← Back to list

dsh-token-rtk

DeepSeek Harness Skills Low risk

Input redundancy pruning for DeepSeek Harness — drop repeated/redundant tokens before they reach the model (layer ②).

DeepSeek Harness 的输入冗余剪枝——送进模型前剪掉重复/冗余 token(layer ②)。

How to install

DeepSeek Harness dsh plugin add github:WODE25500/dsh-token-rtk

About

dsh-token-rtk **Input redundancy pruning — drop repeated/redundant tokens before they reach the model.** — a DeepSeek Harness (dsh) skill, layer rtk of a four-layer token-saving family. Trim verbose logs, duplicated warnings, whole-file pastes, and noise around the real signal so you pay for the signal you need, not the boilerplate around it. (RTK = Rust Token Killer strategy.) Family: dsh-token-skills groups all four layers — handoff, rtk, headroom, caveman. Install dsh plugin --profile web add dsh-token-rtk Then invoke the skill: dsh-token-rtk. Upstream Based on / referencing https://mintlif…

Recommendation signals

42 Tool quality · Based on stars, downloads, maintenance, security and docs
– User interest · Adjusted by in-site views, install copies and download clicks
42 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
JavaScript
GitHub stars
0
mo. downloads
–
Last push
2026-09-04
Created
2026-08-30

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings
curated 收录但无 npm 包/安装命令
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin

Related plugins

Claude Code
Score92

superpowers

obra/superpowers

An agentic skills framework & software development methodology that works.

☆ 291.2K ↓ 1.5K Skills ↗
Claude CodeMCP Server
Score89

rulesync

dyoshikawa/rulesync

A Utility CLI for AI Coding Agents

☆ 1.5K ↓ 914.9K Skills ↗
Claude Code
Score83

dev-browser

SawyerHood/dev-browser

A Claude Skill to give your agent the ability to use a web browser

☆ 6.6K ↓ 14.2K Skills ↗
Claude CodeDeepSeek HarnessCodexMCP Server
Score80

ruflo

ruvnet/claude-flow

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

☆ 73.2K ↓ 77.2K Skills ↗