token-efficiency

仓库创建 2026年7月6日最近提交 22 天前SkillHot 收录 22 天前

▸ 精选理由

兼顾工具与实践，可显著减少 API 成本与上下文膨胀。

这个 Skill 做什么

提供降低 LLM 会话令牌消耗的工具与习惯指南（含 RTK）。

帮你把跟 LLM 会话相关的“令牌”吃得少点，既有工具手段（比如 RTK 那个用 Rust 的 CLI 代理，把命令输出压缩/过滤）也有日常习惯建议。用在新机器或项目初始化、会话快碰上下文/速率/费用上限时，能显著降低 API 花费和跑模型时被上下文淹没的问题。

▸ 展开 SKILL.md 英文原文

Reducing LLM token consumption in AI-assisted development sessions — RTK setup (CLI output compression via hook), when it pays off and complementary habits. Use when setting up a new machine or project for agent work, when sessions are hitting context limits or rate limits too fast, when API costs are a concern, or whenever the user mentions tokens, context window, RTK or session cost.

开发编程令牌优化成本削减会话管理通用

Stars

Forks

仓库内 Skill

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/JoaoEquer/Oficina/main/skills/token-efficiency/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/JoaoEquer/Oficina/main/skills/token-efficiency/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Token efficiency

Tokens are the working memory of the session. Every verbose command output gets re-read on every subsequent turn, so waste compounds: a 2,000-token `git diff` costs ~20,000 tokens over the next 10 turns. Two fronts: tooling (RTK) and habits.

## RTK (Rust Token Killer)

[rtk-ai/rtk](https://github.com/rtk-ai/rtk) is an open-source CLI proxy (single Rust binary, Apache 2.0) that compresses command output before it reaches the context window — 60–90% savings on test runners, git operations and package managers. It runs locally and hooks into the agent's official extension points (Claude Code PreToolUse hook); it does not touch API traffic.

### Setup (once per machine)

```

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有