entrance of every model request — reversibly and structure-aware . The full original text is always saved to disk; what the model sees is always a condensed version carrying a retrieval path. Every optimization obeys one red line: any replacement must be restorable in one step , and the estimated token count after compression must be strictly smaller than the original. --- Why you need it - The bulk of agentic-session cost is tool output that keeps re-entering the context : large JSON from APIs, CLI tables, logs. The same 40KB price table may be billed again on every conversation turn. - But blunt truncation degrades intelligence:…
在 GitHub 打开来自同一生态方向的相似工具。
Tencent
让 AI 助手直接接管你已登录的真实浏览器,自动操作网页又不打断你手头的事。
DDDMUC
给 DeepSeek Harness 加个免费网页搜索,不用 API key,还能切换多个搜索引擎。
LivXue
为 DeepSeek Harness 提供插件市场,帮你发现、安装、启用和更新各类 dsh 插件,目录可审计。