What is Multi-Agent Comms?

A guide to communication between multiple coding agents, including keeping sessions alive, finding peer identities, and choosing message types.

Use it to send one-way updates, make correlated requests, reply to messages, manage keep-alive sessions, and record important decisions in shared work tracking.

It helps agents coordinate without confusing temporary messages with durable project state or sending requests to the wrong peer.

Multi-Agent Comms — Skill for Claude Code and Codex by lukacf/meerkat

Install

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.

Any agent

npx skills add lukacf/meerkat --skill multi-agent-comms

Clone the repo

git clone --depth 1 https://github.com/lukacf/meerkat

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/lukacf/meerkat/multi-agent-comms/github.svg)](https://agentmods.dev/skills/lukacf/meerkat/multi-agent-comms)

Your own site

<a href="https://agentmods.dev/skills/lukacf/meerkat/multi-agent-comms"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/multi-agent-comms/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/lukacf/meerkat/multi-agent-comms"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/multi-agent-comms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 377 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	$0.00020	$0.00377
Opus 5.5	$0.00008	$0.00151
Sonnet 5.5	$0.00004	$0.00075
Haiku 4.5	$0.00002	$0.00038

Measured 1mo ago against content hash 5f67a766866d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Multi-Agent Comms 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.

crates/meerkat-comms/skills/multi-agent-comms/SKILL.md · 40 lines

What it actually says

Multi-Agent Communication

Use comms for live collaboration between agents. Comms moves messages and correlated requests; it is not durable shared work state.

Operating Rules

Use runtime-backed keep-alive mode with a comms_name when a session should receive peer messages after the first turn. keep_alive without a comms_name is invalid; standalone session-service use does not provide the keep-alive lifecycle.
Use one-way messages for ordinary coordination and request/response only when you need a correlated answer.
Call peers before sending and address the canonical peer_id. Names are display labels, not identity, and peers can expose different send kinds.
Use reply_to_peer for the message that triggered the current turn, send_message for unsolicited one-way outreach, and send_request/send_response only for typed correlated contracts.
Prefer queued delivery. Steering interrupts active work and should be reserved for urgent coordination.
Keep durable commitments, claims, dependencies, and terminal outcomes in WorkGraph when WorkGraph is available.
Summarize important peer decisions back into durable artifacts or WorkGraph evidence when they matter beyond the live conversation.

Transport Notes

UDS is for same-machine low-latency peers.
TCP is for cross-machine peers.
In-process transport is for peers in the same runtime.
Trust is keyed by canonical peer identity. A transport address or matching display name alone does not establish trust, and name replacement is a trusted host operation rather than an agent-side shortcut.

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 · 40 lines · 20 tokens per session scan A 5f67a766866d

Subscribe to this mod's changes

Multi-Agent Comms is a skill published in the GitHub repository lukacf/meerkat (23 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 377 once invoked, about $0.0001 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 2026-08-30.

Building agents Claude Code agentic ai ai-agents claude cli

stuck

Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.

QwenLM/qwen-code · 57 tokens

e2e-testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…

QwenLM/qwen-code · 94 tokens

structured-debugging

Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…

QwenLM/qwen-code · 85 tokens

desktop-brand-builder

Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.

QwenLM/qwen-code · 68 tokens

batch-api

Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.

QwenLM/qwen-code · 51 tokens

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens