v0.5.1 · Apache-2.0
MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).
v1.1.0 · MIT
A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.
v0.2.0 · MIT
Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.
v0.4.1 · MIT
DSH crash-rescue plugin: undo config & plugin-code changes, secret-safe snapshots, one-click SAFE MODE, plus offline CLI/GUI that work even when DSH won't boot.
v1.0.1 · MIT
Claude-Code-style TUI bundle for DeepSeek Harness. 充分结合 DSH 的核心机制和高级特性与Codex CLI 、Claude Code 等主流交互机制,打造的 DSH-Code. (对齐DSH官方上游最新版本!持续更新中!支持DSH 特殊模式,插件系统,模型管理,子代理管理,切换模型特殊动画)
v1.12.0 · Apache-2.0
Your coding agent designs terrible UI. stitch-kit wires it into Google Stitch MCP and teaches it the whole pipeline — ideation, screen generation, design systems, production components.
v0.1.3 · MIT
Search agent skills ranked by measured lift vs a no-skill baseline, with safety and rankings.
v0.1.0 · MIT License
Designs a real house exterior on its own photo, prices it line by line and documents it.
v3.2.2 · Apache-2.0
900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.
v0.0.0 · MIT
Open-source MCP server for comparing products and asking the buyer before purchase.
v1.2.0 · MIT
SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.
v0.3.1 · MIT
Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件(场景感知抽帧 + VLM + 可选语音转录)
v0.4.0 · no license
Claude Code plugin that plays a Mr. Meeseeks voice line whenever Claude is waiting for you.
v0.11.0 · MIT
🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 44 commands · 19 skills · 8 agents · 43 rules · 30 hooks · auto-learning pipeline. | 一个插件,完整开发团队。
v0.2.3 · MIT
DeepSeek Harness plugin: per-edit approval with a red/green line diff before write/edit/str_replace_editor — approve once or reject (Claude Code behavior).
v1.4.0 · MIT
Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.
v0.1.14 · MIT
Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance
v0.1.0 · MIT
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
— · MIT
A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.
v0.2.3 · no license
DSH 插件:分支式消息编辑、重掷、重试与版本时间线 | DSH plugin: branch-based message editing, reroll, retry, version timeline
v0.97.0 · MIT
One launcher/updater for the ssheleg skill family (super-ux, task-pipeline, agent-sync, make-skill, sheleg-design, seo-aeo-audit, sheleg-dev, agent-stack) across every agent — Claude Code, Cursor, OpenCode, Kilo, Kimi, Hermes, OpenClaw, Codex, and more.
v1.0.2 · MIT
Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — TWO agent presets in one install: vibe-math-v1 (classic pipeline: brainstorm → solver iteration → multi-verifier debate → Verified) and vibe-math-v2 (new probability
v0.6.6 · MIT
Git-style milestone timeline for DeepSeek Harness - hover for metadata, click to jump to any message. 会话里程碑导航条:像 Git 提交图一眼定位每条提问,悬停看时间/轮次/耗时/TTFT,点击即跳转。
v0.1.1 · MIT
Swift Cycle governance skill adapter for DeepSeek Harness; user-invoked, version-pinned, and offline-verifiable.