What is desktop-mesh-peer?

A procedure for adding Claude Desktop or Codex Desktop as a participant in the Interlateral agent team. The desktop agent gets its own terminal inbox, identity, direct message path, and audit record.

Use it to manually join a desktop coding agent to the mesh and verify that it can receive messages and record important communication.

It prevents desktop agents from being treated as if they were already part of the command-line team. It also requires proof that messages travel through both the direct path and the shared record.

How dazzaji/interlateral_agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dazzaji/interlateral_agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dazzaji/interlateral_agents/main/.agent/skills/desktop-mesh-peer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dazzaji/interlateral_agents

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/desktop-mesh-peer/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/desktop-mesh-peer)

Your own site

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/desktop-mesh-peer"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/desktop-mesh-peer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dazzaji/interlateral_agents/desktop-mesh-peer"><img src="https://agentmods.dev/badge/skills/dazzaji/interlateral_agents/desktop-mesh-peer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,113 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00049	$0.01113
Opus 5.5	$0.00020	$0.00445
Sonnet 5.5	$0.00010	$0.00223
Haiku 4.5	$0.00005	$0.00111

Measured 1mo ago against content hash 1e20f1442b89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

desktop-mesh-peer 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 1mo 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.

.agent/skills/desktop-mesh-peer/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Desktop Mesh Peer

Purpose

Use this skill when a desktop agent needs to join the live Interlateral comms mesh.

Desktop peers are not launched by init or me.sh. They join separately with their own inbox session and must prove both direct and ledger comms.

Required Comms Rules

This skill is self-contained for desktop peer onboarding. Use mesh-comms-core first if the shared socket, helper scripts, or current CLI sessions are not already known.

Every desktop peer must:

own a tmux inbox session on the shared socket /tmp/interlateral-agents-tmux.sock
use a stable desktop identity such as codex-desktop or claude-desktop
receive live messages by direct tmux injection, not by comms.md polling
mirror important messages to interlateral_dna/comms.md as the audit ledger
prove join with a nonce challenge visible in both the direct path and the ledger

Desktop peers are full mesh peers, but they are manually joined peers. The standard init skill only launches the CLI duo.

Default peer policy: desktop peers are opt-in. Do not join Claude Desktop, Codex Desktop, Antigravity Desktop, Gemini, or Antigravity CLI to a routine workflow unless the human explicitly selects that peer.

Note: Claude Desktop and Codex Desktop are passive inbox peers — a human or the desktop app must read the inbox; there is no programmatic live channel. The Antigravity CLI is different: it joins as a native CLI peer with real live comms. To put Antigravity on the mesh, use the agy-cli-peer skill, not this one. See ANTIGRAVITY.md for the full picture.

Identity Choices

Use stable sender identities:

Claude Desktop: claude-desktop
Codex Desktop: codex-desktop

Use stable inbox sessions:

Claude Desktop: ia-claude-desktop
Codex Desktop: ia-codex-desktop

Create Inbox

cd "${INTERLATERAL_AGENTS_REPO:-$PWD}"
source scripts/tmux-config.sh

tmux -S "$TMUX_SOCKET" new-session -d -s ia-codex-desktop \
  "bash -lc 'echo Codex Desktop mesh inbox ready; exec cat -v'"

Read the full file on GitHub · 127 lines

Changes

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.

1mo ago First seen · 127 lines · 49 tokens per session scan A 1e20f1442b89

Subscribe to this mod's changes

desktop-mesh-peer is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,113 once invoked, about $0.0002 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 2026-10-03.

Building agents

desktop-mesh-peer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
desktop-mesh-peerdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	49	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

interlateral_agents: Skill for Claude Code