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 HM-Li/graph-engineeringnpx agentmods add plugins/hm-li/graph-engineering/marketplacegit clone --depth 1 https://github.com/HM-Li/graph-engineeringGrade A, and why
graph-engineering 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": "graph-engineering",
"owner": {
"name": "HM-Li"
},
"plugins": [
{
"name": "graph-engineering",
"source": "./",
"description": "Design multi-agent workflows as dependency graphs, not linear pipelines — fan-out/fan-in, verification gates, and per-node-type model/effort allocation."
}
]
}
What ships with it
1 file beside marketplace.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.
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 · 14 lines scan A ad551ca94d0f
graph-engineering is a plugin published in the GitHub repository HM-Li/graph-engineering (2 stars, last pushed 24d 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
graph-engineering-on-research
Graph engineering for AI agents: research as a graph instead of a waiting line — copy-paste templates and slash commands. EN + 繁中.
graph-engineering
Turn your AI agents from a waiting line into a graph: seven slash commands for parallel research, adversarial verification, and consultant roundtables. EN + 繁中.
jaiskills
Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.
jaiskills
Jairo's agent skills for Claude Code — orchestration, verification, prompting, and OpenAI tooling in one plugin.
lavra-marketplace
Plugin marketplace listing 1 plugin: lavra.
lavra
Compound engineering with persistent memory and multi-agent workflows based on beads. 30 specialized agents, 28 commands, 15 skills, and automatic knowledge capture/recall.