Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script — 100% local & read-only.

Oh My Pi bash runtime ported as a deepseek-harness tool plugin: persistent shell session, output minimizer, managed background jobs, command interception

Claude Code plugins for AI-native engineers

Codex coding preset with customizable prompts and tools for DSH.

Mission control that ships. Not a terminal multiplexer: Claude Code, Codex, Kimi Code and Grok each work in their own git worktree. Only the one that needs you asks for your attention.

Claude Code plugin for people who describe what they want and let Claude build it: brand identity, product planning, plain-language build/ship/debug workflows, and a creator toolkit.

Core Goal Addon (Token Budget, Milestones, Git Snapshots & Retrospective Reports) for DeepSeek Harness

Say goodbye to copy-pasting and DSH Token anxiety. Let ChatGPT on the web connect directly to your local project, code on its own, and hand complex tasks to DSH for sustained execution.

Session lifecycle management for Claude Code — persistent memory, soul purpose, reconcile, harvest, archive

Remote-first terminal UI for DeepSeek Harness with SSH reconnect, Windows/ConPTY and incremental ANSI rendering.

DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制

Kimi for Claude Code and Codex: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and MCP tools through your local Kimi Code CLI. Available through GitHub marketplaces and npm.

ITIL-aligned IT service management for Claude Code and Codex

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and the terminal (plugins, Skill, CLI).

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

MetalBear Skills for our users

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-model AI coding where the model that wrote the diff never grades it.

Mission control for every Claude Code session on your machine.

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

Grok Build plugin for Claude Code, Grok, Codex, Cursor and others. Provides /grok:search, /grok:review, /grok:rescue commands + grok_search MCP tool for live X/web search.

Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and image recognition.

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature video, complexity delta, and deep-linked snippets.

Keeps AI assistants on track during long conversations by tracking tasks across sessions