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 DevExpress/agent-skillsnpx agentmods add plugins/devexpress/agent-skills/dx-reportinggit clone --depth 1 https://github.com/DevExpress/agent-skillsGrade A, and why
dx-reporting 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": "dx-reporting",
"description": "DevExpress XtraReports skills for .NET, ASP.NET Core, Blazor, and Visual Studio designer code patterns: runtime report creation, web viewer/designer integration, safe *.Designer.cs edits, report storage, customization, and export (PDF, XLSX, DOCX, and more).",
"version": "1.5.0",
"license": "MIT",
"author": {
"name": "DevExpress",
"email": "[email protected]",
"url": "https://www.devexpress.com"
},
"skills": "./skills/",
"agents": [
"./agents/devexpress-report-designer-expert.agent.md"
],
"keywords": [
"devexpress",
"reporting",
"xtrareports",
"aspnetcore",
"blazor",
"visual-studio",
"report-designer",
"skills"
],
"mcpServers": {
"dxdocs": {
"url": "https://api.devexpress.com/mcp/docs",
"type": "http"
}
}
}
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 7392e7043d3b
dx-reporting is a plugin published in the GitHub repository DevExpress/agent-skills (49 stars, last pushed 15d 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
telnyx-ai
Telnyx AI — LLM inference, chat completions, embeddings, AI assistants, conversation insights.
cargo
Build with Cargo in Claude Code — 19 skills over the cargo-ai CLI, plus the hosted MCP server (target lists, contact enrichment and verification from licensed data providers, lead scoring, CRM sync, signal monitoring, orchestration, storage, segments, CDK, diagnostics) plus prompt-free approval for safe cargo-ai calls.
cc-commands
CC command and agent compat fixture.
demo-two
Second demo skill.
flightseatmap
Seat maps, seat ratings, traveller reviews and seat alerts for 150+ airlines.
pilot-azure
Azure / Bicep / ACA governance: CAF naming, security baseline, Well-Architected review, Bicep patterns, observability, CI/CD security (OIDC), multi-region DR, cost/FinOps, AKS, API Management, landing zones, SLO/error budgets, and container image security. Ships @infra-reviewer (finds violations), @infra-implementor…