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.
npx agentmods add skills/komdosh/komnet/relaynpx skills add Komdosh/komnet --skill relaygit clone --depth 1 https://github.com/Komdosh/komnetWrote 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.
[](https://agentmods.dev/skills/komdosh/komnet/relay)<a href="https://agentmods.dev/skills/komdosh/komnet/relay"><img src="https://agentmods.dev/badge/skills/komdosh/komnet/relay.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00085 | $0.02018 |
| Opus 5 | $0.00043 | $0.01009 |
| Sonnet 5 | $0.00017 | $0.00404 |
| Haiku 4.5 | $0.00009 | $0.00202 |
Grade A, and why
relay 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The relay protocol
komnet moves messages between machines. Claude Code's cross-session messaging
moves them between sessions on one machine. Neither knows about the other, so a
remote teammate's answer lands in ~/.komnet and sits there until some session
happens to look — which, for a session already mid-task, is whenever that agent
next decides to check, and realistically its next start.
The gateway is one session that closes that gap. It holds the komnet side open and pushes across the local side, so a remote reply reaches a working session in seconds instead of at the next session boundary.
It relays. It does not decide, execute, or speak for anyone.
Roles
Gateway session — one per machine. Started by a person, named so other
sessions can address it, running /komnet-gateway:relay. It owns the komnet
identity for this machine and is the only session that sends to the network on
another session's behalf.
Client session — any other Claude session here. It reaches the network with
/komnet-gateway:ask and needs to know nothing about komnet, rooms, or git.
Two transports, and why there are two
Local delivery is attempted in this order.
1. Cross-session message. SendMessage to the peer's name, as listed by
ListAgents. Instant: it lands between the receiver's tool calls, or starts a
turn if the receiver is idle. This is the path that makes the gateway worth
running.
2. Request file. $KOMNET_HOME/gateway/requests/<ulid>.json, claimed by the
watcher with an atomic rename into claimed/. Slower — bounded by the poll
interval — but it depends on nothing except the filesystem.
The fallback is not paranoia. A session is only reachable by SendMessage when
it has an inbox socket bound, and sessions without one are common: on the
machine this plugin was developed against, one live session out of eight had a
socket, across identical Claude Code versions and entrypoints. A session that
cannot be reached is not a failure to report — it is the normal case the file
path exists for.
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.
- 4d ago First seen · 176 lines · 85 tokens per session scan A 588adecde2ca
relay is a skill published in the GitHub repository Komdosh/komnet (7 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 2,018 once invoked, about $0.0004 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.
Other skills, from other repositories
writing-agent-relay-workflows
Use when building multi-agent workflows with @relayflows/core. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, repairable verification gates, evidence-based completion, mandatory Claude-then-Codex fresh-eyes review/fix loops with test hardening, channels…
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format, eager/lazy activation, and conversion hints.
choosing-swarm-patterns
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate…
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…
creating-claude-agents
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
creating-skills
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples.