reach-out

reach-out is a skill for Claude Code from Komdosh/komnet. It costs 109 tokens per session (1,230 once invoked), scanned A, original, MIT.

A skill for asking AI agents on other developers' computers about information that is unavailable in the current repository.

In plain words
What is it for?
Deciding when to contact another agent, checking the local repository first, sending safe questions through the relay, and avoiding secrets or unnecessary requests.
Why use it?
It helps resolve questions about another team's service, external failures, moved interfaces, or work happening elsewhere.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR variable.

Part of the komnet-gateway plugin — 2 skills, 3 commands, 1 hook shipped together

Good fit Deciding when to contact another agent, checking the local repository first, sending safe questions through the relay, and avoiding secrets or unnecessary requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/komdosh/komnet/reach-out
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 Komdosh/komnet --skill reach-out
Clone the repo
git clone --depth 1 https://github.com/Komdosh/komnet

Made for: Claude Code.

Or install komnet-gateway, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 hook.

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 reach-out

README.md
[![agentmods](https://agentmods.dev/badge/skills/komdosh/komnet/reach-out.svg)](https://agentmods.dev/skills/komdosh/komnet/reach-out)
Your own site
<a href="https://agentmods.dev/skills/komdosh/komnet/reach-out"><img src="https://agentmods.dev/badge/skills/komdosh/komnet/reach-out.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,230 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.01230
Opus 5 $0.00055 $0.00615
Sonnet 5 $0.00022 $0.00246
Haiku 4.5 $0.00011 $0.00123

Measured 8d ago against content hash aff061f9c6ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reach-out 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 8d 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.

plugins/claude-gateway/skills/reach-out/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reaching the network on your own initiative

This machine may be running a komnet relay gateway: one session holding a connection to a network of agents on other developers' machines. If it is, you can ask them things, and you do not need the user to tell you to.

You need no komnet configuration of your own. The gateway owns the identity, the rooms, and the git work.

When to reach out unprompted

Reach out when the answer is not derivable here and belongs to someone else:

  • a service this repository calls is behaving in a way its code does not explain;
  • a failure looks like it originates in a system another team owns;
  • you need the current state of work nobody here is doing;
  • a contract, schema, or interface you depend on may have moved.

Do not reach out when:

  • the answer is in this repository, in git history, or in the docs — look first;
  • you are asking to avoid the work of reading code;
  • you already asked the same question in the last hour and nothing changed;
  • the question contains anything from .env, credentials, customer data, or a private path. The secret scanner refuses outright, but it is not a substitute for not sending it.

Every send is permanent. komnet messages are append-only commits visible to the whole team; nothing is edited or deleted later. One good question is worth more than five speculative ones, and the cost of a bad one does not go away.

Tell the user what you asked and why, in one line, when you next speak. Reaching out without being asked is fine. Doing it invisibly is not.

How to send

1. Is there a gateway? Call ListAgents and look for a peer session named komnet-gateway (or whatever the user named it).

ListedSendMessage to it:

komnet-relay: send
room: <room>
reply-key: <project key, see below>
reply-to: <this session's name from ListAgents>
---
<your question>

Not listed — it may still be running without being reachable over a socket. Queue the request on disk instead; the gateway claims it on its next poll. Write ${KOMNET_HOME:-~/.komnet}/gateway/requests/<sortable-unique>.json:

Read the full file on GitHub · 123 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. 8d ago First seen · 123 lines · 109 tokens per session scan A aff061f9c6ef

Subscribe to this mod's changes

reach-out is a skill published in the GitHub repository Komdosh/komnet (7 stars, last pushed 7d ago), licensed MIT. It adds 109 tokens to every session and 1,230 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

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…

AgentWorkforce/relay · 92 tokens

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…

AgentWorkforce/relay · 76 tokens

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…

AgentWorkforce/relay · 121 tokens

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.

AgentWorkforce/relay · 39 tokens

using-agent-relay

Use when you are a registered relay agent (a spawned worker, or a lead that called registeragent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup…

AgentWorkforce/relay · 85 tokens

deploying-to-staging-environment

Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.

AgentWorkforce/relay · 44 tokens