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.
/plugin marketplace add cloud1map/agent-relaynpx agentmods add plugins/cloud1map/agent-relay/marketplacegit clone --depth 1 https://github.com/cloud1map/agent-relayGrade 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 yesterday.
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",
"interface": {
"displayName": "Agent Relay"
},
"plugins": [
{
"name": "agent-relay",
"source": {
"source": "local",
"path": "./plugins/agent-relay"
},
"policy": {
"installation": "AVAILABLE",
"authentication": "ON_INSTALL"
},
"category": "Developer Tools"
}
]
}
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.
- yesterday First seen · 21 lines scan A 325ad24a370a
agent-relay is a plugin published in the GitHub repository cloud1map/agent-relay (0 stars, last pushed 5d ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
a2amesh
A2A Mesh workflows for endpoint validation, approved task operations, and security-bounded MCP consumption.
swarmwage
Hire other AI agents from inside Claude Code. Discover, hire, and pay specialized agents in USDC on Base via the open Swarmwage protocol — sub-second sync calls, on-chain receipts, zero protocol fee. Ships an MCP server plus two skills (buyer-side hire + seller-side publish).
wire
Magic-wormhole for AI agents — bilateral signed-message bus over local and federated mailbox relays. Rust-native MCP server with Ed25519-rooted identity. Discover, pair, and message Claude, Codex, and Copilot agents from this session.
ainb-hooks
Emit every safely observable Claude Code lifecycle event into Hangar's durable provider log. User-facing events still reach ainb-notifyd over its Unix socket. The same notify.sh powers ATC structured control when installed with AINBMANAGED=atc. stallguard.py additionally blocks turn-end when a session would idle on i.
google-search-console-mcp
Plugin marketplace listing 1 plugin: google-search-console-mcp.
tdmcp
Plugin marketplace listing 1 plugin: tdmcp.