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 sharziki/purdue-mcp --skill purdue-huddlegit clone --depth 1 https://github.com/sharziki/purdue-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/sharziki/purdue-mcp/purdue-huddle)<a href="https://agentmods.dev/skills/sharziki/purdue-mcp/purdue-huddle"><img src="https://agentmods.dev/badge/skills/sharziki/purdue-mcp/purdue-huddle/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/sharziki/purdue-mcp/purdue-huddle"><img src="https://agentmods.dev/badge/skills/sharziki/purdue-mcp/purdue-huddle.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 | $0.00096 | $0.01022 |
| Opus 5 | $0.00048 | $0.00511 |
| Sonnet 5 | $0.00019 | $0.00204 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
purdue-huddle scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl`, `fetch`, the MCP server itself — gets `429` with How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keeping Huddle events fresh
Why this needs setting up at all
Every other source in purdue-mcp is fetched live. Huddle cannot be, and the
reason is worth understanding before you debug it:
gethuddle.social sits behind Vercel's bot challenge. Every plain HTTP client —
curl, fetch, the MCP server itself — gets 429 with
x-vercel-mitigated: challenge, whatever headers it sends. A real browser
clears the challenge in about a second on a normal home or campus
connection, and never clears it from a datacenter address. That was measured,
not assumed: the same headless Chrome passed on a laptop and sat on "Vercel
Security Checkpoint" indefinitely from a VPS.
So there is no server anyone can run that stays fresh. The fetch has to happen on a machine like yours, which means you run it.
Setup
One command, using a Chrome/Chromium/Edge/Brave you already have:
npx -y purdue-mcp-huddle
It writes ~/.cache/purdue-mcp/huddle-purdue.json (~1.7 MB, about 2,600
events) and huddle_events picks it up on the next call. Takes ~4 seconds.
Nothing is installed as a service, nothing runs in the background, and no browser profile or login is touched — it launches a throwaway profile, reads the public events API from inside the page, and exits.
Keeping it current
New flyers appear daily, so a copy from last week will miss this week's callouts. Pick whichever fits the machine:
# cron (Linux/macOS)
crontab -e
7,37 * * * * npx -y purdue-mcp-huddle --quiet
# systemd user timer (Linux) — survives reboots, catches up after suspend
# Use OnCalendar, not OnUnitActiveSec: the monotonic clock stops while a
# laptop sleeps, so an interval timer silently drifts by the length of
# every nap.
On a laptop that sleeps a lot, running it by hand when you actually want events is honestly fine — the tool always tells you how old its copy is.
Options
| Flag / variable | Effect |
|---|---|
--out <path> |
Write somewhere else. Pair with PURDUE_MCP_HUDDLE_MIRROR. |
--college <name> |
Another Huddle campus. Default Purdue University. |
--quiet |
Errors only, for cron. |
PURDUE_MCP_CHROME |
Path to a browser, if it is somewhere unusual. |
PURDUE_MCP_HUDDLE_MIRROR |
Where huddle_events reads from — a file path or a URL. Overrides the local copy, so a club or a household can share one file. |
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 · 93 lines · 96 tokens per session scan A 61565c1d06a4
purdue-huddle is a skill published in the GitHub repository sharziki/purdue-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,022 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…