Multi-Persona-Layer for Claude Code. Per-chat agent roles (Coder, Browser, Inbox, Research, ...) — each with its own tools, MCP servers, and system prompt. Optional, on top of voice or standalone.
Plugin cowork from marketplace corvin-voice-local in CorvinLabs/CorvinOS. Commands read from the repo's manifest — today.
coworkMulti-persona layer for Claude Code. Per chat (or per CLI call) a different agent role: coder (default), browser, inbox, research, ... Each persona has its own tools, MCP servers, system prompt and workspace. Optional, on top of voice or standalone. Trigger when the user mentions cowork, persona, ag
/cowork:cowork-addCopy a bundle persona into the user dir (~/.config/claude-cowork/personas/) for editing
/cowork:cowork-bindBind a persona to a chat (writes settings.json, hot-reload kicks in immediately)
/cowork:cowork-listList all known cowork personas (bundle + user)
/cowork:cowork-rmDelete a user persona (bundle persona stays untouched)
/cowork:cowork-runRun claude locally in a persona (standalone — no bridge/voice)
/cowork:cowork-showShow a persona as JSON (tools, MCP, prompt-append, ...)
/cowork:cowork-unbindRemove a chat's persona binding (chat_profile stays otherwise)
Voice mode for Claude Code: reads assistant replies aloud (TTS) with auto language detection (de/en) and optional summarization. Also provides the WhatsApp / Telegram / Discord / Slack / Email bridges that funnel inbound messages into a Claude subprocess.
1 skill · 42 commands · hooks
CorvinOS install and update from Claude Code. /corvin:install runs the installer of your local CorvinOS clone (repo-only — nothing is downloaded) and verifies the console really serves the app; /corvin:update checks origin/main for a newer version, runs the clone's updater (with automatic rollback) and re-verifies. Both are safe to re-run.
2 commands
Runtime tool generation: chat-pinned personas can register and execute schema-bound tools, sandboxed via bubblewrap + rlimits, hash-chain audited, with task/session/project/user scope routing.
1 skill
Runtime skill generation: chat-pinned personas can create Markdown skills with front-matter and prompt-inject them into sub-agents. Lint-gated, hash-chain audited, auto-purges ungraded skills after 7 days.
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.