agent-comm

agent-comm is a skill for Claude Code, Codex from tatargabor/set-agent-comm. It costs 90 tokens per session (4,486 once invoked), scanned A, original, MIT.

A skill for sending and receiving messages between other coding-agent sessions through set-agent-comm, a local message bus.

In plain words
What is it for?
Use it to read the inbox, answer assigned requests, announce your scope, and monitor for new messages.
Why use it?
It helps agents coordinate responsibilities and respond only when a message requires their attention.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tatargabor/set-agent-comm/agent-comm
Any agent
npx skills add tatargabor/set-agent-comm --skill agent-comm
Clone the repo
git clone --depth 1 https://github.com/tatargabor/set-agent-comm

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.

agentmods badge for agent-comm

README.md
[![agentmods](https://agentmods.dev/badge/skills/tatargabor/set-agent-comm/agent-comm.svg)](https://agentmods.dev/skills/tatargabor/set-agent-comm/agent-comm)
Your own site
<a href="https://agentmods.dev/skills/tatargabor/set-agent-comm/agent-comm"><img src="https://agentmods.dev/badge/skills/tatargabor/set-agent-comm/agent-comm.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,486 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.04486
Opus 5 $0.00045 $0.02243
Sonnet 5 $0.00018 $0.00897
Haiku 4.5 $0.00009 $0.00449

Measured 5d ago against content hash b579b17531f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-comm 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 5d 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.

skills/agent-comm/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Talking to the other sessions

The bus is set-agent-comm: one file per session, everyone appends to their own and reads the others'. Rooms here: {{ROOMS}}.

The one rule everything else follows from

Being read is free. Being interrupted is not. A wake-up is a whole turn of this session, on this model, with this project's context behind it. So the bus separates the two, and it does so in the server rather than in your good intentions:

what you send who is interrupted
anything with to exactly those agents
broadcast QUESTION / REQUEST everyone in the room
broadcast FACT / ANSWER nobody — delivered, unread, read when they next look

This is measured, not guessed. In this bus's first two days, 190 entries were written and every single one was a broadcastto was never used, so every entry woke every seat. In one room that produced 23 entries in 8 minutes between four sessions, each a 2000-character broadcast FACT, each re:-chained to the last, and the message saying "I'm closing this off" woke everyone and asked for another answer.

Two habits follow:

  • Broadcast a FACT freely. It costs the others nothing. This is the cheap, generous move.
  • When you need an answer, address it. to: ["<seat>"] — and the seat you want is almost always the from of the entry you are replying to.

…and one trap that comes with them

⚠ A free FACT is not a free lunch. Measured on 2026-08-06 in a six-session live run: all five entries were broadcast FACTs, including the one that renamed an id two other projects had to follow, and a decision that two of them had to agree on. Nobody was woken by any of them. It worked only because every session happened to be given a turn anyway.

So, before you send: does anyone have to DO something because of this?

  • No → broadcast FACT. Free, and everyone gets it.
  • Yes, and you know who → REQUEST (or QUESTION) to that seat. One name.
  • Yes, several people, different things → that is one send each, not one entry naming them all.
  • Yes, but you do not know who → broadcast REQUEST. It wakes the room, which is the price of not knowing, and agents usually answers it first.

Read the full file on GitHub · 327 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.

  1. 5d ago First seen · 327 lines · 90 tokens per session scan A b579b17531f9

Subscribe to this mod's changes

agent-comm is a skill published in the GitHub repository tatargabor/set-agent-comm (2 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 4,486 once invoked, about $0.0005 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens