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 hugobowne/show-us-your-agent-skills --skill wikipedia-discoverygit clone --depth 1 https://github.com/hugobowne/show-us-your-agent-skillsWrote 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/hugobowne/show-us-your-agent-skills/wikipedia-discovery)<a href="https://agentmods.dev/skills/hugobowne/show-us-your-agent-skills/wikipedia-discovery"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/wikipedia-discovery/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/hugobowne/show-us-your-agent-skills/wikipedia-discovery"><img src="https://agentmods.dev/badge/skills/hugobowne/show-us-your-agent-skills/wikipedia-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.01057 |
| Opus 5 | $0.00041 | $0.00528 |
| Sonnet 5 | $0.00016 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
wikipedia-discovery 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 13d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wikipedia discovery
Use the current wiki hostname (e.g. en.wikipedia.org) for all API requests unless you intentionally switch language wiki.
Helping someone learn (user-facing)
When the user wants to learn about something, steer them toward concrete articles (and sections by heading when helpful). In natural language:
- Name articles by title and briefly say why each is relevant to their question.
- Do not paste full URLs, do not use markdown links, and do not bullet raw links—readers use
url_changeon their own; your job in chat is titles + relevance only.
Behind the scenes, when it is time to open the mirror, use message_parent with a full Wikipedia url (optional # section / anchor per below); that string is not for display in the user-visible reply.
I have a phrase / topic — find articles
Search the index, return ranked titles/snippets, optionally narrow namespaces. Prefer REST search for simple JSON cards; use Action API list=search when you need Cirrus options, generators, or wikitext-era fields. Paging: Action list= modules return continue — merge those params on the next request until absent. REST search may use limit / offset where supported. Details: wikipedia-discovery/references/topic-search.md.
I’m on (or chose) this article — what’s next?
Use summary for a short lead, links / backlinks to move outward in the graph, extracts for longer previews, categories / random when exploration fits. Same continue discipline for any prop/list that paginates. Details: wikipedia-discovery/references/article-next-steps.md.
Changing the Wikipedia URL (message_parent / url_change)
When the mirrored page should change, call message_parent with:
{"type": "url_change", "url": "<full https URL on wikipedia.org, optional #section-or-id>"}
url must stay on Wikipedia (*.wikipedia.org / wikipedia.org). Query APIs first when you only need metadata; send url_change when the left pane should actually load that resource.
What ships with it
3 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.
- 13d ago First seen · 62 lines · 81 tokens per session scan A 9e1bd267cebb
wikipedia-discovery is a skill published in the GitHub repository hugobowne/show-us-your-agent-skills (67 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,057 once invoked, about $0.0004 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
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…