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 GoalfyAI/goalfydatanpx agentmods add plugins/goalfyai/goalfydata/claude-codegit clone --depth 1 https://github.com/GoalfyAI/goalfydataGrade A, and why
goalfydata 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": "goalfydata",
"displayName": "GoalfyData",
"version": "1.0.14",
"description": "Use when users need deep data analysis (multi-round SQL queries, aggregations, trend comparisons) or want to persist data (Excel / CSV / API / database) as long-lived, cross-platform structured assets — typical scenarios include: complex or recurring data analysis, accessing the same data across multiple Agents / services / devices, sharing data for collaboration, and building dashboards from data for public deployment and sharing. GoalfyData is independent of any single project or conversation, covering the complete dataset lifecycle from table creation, import, query analysis, governance rules, permission sharing, credential management, and GoalfyData Managed Refresh (scheduled auto-updates) to dashboard deployment.",
"author": {
"name": "GoalfyAI",
"url": "https://goalfydata.ai/"
},
"homepage": "https://goalfydata.ai/",
"privacyPolicy": "https://goalfydata.ai/privacy",
"termsOfService": "https://goalfydata.ai/terms",
"license": "Apache-2.0",
"keywords": [
"dataset",
"uds",
"data-management",
"data-analysis",
"sql-query",
"goalfydata",
"mcp",
"dashboard",
"visualization",
"report",
"excel",
"csv",
"data-app"
],
"skills": "./skills/",
"mcpServers": "./.mcp.json"
}
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 · 32 lines scan A 79fc3fa05562
goalfydata is a plugin published in the GitHub repository GoalfyAI/goalfydata (9 stars, last pushed 9d 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 2026-08-31.
Other plugins, from other repositories
tsk-config
Guides users through configuring tsk Docker container images for their project, including stack, agent, and project layer setup.
mqc-nlv
新诉讼可视化 · New Litigation Visualization —— 把法律画出来。缪奇川出品的诉讼可视化 skill 集。.
cc-market
Plugin marketplace listing 4 plugins: demo-one, demo-two, demo-three, external-one.
extra-plugin
Not listed in the marketplace.
blocked-resource
blocked-resource. Inspect and compile Claude Code and Codex plugins into auditable DeepSeek Harness bundles.
coding-coach
面向非开发人员的「从想法到上线」技能包：工程（mattpocock/skills 精选）+ 产品（product-manager 等）+ 界面与上线（UI/UX、文案、部署）。Non-developer-friendly product-building skills.