From asi
Discovers Tailscale mesh peers supporting LocalSend for file exchange via CLI commands and Python API. Bridges networks using Tailscale status and LocalSend multicast.
How this skill is triggered — by the user, by Claude, or both
Slash command
/asi:tailscale-localsendThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Discover peers via Tailscale mesh and exchange files via LocalSend protocol.
Discover peers via Tailscale mesh and exchange files via LocalSend protocol.
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Tailscale API │────▶│ Peer Discovery │────▶│ LocalSend API │
│ (mesh network) │ │ (propagator) │ │ (file xfer) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
tailscale status --json → get mesh peers# Discover peers on tailscale with localsend
just ts-localsend-discover
# Send file to peer
just ts-localsend-send <peer> <file>
# Receive mode
just ts-localsend-receive
from tailscale_localsend import TailscaleLocalSend
tls = TailscaleLocalSend(seed=0x6761795f636f6c6f)
# Discover peers
peers = tls.discover()
# [{'name': 'macbook', 'tailscale_ip': '100.x.x.x', 'localsend_port': 53317, 'color': '#A855F7'}]
# Send file
tls.send(peer='macbook', file='data.json')
# Receive (blocking)
tls.receive(callback=lambda f: print(f"Got {f}"))
tailscale status --json for mesh peersPOST /api/localsend/v2/prepare-uploadPOST /api/localsend/v2/upload?sessionId=...Each peer gets deterministic color from Gay.jl:
peer_color = gay_color_at(hash(peer_fingerprint) % 1000, seed=GAY_SEED)
from epistemic_arbitrage import ArbitrageNetwork
network = ArbitrageNetwork(seed=1069)
for peer in tls.discover():
network.add_cell(peer['name'], knowledge=peer.get('files', 0))
# Propagate knowledge between peers
network.add_propagator(:peer_sync, sources, targets)
network.run_parallel(n_workers=len(peers))
just ts-peers # List tailscale peers
just ls-peers # List localsend peers
just ts-ls-bridge # Bridge both networks
Base directory: ~/.codex/skills/tailscale-localsend
This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:
distributed-systems: 3 citations in bib.duckdbThis skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:
Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826
The skill participates in triads satisfying:
(-1) + (0) + (+1) ≡ 0 (mod 3)
This ensures compositional coherence in the Cat# equipment structure.
npx claudepluginhub plurigrid/asi --plugin asiImplements MCP tools for LocalSend P2P file transfers: discovery/advertising via NATS/Tailscale, session negotiation, transfer, and throughput tuning with spectral gap heuristic.
Manages Tailscale mesh VPN networks via CLI and API: check status/peers, ping devices, list tailnet devices, send files, expose services with serve/funnel, create auth keys.
Guides Tailscale VPN setup and management: CLI commands, subnet routers, exit nodes, Tailscale SSH, ACLs/grants, MagicDNS, Serve/Funnel, API automation for secure mesh networks.