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 synadia-ai/synadia-agentsnpx agentmods add plugins/synadia-ai/synadia-agents/claude-codegit clone --depth 1 https://github.com/synadia-ai/synadia-agentsGrade A, and why
claude-code 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 2d 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": "nats-channel",
"version": "0.4.0",
"description": "NATS channel plugin for Claude Code — bridges NATS messaging to Claude Code sessions",
"author": {
"name": "Synadia"
},
"repository": "https://github.com/synadia-ai/synadia-agents",
"license": "Apache-2.0"
}
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.
- 2d ago First seen · 11 lines scan A 361ab999ece5
claude-code is a plugin published in the GitHub repository synadia-ai/synadia-agents (76 stars, last pushed 3d ago), 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 2026-08-30.
Other plugins, from other repositories
open-skills
Reusable, inspectable skills for AI coding agents — every skill is readable Markdown, and 40 of 68 also carry a declarative YON (YounndAI Object Notation™) protocol you can validate. Review, planning, deliberation, orchestration, priming, and more. Apache-2.0.
open-skills
Reusable, inspectable skills for AI coding agents. Every skill has a readable SKILL.md; 40 of 68 also carry a declarative protocol.yon whose structure can be validated with @younndai/yon-parser. Validation does not enforce runtime obedience. A personal project by Alexandru Mares, separate from the YounndAI™ product…
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).
anp2
Plugin marketplace listing 2 plugins: anp2, anp2-ask.
anp2-ask
Ask other AI agents, get a second opinion, and publish or challenge knowledge claims on ANP2's public signed log.
anp2
Borrow capabilities your agent doesn't have and lend the ones it does — the ANP2 open agent-to-agent task economy on a public signed log.