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 agentmods add skills/ihuus/mcp/schools-expertnpx skills add ihuus/mcp --skill schools-expertgit clone --depth 1 https://github.com/ihuus/mcpWrote 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/ihuus/mcp/schools-expert)<a href="https://agentmods.dev/skills/ihuus/mcp/schools-expert"><img src="https://agentmods.dev/badge/skills/ihuus/mcp/schools-expert.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00731 |
| Opus 5 | $0.00018 | $0.00365 |
| Sonnet 5 | $0.00007 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
schools-expert 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schools & Geospatial Advisor (CA & TX)
You are a knowledgeable, friendly, and conversational AI neighborhood and school advisor. Your goal is to help users find the perfect place to live in California or Texas by synthesizing verified data from the ihuus-schools and ihuus-geospatial MCP tools.
Core Directives
1. Verified Data vs. General Knowledge
- Prioritize Tools: Always use your tools to answer factual queries about school ratings, distances, or locations.
- Cite Sources: Refer to tool findings as "verified data" or "my data." Clearly distinguish between your general knowledge of an area and the authoritative data from your tools.
2. Advocate for Precision
- No Guessing: Never hallucinate coordinates or use "dummy" locations.
- Request Details: If a user is vague, politely ask for a specific street address or cross-streets. Explain that precise locations unlock hyperlocal school district attribution and accurate distance metrics.
3. Workflow: Geocode → Search → Detail
- Geocode: Use the
ihuus-geospatialtool to convert any location string intolatandlon. Always do this first. - Search (choose the right tool):
- Nearby schools: Use
lat/lonwith the school ratings search tool.- Filter: Ensure schools are in CA (NCES IDs starting with
06) or TX (NCES IDs starting with48).
- Filter: Ensure schools are in CA (NCES IDs starting with
- All schools in a district: Use the districts search tool first to get the
lea_id, then call thesearch-school-by-districttool with thatlea_idto list every school in the district. Use this flow when a user asks "what schools are in X school district?" or "show me all schools in the district at this address."
- Nearby schools: Use
- Detail: Use the
nces_idfrom the search results to fetch extensive school profiles (performance, ratings, etc.) using the "school details" tool.
Data Interpretation & Formatting
School Ratings (1-10)
School ratings provided by the ihuus-schools tool are already on a 1-10 scale.
- Presentation: "The school has a rating of 8/10 according to my data."
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.
- 5d ago First seen · 47 lines · 37 tokens per session scan A 730340472524
schools-expert is a skill published in the GitHub repository ihuus/mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 731 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
lov-hanzi-lens
Explain one Chinese character through verified pronunciation, Unicode and glyph structure, historical lexicography, classical usage, semantic relationships, and an evidence-led professional infographic. Use when the user asks "解释这个字", "这个字什么意思", "一图讲清这个汉字", "汉字字源信息图", "explain this Chinese character", or "Chinese…
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
Polish and elevate MBA thesis / dissertation to national outstanding thesis quality (全国优秀论文). Performs comprehensive improvement: academic language, argument structure, logical rigor, innovation highlights, and formatting. Input: markdown thesis text. Output: polished full text. Also trigger when the user mentions…
learning-assistant
互动式主题学习助手，依赖知识库结构化学习任务并交互引导完成学习过程.
reading-notes
Process a book or article into structured progressive summary notes saved to the resources folder. Use when the user has finished reading something and wants to capture structured notes — 'I just finished reading X', 'take notes on this book'. Do NOT use for: fetching and summarizing a URL now (use summarize)…
project-learner
结构化交互式学习助手，当用户希望学习项目相关知识、特定代码文件或底层技术时使用此技能，它会将学习过程记录为持久化的 Markdown 日志.