set-core: Skill for Claude Code

.claude/skills/agent-comm/SKILL.md

agent-comm is a skill for Claude Code from tatargabor/set-core. It costs 90 tokens per session (4,619 once invoked), scanned A, original, MIT.

Talking to the other agent sessions over set-agent-comm — reading the inbox, answering what is actually yours, declaring your scope so nobody has to ask, and arming the watch that wakes you when something needs you. Use it when you are told there is unread mail, when a message arrives from another project, from…

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: reads .claude/ paths.

This is tatargabor/set-core's own configuration. It tells Claude Code how to work on set-core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything set-core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tatargabor/set-core. 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/tatargabor/set-core/main/.claude/skills/agent-comm/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tatargabor/set-core

Made for: Claude Code.

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-core/agent-comm.svg)](https://agentmods.dev/skills/tatargabor/set-core/agent-comm)
Your own site
<a href="https://agentmods.dev/skills/tatargabor/set-core/agent-comm"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/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 4,619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.04619
Opus 5 $0.00045 $0.02309
Sonnet 5 $0.00018 $0.00924
Haiku 4.5 $0.00009 $0.00462

Measured today against content hash 70eb6cc72423, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 today.

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.

.claude/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: wpc-board.

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. today First seen · 327 lines · 90 tokens per session scan A 70eb6cc72423

Subscribe to this mod's changes

agent-comm is a skill published in the GitHub repository tatargabor/set-core (35 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 4,619 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 2026-09-06.

Related

Other skills, from other repositories

drug-design

End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.

synthetic-sciences/openscience · 44 tokens

atmos-migration

This skill helps you migrate a repository to Atmos. It covers native Terraform, Terraform Workspaces, Terramate, Terragrunt, Makefiles, Justfiles, and Taskfiles. It gives minimum-disruption paths, file-layout options, workspace mapping, task-to-command mapping, generatehcl/script decomposition, and the remote-state…

cloudposse/atmos · 96 tokens

atmos-components

Component architecture: Terraform root modules, remote source provisioning, abstract components, component inheritance, versioning, mixins, catalog patterns.

cloudposse/atmos · 29 tokens

atmos-design-patterns

Design patterns: stack organization, component catalogs, inheritance, configuration composition, version management, layered configuration.

cloudposse/atmos · 25 tokens

atmos-helmfile

Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.

cloudposse/atmos · 33 tokens

atmos-kubernetes

Native Kubernetes components (experimental): render/plan/diff/apply/deploy/delete/validate via Kubernetes Go SDK server-side apply, components.kubernetes, kubectl/kustomize providers, paths/manifests, provision targets (cluster vs. GitOps repo), and auth.

cloudposse/atmos · 59 tokens