orchestrating-agent-relay SKILL.md skillA

orchestrating-agent-relay from agentworkforce/relay is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add agentworkforce/relay/orchestrating-agent-relay@git:20261108.43a614d

Pins git:20261108.43a614d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
agentworkforce/relay
Path
.agents/skills/orchestrating-agent-relay/SKILL.md
Versions recorded
4
Latest version
git:20261108.43a614d, committed Nov 8, 2026
First version recorded
May 19, 2026
Size
50,323 bytes
Repository stars
1,134
License
Apache-2.0

The canonical way to run agent-relay - set up the Agent Relay core with `agent-relay init` and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

> **The local broker was removed.** `agent-relay node up`, `node down`,
> `node status`, `node metrics`, `node tail`, `node deadletters`,
> `node redeliver` and `node agent …` now only print a removal notice. Run
> `agent-relay init` to set up and start the Agent Relay core (or
> `agent-relay init --hosted` for the hosted service), then spawn, list and
> release agents through the relay MCP (`add_agent`, `list_agents`,
> `remove_agent`) or the desktop app. Sections below that still mention the
> broker, `node agent …`, `node tail` or `--state-dir` describe older releases.

### Overview

A headless orchestrator is an agent that:

1. Makes sure the Agent Relay core is set up on this machine (`agent-relay init`;
   `agent-relay init --hosted` to use the hosted service instead)
2. Spawns and manages worker agents through the relay MCP
3. Monitors agent lifecycle events
4. Coordinates work without human intervention

The orchestrator drives the team and reads/sends/lists through the **Agent
Relay MCP server** (`agent-relay mcp`). The session registers itself once with
the `register_agent` tool (name it `orchestrator`) — every messaging tool
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_adwojglpythiz4oc/3d7ac13a65a792c50a5d55e6177215d4fb96b1c25c0531077dfb5106067d1630.json

Then /plugin install orchestrating-agent-relay@markdownregistry-adwojglpythiz4oc in Claude Code. It installs git:20261108.43a614d, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add agentworkforce/relay/orchestrating-agent-relay@sha256:3d7ac13a65a792c5

The line at the top of this page pins the label git:20261108.43a614d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_adwojglpythiz4oc.svg)](https://markdownregistry.com/a/art_adwojglpythiz4oc)

7 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in agentworkforce/relay/orchestrating-agent-relay since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of orchestrating-agent-relay from somewhere else? Ask it: where did my orchestrating-agent-relay come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 4 versions of this file, between May 19, 2026 and Nov 8, 2026, about one every 58 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261108.43a614d latest2026-11-08 43a614d 50,323 BA view · diff
git:20260922.12ce6472026-09-22 12ce647 49,962 BA view · diff
git:20260919.270f08c2026-09-19 270f08c 50,142 BA view · diff
git:20260519.f5dd2592026-05-19 f5dd259 12,880 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (50323 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agentworkforce/relay · 1,134 stars · license Apache-2.0 · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_adwojglpythiz4oc
GET https://markdownregistry.com/api/v1/resolve?ref=agentworkforce/relay/orchestrating-agent-relay
GET https://markdownregistry.com/api/v1/blob/3d7ac13a65a792c50a5d55e6177215d4fb96b1c25c0531077dfb5106067d1630

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from agentworkforce/relay

choosing-swarm-patterns SKILL.md skill
agentworkforce/relay · .agents/skills/choosing-swarm-patterns/SKILL.md · Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration…
git:20261106.567a3d8 · audit A · 1,134 stars
creating-agent-skills SKILL.md skill
agentworkforce/relay · .agents/skills/creating-agent-skills-skill/SKILL.md · Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the…
git:20260919.270f08c · audit A · 1,134 stars
emil-design-eng SKILL.md skill
agentworkforce/relay · .agents/skills/emil-design-eng/SKILL.md · This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible…
git:20260619.f9a7ef7 · audit A · 1,134 stars
relay-80-100-workflow SKILL.md skill
agentworkforce/relay · .agents/skills/relay-80-100-workflow/SKILL.md · Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the…
git:20260919.270f08c · audit A · 1,134 stars
review-animations SKILL.md skill
agentworkforce/relay · .agents/skills/review-animations/SKILL.md · Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy…
git:20260619.f9a7ef7 · audit A · 1,134 stars
review-fix-signoff-loop SKILL.md skill
agentworkforce/relay · .agents/skills/review-fix-signoff-loop/SKILL.md · Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context…
git:20260519.f5dd259 · audit A · 1,134 stars
setting-up-relayfile SKILL.md skill
agentworkforce/relay · .agents/skills/setting-up-relayfile/SKILL.md · Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a…
git:20260919.270f08c · audit C · 1,134 stars
using-agent-relay SKILL.md skill
agentworkforce/relay · .agents/skills/using-agent-relay/SKILL.md · Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with…
git:20261010.4722976 · audit A · 1,134 stars
writing-relayflows SKILL.md skill
agentworkforce/relay · .agents/skills/writing-relayflows/SKILL.md · Use when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is…
git:20260919.270f08c · audit A · 1,134 stars
accessibility Claude Code subagent
agentworkforce/relay · .claude/agents/accessibility.md · A11y auditing, WCAG compliance, and inclusive design review. Ensures digital content is usable by everyone.
git:20260814.67b52ca · audit A · 1,134 stars
api-designer Claude Code subagent
agentworkforce/relay · .claude/agents/api-designer.md · REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for…
git:20260814.67b52ca · audit A · 1,134 stars
architect Claude Code subagent
agentworkforce/relay · .claude/agents/architect.md · System design and architecture decisions. Technical planning, tradeoff analysis, and design documentation.
git:20260525.164e16b · audit A · 1,134 stars

Every file in agentworkforce/relay

Other files named orchestrating-agent-relay

orchestrating-agent-relay SKILL.md skill
agentworkforce/relay · .claude/skills/orchestrating-agent-relay/SKILL.md · The canonical way to run agent-relay - set up the Agent Relay core with `agent-relay init` and autonomously spawn…
git:20261108.43a614d · audit A · 1,134 stars

Browse by kind, by grade A, or by owner.

Kept in .agents/skills, the folder Codex reads. More agent skills for Codex.