What is warp-mesh-peer?

A skill for connecting Claude Code and Codex CLI to a shared Interlateral agent network through Warp terminal panes. Warp displays the terminals, while tmux carries messages between them.

It is for opening or attaching Warp panes to Claude and Codex sessions, setting up the launch configuration, and sending work through tmux.

It avoids using unsupported Warp features as the communication channel and ensures agents target the correct terminal session.

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/warp-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/warp-mesh-peer/github.svg)](https://agentmods.dev/skills/dazzaji/interlateral_agents/warp-mesh-peer)

Your own site

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

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,006 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	$0.00044	$0.01006
Opus 5.5	$0.00018	$0.00402
Sonnet 5.5	$0.00009	$0.00201
Haiku 4.5	$0.00004	$0.00101

Measured 1mo ago against content hash c051fc7fc6d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

warp-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/warp-mesh-peer/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Warp Mesh Peer

Purpose

Use this skill when the human wants Interlateral CLI agents visible inside Warp while preserving the standard tmux mesh.

Warp is the terminal surface. tmux remains the transport. Do not use Warp Oz, Warp Drive, AppleScript, or Accessibility paste as the mesh channel.

Boundary

This skill is for Claude Code and Codex CLI running inside tmux sessions that are attached from Warp panes.

It is not the Desktop join path. If Claude Desktop or Codex Desktop needs to join the mesh, use desktop-mesh-peer.

Canonical Sessions

Claude Code in Warp: ia-claude-warp
Codex CLI in Warp: ia-codex-warp

Suffix variants are allowed for reviews or sprints, for example:

ia-claude-warp-review
ia-codex-warp-breaker

Always target the exact tmux session name.

Quick Start

Install or refresh the Warp launch configuration:

scripts/install-warp-launch-config.sh --force

Open the Warp mesh:

open "warp://launch/interlateral-warp-mesh"

This opens Warp panes attached to:

ia-claude-warp
ia-codex-warp

If the sessions do not exist, the wrapper creates them using the existing repo launchers.

Manual Attach

Run either peer directly:

scripts/warp-mesh-peer.sh claude ia-claude-warp
scripts/warp-mesh-peer.sh codex ia-codex-warp

Relaunch one named peer explicitly:

scripts/warp-mesh-peer.sh --relaunch claude ia-claude-warp
scripts/warp-mesh-peer.sh --relaunch codex ia-codex-warp

The wrapper never kills an existing session unless --relaunch is supplied.

Comms

Use the same mesh helpers as the rest of the repo.

For Warp Claude:

source scripts/tmux-config.sh
claude_send_long_logged =ia-claude-warp: "ACK challenge: warp-claude-001. Reply with this nonce."

For Warp Codex:

source scripts/tmux-config.sh
agent_send_long_logged =ia-codex-warp: "ACK challenge: warp-codex-001. Reply with this nonce."

comms.md is the ledger, not the wake-up path. A valid proof has both a visible direct reply and a stamped ledger entry.

Read the full file on GitHub · 133 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 · 133 lines · 44 tokens per session scan A c051fc7fc6d5

Subscribe to this mod's changes

warp-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 44 tokens to every session and 1,006 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

warp-mesh-peer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
warp-mesh-peerdazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	44	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