Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add plurigrid/asi --skill localsend-mcpgit clone --depth 1 https://github.com/plurigrid/asiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/plurigrid/asi/localsend-mcp)<a href="https://agentmods.dev/skills/plurigrid/asi/localsend-mcp"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/localsend-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/plurigrid/asi/localsend-mcp"><img src="https://agentmods.dev/badge/skills/plurigrid/asi/localsend-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01212 |
| Opus 5 | $0.00014 | $0.00606 |
| Sonnet 5 | $0.00005 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
localsend-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LocalSend MCP Skill
Use This Skill When
- The user mentions LocalSend, AirDrop-like transfer, or peer-to-peer file sharing.
- The task asks for an MCP server or tool set around LocalSend.
- Discovery/advertising needs to use NATS or Tailscale before transferring data.
Reality Check (LocalSend in This Repo)
localsend(Flox package) launches a GUI and does not exit for--help.- Discovery uses UDP multicast
224.0.0.167:53317(LAN only). - Transfer runs HTTPS on port
53317; direct IPs are required across subnets. - For headless automation, prefer a CLI client (e.g.,
jocalsend) or a small protocol wrapper.
Architecture: Advertise -> Negotiate -> Transfer -> Tune
- Advertise capabilities over NATS (or Tailscale if LAN multicast is blocked).
- Negotiate transport and parameters (LAN multicast vs direct IP).
- Transfer via LocalSend protocol/CLI.
- Tune throughput until spectral gap <= 0.25 (>= 75% of target throughput).
MCP Tool Set (Draft)
Discovery / Advertising
localsend_advertise:- Inputs:
agent_id,device_name,localsend_port,tailscale_ip?,capabilities,spectral_gap_target
- Inputs:
localsend_list_peers:- Inputs:
source=localsend_multicast|nats|tailscale
- Inputs:
Session Negotiation
localsend_negotiate:- Inputs:
peer_id,preferred_transport,max_chunk_bytes,max_parallel - Output:
session_id,transport,target_ip,port
- Inputs:
Transfer
localsend_send:- Inputs:
session_id,file_path,chunk_bytes,parallelism
- Inputs:
localsend_receive:- Inputs:
session_id,dest_dir,accept
- Inputs:
Throughput Tuning
localsend_probe:- Inputs:
session_id,probe_bytes,probe_parallelism - Output:
throughput_bps,rtt_ms,loss_rate
- Inputs:
localsend_session_status:- Inputs:
session_id - Output:
bytes_sent,bytes_received,throughput_bps,spectral_gap
- Inputs:
Spectral Gap Heuristic (Practical)
Define:
spectral_gap = 1.0 - (observed_throughput / target_throughput)
Stop tuning when spectral_gap <= 0.25.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 135 lines · 27 tokens per session scan A e7303d138727
localsend-mcp is a skill published in the GitHub repository plurigrid/asi (62 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,212 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…