Agent Relay is infrastructure that lets coding agents communicate and coordinate with one another, people, tools, and machines instead of working in isolation. Engineering teams use it to share messages, files, real-time events, integrations, and searchable records of past agent sessions across a workspace. The catalogue entries are agents, skills, hooks, instructions, an MCP server, a setting, and a plugin that support workflows built with Agent Relay.
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.
git 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/plugins/agentworkforce/relay/gemini-relay-extension)<a href="https://agentmods.dev/plugins/agentworkforce/relay/gemini-relay-extension"><img src="https://agentmods.dev/badge/plugins/agentworkforce/relay/gemini-relay-extension/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/plugins/agentworkforce/relay/gemini-relay-extension"><img src="https://agentmods.dev/badge/plugins/agentworkforce/relay/gemini-relay-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-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 2mo 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.
What it actually says
{
"name": "agent-relay",
"version": "0.1.0",
"description": "Lets your Gemini CLI sub-agents communicate with each other in real time",
"contextFileName": "GEMINI.md",
"mcpServers": {
"agent-relay": {
"command": "node",
"args": ["${extensionPath}${/}relay-server.js"],
"cwd": "${extensionPath}"
}
},
"permissions": {
"autoApprove": [
{
"toolName": "agent-relay.*",
"reason": "Allow real-time agent-to-agent communication"
},
{
"toolName": "mcp_agent_relay_*",
"reason": "Allow real-time agent-to-agent communication (compat)"
}
]
}
}
What ships with it
19 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/relay-researcher.md 906 B
- agents/relay-reviewer.md 908 B
- agents/relay-worker.md 883 B
- commands/fanout/fanout.toml 909 B
- commands/status/status.toml 465 B
- commands/team/team.toml 1.1 KB
- GEMINI.md 3.8 KB
- hooks/after-agent-inbox.sh 2.2 KB runs code
- hooks/after-tool-inbox.sh 1.5 KB runs code
- hooks/before-model-inject.sh 2.4 KB runs code
- hooks/hooks.json 1.5 KB
- hooks/session-end.sh 2.1 KB runs code
- hooks/session-start.sh 2.6 KB runs code
- hooks/subagent-bootstrap.sh 606 B runs code
- package-lock.json 286 B
- package.json 1.0 KB
- README.md 5.3 KB
- relay-server.js 6.2 KB runs code
- setup.sh 1.5 KB runs code
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.
- 2mo ago First seen · 26 lines scan A 670c78c111d5
agent-relay is a plugin published in the GitHub repository AgentWorkforce/relay (1,094 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
agent-relay compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-relayAgentWorkforce/relay | Plugin | 1.1k | yesterday | Apache-2.0 | A | — | Gemini CLI |
| adealvin-reyes/better-agentic-ide | Plugin | 45 | 2d ago | MIT | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 65k | 9d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 46k | yesterday | Apache-2.0 | A | — | Claude Code |
| nextjsvercel/next.js | Plugin | 143k | yesterday | MIT | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | yesterday | Apache-2.0 | A | — | Gemini CLI |
| knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins | Plugin | 35k | 2d ago | Apache-2.0 | A | — | Claude Code |