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.
npx skills add maxanatsko/mcp-engine-public --skill mcp-engine-model-qualitygit clone --depth 1 https://github.com/maxanatsko/mcp-engine-publicWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/maxanatsko/mcp-engine-public/mcp-engine-model-quality)<a href="https://agentmods.dev/skills/maxanatsko/mcp-engine-public/mcp-engine-model-quality"><img src="https://agentmods.dev/badge/skills/maxanatsko/mcp-engine-public/mcp-engine-model-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/maxanatsko/mcp-engine-public/mcp-engine-model-quality"><img src="https://agentmods.dev/badge/skills/maxanatsko/mcp-engine-public/mcp-engine-model-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00115 | $0.00622 |
| Opus 5 | $0.00057 | $0.00311 |
| Sonnet 5 | $0.00023 | $0.00124 |
| Haiku 4.5 | $0.00012 | $0.00062 |
Grade A, and why
mcp-engine-model-quality 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 9d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
4 files beside SKILL.md 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.
- 9d ago First seen · 54 lines · 115 tokens per session scan A 91f14c508cdc
mcp-engine-model-quality is a skill published in the GitHub repository maxanatsko/mcp-engine-public (256 stars, last pushed 12d ago), with no licence file. It adds 115 tokens to every session and 622 once invoked, about $0.0006 per session on Opus 5. 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 skills, from other repositories
powerbi-expert
Expert-level Power BI, DAX, M language, data modeling, Power Query, report design, and paginated reports. Use when the user mentions DAX, Power Query, BI, Microsoft platforms, analytics, or data modeling, or when the task involves DAX Fundamentals, Advanced DAX, Row-Level Security, or Report Design.
shadow-perception-powerbi
Pre-publish council for Power BI Tabular models. Five voices review .bim / .tmdl / .dax for divide-by-zero without DIVIDE(), USERPRINCIPALNAME() bypassable without an RLS role, duplicate measure names, PII column references, and performance smells (nested CALCULATE, EARLIER pattern). Returns SHIP / REWORK / BLOCK…
powerbi-mcp
Kết nối và tương tác trực tiếp với Power BI Desktop (Local) và Power BI Service (Cloud) qua MCP Server.
powerbi-pipeline
Quy trình chuẩn 9 khâu để AI Agent làm phân tích dữ liệu end-to-end trên Power BI — từ kết nối Power Query, transform M, mô hình hóa, DAX, đến trang báo cáo hoàn thiện theo template và chưng cất tri thức. Kích hoạt khi người dùng yêu cầu: "phân tích dữ liệu với Power BI", "dựng báo cáo Power BI từ đầu", "làm dashboard…
kpim-analysis
Quy trình phân tích KPIM để AI Agent triển khai một dự án báo cáo Power BI trọn vẹn từ một bộ dữ liệu + tài liệu đầu vào — tự khảo sát, hỏi ngược người dùng, dựng tài liệu nghiệp vụ chuẩn hóa (6 mindmap + bảng), lập kế hoạch (Excel), rồi bàn giao cho powerbi-pipeline thực thi. Kích hoạt khi user: "phân tích bộ dữ liệu…
powerbi-knowledge
Knowledge OS của powerbi-agent — cơ chế lưu trữ & học hỏi tri thức dự án Power BI vào thư mục dự án do USER CHỈ ĐỊNH ngoài repo (mặc định /powerbi-project). Kích hoạt khi: bắt đầu/kết thúc dự án Power BI, user nói "lưu tri thức", "đóng gói kiến thức", "dự án cũ làm thế nào", "đã từng làm gì tương tự", "quét thiết kế…