← Back to list

context-razor

DeepSeek Harness Memory Low risk

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.

上下文剃刀:把当前会话上下文逐条列出(角色/预览/≈token 估算),超阈值标红,勾选后不经 LLM 精确裁剪,删了什么一目了然。

How to install

DeepSeek Harness dsh plugin add @weibaohui/context-razor

About

@weibaohui/context-razor **上下文剃刀**:把当前会话上下文逐条列出来——角色、预览、≈token(cl100k_base 估算,与技能市场同词表)——超阈值标红,勾选后精确裁剪。压缩不知道裁了什么,剃刀让你自己挑。 核心功能 **逐条列出**:当前会话模型可见的每条上下文(用户/助手/工具结果)按序排列,带预览、字符数与 ≈token 估算,点 ⋯ 查看全文与真实 usage **占比标注**:每条的 token 徽章同时显示其占全部上下文的百分比(如 ≈5728 · 15%),一眼看出谁是上下文大头 **类型筛选**:按类型一键过滤——用户 / 注入 / 助手,以及各工具名(bash、skill、read、edit…按会话实际出现的动态生成)。多选 toggle,与 token 量级筛选正交叠加 **超阈值标红**:可调阈值(默认 500 token,本地记忆),超限条目红色高亮;「只看超阈值」过滤 + 「token 高→低」排序,大头一眼可见 **精确裁剪**:勾选任意条目一键删除——连续段自动合并处理。删除走宿主 surface replace 协议(与官方 compaction 同款机制),**不经 LLM 总结**,删了什么、删了多少完全由你决定。每行尾部带 ✕ 快捷按钮,**单条直接删**与勾选后**多选批量删**走同一确认弹窗 **不重排*…

Recommendation signals

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

Meta

License
MIT
Language
JavaScript
GitHub stars
0
mo. downloads
Last push
2026-09-03
Created
2026-09-02

Links

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
deepseek-harness, dsh, dsh-plugin

Related plugins

DeepSeek Harness
Score83

dsh-mnemon

omdsh-dev/dsh-mnemon

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

☆ 345 ↓ 33.1K Memory
MCP ServerClaude Code
Score80

markdownify-mcp

zcaceres/markdownify-mcp

A Model Context Protocol server for converting almost anything to Markdown

☆ 3.0K ↓ 1.3K Memory
DeepSeek Harness
Score80

hindsight

vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

☆ 23.2K ↓ 119.1K Memory
MCP Server
Score79

airtable-mcp-server

domdomegg/airtable-mcp-server

🗂️🤖 Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases

☆ 456 ↓ 14.0K Memory