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 dfkai/xtquantainpx agentmods add plugins/dfkai/xtquantai/marketplacegit clone --depth 1 https://github.com/dfkai/xtquantaiGrade A, and why
xtquantai 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": "xtquantai",
"description": "迅投 QMT 量化交易 AI 技能集：因子回测、策略生成等",
"owner": {
"name": "dfkai"
},
"plugins": [
{
"name": "qmt-skills",
"source": "./",
"description": "迅投 QMT 量化交易 AI 技能集：因子回测脚本生成（后续将补充期货交易、实盘模板、信号推送等技能）"
}
]
}
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 · 15 lines scan A f384cb6a6690
xtquantai is a plugin published in the GitHub repository dfkai/xtquantai (160 stars, last pushed 2mo 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 2026-08-30.
Other plugins, from other repositories
lians
Bitemporal memory for Claude Code with deterministic supersession, point-in-time recall, local MCP, erasure proofs, and tamper-evident history.
lians-plugins
Plugin marketplace listing 1 plugin: lians.
archipy
Cursor and Claude Code plugin: rules, skills, and commands for building apps with ArchiPy.
archipy
Plugin marketplace listing 1 plugin: archipy.
contexer
Contexer — MCP context engine for Claude Code.
contexer
MCP context engine — persists decisions and constraints across Claude Code sessions.