What is mesh-comms-core?

A guide to the communication machinery used by the Interlateral command-line agent team. It covers finding shared terminal sessions, sending prompts directly, recording messages, identifying agents, and proving two-way replies.

Use it to set up or troubleshoot direct communication between command-line agents, including terminal-session discovery, message delivery, and reply checks.

It removes uncertainty about how agents reach one another and whether a message was actually received. It also separates message transport from the higher-level process used to collaborate.

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

Your own site

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

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,634 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	$0.00055	$0.01634
Opus 5.5	$0.00022	$0.00654
Sonnet 5.5	$0.00011	$0.00327
Haiku 4.5	$0.00006	$0.00163

Measured 1mo ago against content hash 69c6ed851c6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mesh-comms-core 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/mesh-comms-core/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mesh Comms Core

Purpose

Use this skill before any collaboration pattern that depends on live peer communication.

It covers transport mechanics only:

tmux socket and session discovery
direct prompt delivery
comms.md ledger mirroring
identity stamping
safe TUI submission
two-way ACK proof

It does not assign roles, choose sprint process, onboard desktop peers, or define review/breaker/verifier workflows.

Sprint-specific evidence regimes, gate tables, and approval policies belong in sprint specs or templates, not in this transport skill.

Default peer policy: the normal mesh is Claude Code + Codex. Gemini CLI, Antigravity CLI, and Antigravity Desktop helpers are documented here only so operators can use them after an explicit opt-in decision. Do not treat helper availability as permission to recruit those peers.

Desktop Boundary

Use this skill for CLI mesh transport. If Claude Desktop or Codex Desktop needs to join the mesh, switch to desktop-mesh-peer at .agent/skills/desktop-mesh-peer/SKILL.md.

Desktop agents are manually joined peers. They need their own tmux inbox session, stable identity, direct ACK, and ledger mirror. Do not treat comms.md polling as a desktop join path.

Always In The Path

Every agent handoff depends on these rules. Keep them in the active path whenever agents are coordinating:

Direct-send wakes the peer; comms.md records the event.
Never rely on comms.md alone as a wake-up mechanism.
Pane text alone does not count. A message drafted in a terminal has not been delivered until it is submitted through a live path and, when available, mirrored to the ledger.
Use the shared socket every time: /tmp/interlateral-agents-tmux.sock.
Use repo helpers before raw tmux send-keys.
Use the target-specific helper when one exists; current Claude Code uses claude_send*_logged, while Codex and explicitly selected Gemini peers continue to use the generic helpers.
For Codex, never send C-c to clear input; it can kill the CLI.
Prove new or uncertain comms with a nonce ACK.
Check idle before follow-up prompts so text is not injected into a busy agent.

Read the full file on GitHub · 187 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 · 187 lines · 55 tokens per session scan A 69c6ed851c6a

Subscribe to this mod's changes

mesh-comms-core is a skill published in the GitHub repository dazzaji/interlateral_agents (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,634 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

mesh-comms-core next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mesh-comms-coredazzaji/interlateral_agents	Skill	11	10d ago	Apache-2.0	A	55	Claude Code, Codex
imagegenopenai/codex	Skill	133k	today	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
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

interlateral_agents: Skill for Claude Code