Borrowing it
Nothing to install: this file belongs to sprine/ontario-data-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sprine/ontario-data-mcp/main/.claude/skills/refresh-site-examples/SKILL.mdgit clone --depth 1 https://github.com/sprine/ontario-data-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/sprine/ontario-data-mcp/refresh-site-examples)<a href="https://agentmods.dev/skills/sprine/ontario-data-mcp/refresh-site-examples"><img src="https://agentmods.dev/badge/skills/sprine/ontario-data-mcp/refresh-site-examples.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 | $0.00068 | $0.02435 |
| Opus 5 | $0.00034 | $0.01218 |
| Sonnet 5 | $0.00014 | $0.00487 |
| Haiku 4.5 | $0.00007 | $0.00244 |
Grade A, and why
refresh-site-examples 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 8d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Site Examples
Generate real, source-backed examples for the site/index.html landing page. Examples are stored in site/examples.json and fetched at runtime by site/carousel.js. SQL is highlighted by site/sql-highlight.js.
NON-NEGOTIABLE: Factual Correctness
Every number, statistic, and finding on the site MUST be verified by querying real data. Hallucinations = mistrust. This is the #1 rule.
- NEVER write a number you haven't queried from real data
- NEVER use "plausible" or "realistic" numbers — only VERIFIED numbers
- If data can't be queried (XLSX-only, 0 resources, rate-limited), write the finding WITHOUT specific numbers — describe what the query reveals instead
- If a cross-dataset claim can't be verified (e.g. one dataset has no downloadable resources), rewrite to use only verifiable data
- After writing any claim, ask yourself: "Did I run a query that returned this exact number?" If no, delete the number.
When to use
- User asks to update, refresh, add, or replace examples on the site
- User wants new examples for a specific topic or section
- User wants to make examples "real" or add sources
JSON schema
Each example is an object in the array:
{
"tag": "Time series",
"question": "Natural language question a person would ask?",
"answer": "Narrative of what the tool does — dataset name, resource count, analysis technique.",
"punchline": "The bold finding, verified by real query.",
"sources": [
{
"title": "Exact Dataset Title from get_dataset_info",
"url": "https://data.ontario.ca/dataset/{slug}",
"org": "Organization Name from get_dataset_info"
}
],
"hood": {
"steps": [
{ "tool": "search_datasets", "description": "dataset_id_first_8_chars" },
{ "tool": "download_resource", "description": "17 CSVs" },
{ "tool": "query_cached", "description": "" }
],
"sql": "SELECT col_name,\n SUM(TRY_CAST(other_col AS INTEGER)) AS total\nFROM table_name\nGROUP BY col_name\nORDER BY total DESC"
},
"followup": {
"question": "Follow-up question?",
"answer": "Follow-up narrative.",
"punchline": "Follow-up finding (if verified).",
"sources": [{ "title": "...", "url": "...", "org": "..." }]
}
}
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.
- 8d ago First seen · 194 lines · 68 tokens per session scan A 73cb12125881
refresh-site-examples is a skill published in the GitHub repository sprine/ontario-data-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 2,435 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…