By CHKDSKLabs
P2P sync for your .claude configuration across machines. Like OneDrive, but for crabs.
This skill should be used when the user asks to "resolve crabtalk conflicts", "show sync conflicts", "fix crabtalk conflicts", "view config diffs", "crabtalk conflicts", or mentions merge conflicts from CrabTalk sync.
This skill should be used when the user asks to "check crabtalk status", "show sync status", "list connected devices", "crabtalk peers", "who's online", "last sync time", or mentions CrabTalk connection or device status.
This skill should be used when the user asks "how does crabtalk work", "what does crabtalk sync", "crabtalk architecture", "crabtalk troubleshooting", "sync not working", "crabtalk help", or has questions about CrabTalk's sync mechanism, security, or behavior.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
P2P sync for your .claude configuration across machines. No central server touches your file contents — devices discover each other through the rendezvous API and exchange files directly over encrypted libp2p QUIC streams.
~/.claude/plugins/)~/.claude/agents/)~/.claude/settings.json)~/.claude/CLAUDE.md)~/.claude/keybindings.json)Conversation history, caches, auth tokens, .local.md files, temp files.
/crabtalk:conflictscrabtalk/
├── .claude-plugin/ # Plugin manifest
├── skills/ # User-facing skills (setup, conflicts, status, sync-guide)
├── hooks/ # SessionStart auto-connect
├── mcp-server/ # MCP server — daemon IPC bridge and Claude-facing tools
├── daemon/ # Rust libp2p daemon — watching, peer connections, file transfer
└── server/ # Rendezvous server — auth and peer discovery
# Install the plugin
claude --plugin-dir /path/to/crabtalk
# Create an account or log in
# Use /crabtalk:setup in a Claude Code session
| Skill | Description |
|---|---|
/crabtalk:setup | Create account or log in, configure device |
/crabtalk:conflicts | View and resolve sync conflicts (unified diff) |
/crabtalk:status | See connected peers, last sync, pending changes |
MIT
npx claudepluginhub chkdsklabs/crabtalkAgentic design workflow: April elicits the five upstream design documents, Shredder slices them into a dependency-ordered queue, and Karai dispatches Bebop / Baxter / Chaplin / Metalhead / Splinter / Tatsu / Krang through Bishop review and Tiger Claw adversarial QA, with Traag-style scope enforcement via PreToolUse hook.
Sync Claude Code sessions across devices with encrypted cloud storage
Sync and evolve your Claude Code brain across machines. Automatically exports, merges, and applies your accumulated knowledge (memory, skills, agents, rules, settings) across all your development machines via Git.
Peer-to-peer communication between Claude Code sessions on the same machine
Commands for syncing CLAUDE.md, permissions allowlist, and refreshing context. Hooks for marketplace-to-plugin sync.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.