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 skills add AgentWorkforce/relay --skill orchestrating-agent-relaygit clone --depth 1 https://github.com/AgentWorkforce/relayWrote 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/agentworkforce/relay/orchestrating-agent-relay)<a href="https://agentmods.dev/skills/agentworkforce/relay/orchestrating-agent-relay"><img src="https://agentmods.dev/badge/skills/agentworkforce/relay/orchestrating-agent-relay/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentworkforce/relay/orchestrating-agent-relay"><img src="https://agentmods.dev/badge/skills/agentworkforce/relay/orchestrating-agent-relay.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.05357 |
| Opus 5.5 | $0.00024 | $0.02143 |
| Sonnet 5.5 | $0.00012 | $0.01071 |
| Haiku 4.5 | $0.00006 | $0.00536 |
Grade D, and why
orchestrating-agent-relay scanned grade D with 2 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 23d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 .agentworkforce/relay/orchestrator.token # tighten a pre-existing file too Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| Half-started broker: process alive but `node status` says stopped and `Failed to read broker connection metadata` | `node up` spawned a broker that never finished writing connection metadata (readiness timed out) and w How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
A headless orchestrator is an agent that:
- Starts the local relay broker itself (
agent-relay node up) - Spawns and manages worker agents on that broker
- Monitors agent lifecycle events
- 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
errors with Not registered. Call the "register_agent" tool first. until it
does. Lifecycle
control — starting the broker, spawning/releasing local agents, streaming
broker debug events — goes through the agent-relay node command group. The
workers it spawns are registered participants too; their peer-messaging
reference is the using-agent-relay skill.
The model
- Agent Relay delivers messages node-only: every agent is owned by a node,
- A fleet is the set of nodes advertising capabilities (
spawn:<harness> - Agent-to-agent coordination is messages — channels, DMs, threads — plus
When to Use
- Agent needs full control over its worker team
- No human available to run
agent-relay node upmanually - Agent should manage agent lifecycle autonomously
- Building self-contained multi-agent systems
Quick Reference
| Step | Command/Tool |
|---|---|
| Verify installation | command -v agent-relay or npx agent-relay --version |
| Verify Node runtime if shim fails | node --version or fix mise/asdf first |
| Start broker | agent-relay node up --background --verbose |
| Check broker readiness | agent-relay node status --wait-for 10 |
| Workspace + cloud + broker status | agent-relay status |
| Spawn worker | agent-relay node agent spawn claude --name Worker1 --task "..." |
| List workers | agent-relay node agent list |
| Resource usage | agent-relay node metrics |
| Send DM to worker (MCP) | send_dm(to: "Worker1", text: "...") |
| Post to channel (MCP) | post_message(channel: "general", text: "...") |
| Read worker replies (MCP) | check_inbox(limit: 20) / list_messages(channel: "general") |
| Give a human a follow-along link | agent-relay observer |
| Inspect a worker's TTY | agent-relay node agent attach Worker1 --mode view |
| Release worker | agent-relay node agent release Worker1 |
| Stop broker | agent-relay node down |
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.
- 23d ago Changed · -3 lines e08adf111011
- 26d ago First seen · 383 lines · 61 tokens per session scan D 4982c1a55640
orchestrating-agent-relay is a skill published in the GitHub repository AgentWorkforce/relay (885 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 5,357 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.
Other skills, from other repositories
kirocrew-app-dev
Build, package, and publish Kiro Crew external apps. Covers app.json manifests, UI components, crons, skills, lifecycle hooks, development mode, registry publishing, and common pitfalls.
goal-conductor
Own a goal too large for one session ('clear the flaky-test backlog', 'push N PRs green') end to end via the work ledger — decompose into items, one session per item, read worker status as data, verify claims with the acceptance evaluator, decide each round until done. Use when handed such a goal.
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.