Havuz

dsh-model-master（模型选择大师）— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to mea

DSH 插件：统计所有经过 DeepSeek Harness 的模型调用——Token 用量、成本核算（含峰谷计价）、供应商余额与配额，并按模型/供应商/项目/来源/账号/日期拆分。A token usage, cost and provider-balance plugin f

Inline Antigravity dashboard: tok/s, DSH-style cache hit rate, five-hour and weekly quotas. English by default, Chinese switching, reversibl

Browse every public Agent Skill grouped by theme, multi-select and install them through npx skills add.

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flag

Edit a DeepSeek Harness (dsh) custom mode: system prompt, base mode, and plugin switches.

面向 AI Coding Agent 的任务感知工作区上下文检索与生命周期追踪：按当前任务找到、组织并持续追踪最相关的文档、代码与媒体。纯本地、零模型调用、零网络。 Task-aware workspace context retrieval and lifecycle tra

OpenAI Privacy hackathon - Paris, 🏆 winning project

✂️ Token saver & usage tracker for coding agents: terse caveman replies, compact RTK shell output, lean Ponytail code, Headroom compression,

DeepSeek Harness（DSH）Web 界面右下角的常驻余额挂件。基于 MeteorNOX/DeepSeek-Balance-Whale-Widget 修改的铁盆鲸鱼娘版。

A Codex CLI plugin packaging a full software studio — 45 specialist roles, 91 workflow skills, and deterministic quality gates for game and

「DSH·质量 diff」：接管 edit/write 及 extraTools 配置的其他工具卡片，行级去重与行内高亮，消除相同内容在删除与新增两区的重复；兼容 PTC 模式。

Recipes for Look's user-declared sources. Copy one in, reload, make it yours

Plugins for Paseo — a skills browser, a GitHub board, and a launchd job scheduler.

DeepSeek Harness (DSH) plugin: a read-only ledger for the plugins you already have installed — a capability inventory with file:line evidenc

把工作组织成目标看板的 DeepSeek Harness (dsh) 插件：目标 / 判据 / 上下文卡片 / 执行 attempt 的二维泳道看板，数据以文件+事件流落在 .dsh-graph · Goal-kanban plugin for DeepSeek Harness

DeepSeek Harness plugin: 15 obra/superpowers engineering skills, bilingual descriptions, per-skill toggles | DeepSeek Harness 插件：15 个 obra/s

DeepSeek Harness Web arayüzüne bakiye, kullanım ve oturum başına maliyet bilgilerini gösteren özelleştirilebilir bir yüzen widget ekler.

Neden yükseliyor · 41 günlük yaşına göre 3201 yıldız, son 28 günde 34 commit ve 5 farklı yazar dikkat çekici ilgi ve geliştirme aktivitesi gösteriyor. Bunun ne kadarının kalıcı kullanıcı benimsemesine dönüştüğü bu ölçümlerden anlaşılamıyor.

Blue: a TUI is not a package, it is a Cordis plugin tree — a modern terminal UI for DeepSeek Harness with hot-swappable render, interaction,

改配置+重启才能加 MCP？DeepSeek Harness (DSH) 插件「技能配置」解决：设置页粘贴 JSON 即连 MCP 服务器、热加载免重启；上传 zip/.skill 自动识别 SKILL.md，创建/编辑/启停技能，即点即用

DeepSeek Harness Web UI plugin for streaming rendering and scroll handling.

DeepSeek Harness (DSH) backup & restore plugin — export, import, migrate and sync your complete DSH configuration, plugins, MCP servers, ski

A terminal coding interface that brings the DeepSeek Harness kernel's full capability set — special modes, plugins, model & subagent managem

Import pi / opencode / codex / claude-code sessions, chat history, and agents into DeepSeek Harness — one-click Sync button, slash commands,

「DSH·工具结果自动展开」：在 DSH Web 界面自动展开工具调用卡片，支持侧边栏开关。标准可安装的 dsh 客户端插件。

Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept i

A practical guide to DSH plugin quality: ENTRY checks, FLOW journeys, and BOOST practices. Community guide; not a certification or ranking.

👾 A PestPHP Plugin for Coverage-Guided Fuzz Testing.

cmux plugin for Herdr: live sidebar status pills, tab/pane mirroring, nested agents CLI

Oh My Pi host plugin for the GSD Embeddable Orchestration System — extension bindings, slash-command surface, Host-Integration SDK adapter,

Storyblok-style click-to-scroll for Payload CMS Live Preview — hover a component in the preview, click it, and the admin edit form scrolls t

Grok Build plugin: hand work to local Claude Code or Codex as a background task

Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Simple utility plugins for nvim 🏡🧩

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation,

High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics, CLI / Server / IDE

One AI engineering team for Claude Code. Install once — every project gets a full-stack specialist team that auto-specializes to its stack.

The multi-paradigm database expert for Claude Code — design a schema, audit it on two never-blended scores (Design & Integrity / Performance

Real-time macOS system metrics (power, battery, CPU, temp, fan, memory, network) in your zsh RPROMPT

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops wit

The autonomous SDLC for Claude Code that won't pass a gate on an unproven verdict.

Single-line local context HUD for Codex CLI sessions.

TaiyiForge, Claude, Codex, Cursor ve OpenCode için AI destekli yazılım geliştirmeyi aşamalı ve denetlenebilir bir workflow'a dönüştüren TypeScript tabanlı bir araçtır.

Neden yükseliyor · 115 günlük bir repo için 886 yıldız dikkat çekici; AI coding agent'ları için tekrarlanabilir workflow ve kontrol ihtiyacına denk geliyor olabilir. Ancak yıldızların nedenini doğrulayan ek veri yok ve son 28 günde commit ile farklı yazar sayısı sıfır; bu nedenle ilginin güncel geliştirme faaliyetiyle desteklendiği söylenemez.

Show local time on every Claude Code message, and let Claude know when each prompt was sent. Zero-config plugin, cross-OS, graceful degradat

Turn your local web projects into Mac apps you can launch from the Dock, with their own window, name and icon.

The WorkBoard for Claude Code and humans. Watch your work come to life — never lose an idea, never lose a workflow.

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat

Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on Git

Hermes Agent plugin: rewrites your prompts before they hit the LLM — across CLI, TUI, Discord, Telegram. Quality scoring + analytics + arrow