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 Gentech-Labs/genTech-agent-kit --skill desktop-meshgit clone --depth 1 https://github.com/Gentech-Labs/genTech-agent-kitWrote 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/gentech-labs/gentech-agent-kit/desktop-mesh)<a href="https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/desktop-mesh"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/desktop-mesh/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/gentech-labs/gentech-agent-kit/desktop-mesh"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/desktop-mesh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.01703 |
| Opus 5.5 | $0.00031 | $0.00681 |
| Sonnet 5.5 | $0.00016 | $0.00341 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
desktop-mesh 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop Mesh — Peers Across Machines
When to Use
- You run Hermes on more than one machine — e.g. always-on VPS agents plus a desktop/laptop (the Hermes desktop app, a home workstation, a GPU box).
- You want those agents to DM each other and act on handoffs, not just share files.
- You want the desktop to be woken when work arrives, instead of only polling.
- You are wiring agents on different platforms and want one addressable mesh.
The Problem This Solves
hermes peer dm <peer> is the cross-machine twin of a local bot chat — but it silently
fails across machines, and the reason is not obvious:
The api_server binds to 127.0.0.1 by default. Loopback means "this machine
only." Two agents on the same host talk fine. Two agents on different hosts
cannot reach each other at all — even though both are running, both are healthy, and
both are on the same private network.
The failure is invisible from the inside: every local check passes. Only a remote probe reveals it. Always verify from the other end.
The mesh gap is usually symmetric. If your desktop can't reach the server, the server almost certainly can't reach your desktop either — don't fix one direction and declare victory.
Requirements
- A private network between the machines. Tailscale is assumed here (works through NAT, no public exposure, per-node identities); any private overlay (WireGuard, Netmaker, a LAN/VPN) substitutes.
- Hermes installed on both machines.
- Shell access to the server (to set env vars) and to the desktop.
The Fix — Four Steps
1. Bind the api_server to the private interface (not loopback)
These are environment variables, not config.yaml keys. Put them in each profile's
.env (~/.hermes/profiles/<profile>/.env):
API_SERVER_ENABLED=true
API_SERVER_HOST=100.x.y.z # ← your Tailscale IP. THIS is the whole trick.
API_SERVER_PORT=8642
API_SERVER_KEY=<long-random-secret>
Get the right address with tailscale ip -4 on each machine.
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.
- 2d ago First seen · 145 lines · 78 tokens per session scan A 9dc43c326772
desktop-mesh is a skill published in the GitHub repository Gentech-Labs/genTech-agent-kit (0 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,703 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
talking-head-recut
Package an existing talking-head / interview / podcast video by layering timed, designed GRAPHIC OVERLAY cards onto the playing video — titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript. The source video plays in full; the agent designs and writes each card's HTML…
de-ai-polish
A writing-editing tool that detects common AI-style wording and rewrites text to sound more natural.
embedded-captions
Add captions to a talking-head video. ONE catalog (CATALOG.md) of 32 visual identities behind two engines: column-flow (captions composited INTO the scene — matte occlusion + mix-blend; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) and themed constitutions…
skill-creator
A tool for creating, editing, improving, and evaluating agent skills. It can also benchmark skill performance and refine descriptions so the right skill is triggered more reliably.
slideshow
Author a HyperFrames slideshow composition — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching sequences, and hotspot navigation. Use as an intent check when the user asks for a presentation, pitch deck, slide deck, interactive deck, or page-to-deck conversion that might…
evoflow-admin
A command-line administration tool for governing EvoFlow through scripts and terminal commands.