wikipedia-guide

wikipedia-guide is a skill for Claude Code from cyanheads/wikipedia-mcp-server. It costs 84 tokens per session (1,705 once invoked), scanned A, original, Apache-2.0.

A usage guide for searching and reading Wikipedia articles across its separate language editions. It explains how to identify the right article, section, language edition, and related Wikidata item.

In plain words
What is it for?
Use it to search articles, read summaries and sections, follow language links, find nearby geotagged articles, and inspect cited footnotes.
Why use it?
It prevents confusing similarly titled pages, using the wrong section reference, or treating missing coverage in one language edition as proof that information is absent.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wikipedia-mcp-server plugin — 35 skills, 1 MCP server shipped together

Good fit Use it to search articles, read summaries and sections, follow language links, find nearby geotagged articles, and inspect cited footnotes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyanheads/wikipedia-mcp-server/wikipedia-guide
Install

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.

Any agent
npx skills add cyanheads/wikipedia-mcp-server --skill wikipedia-guide
Clone the repo
git clone --depth 1 https://github.com/cyanheads/wikipedia-mcp-server

Made for: Claude Code.

Or install wikipedia-mcp-server, the plugin that ships this one along with the rest of its 35 skills, 1 MCP server.

Wrote 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.

agentmods badge for wikipedia-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyanheads/wikipedia-mcp-server/wikipedia-guide/github.svg)](https://agentmods.dev/skills/cyanheads/wikipedia-mcp-server/wikipedia-guide)
Your own site
<a href="https://agentmods.dev/skills/cyanheads/wikipedia-mcp-server/wikipedia-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/wikipedia-mcp-server/wikipedia-guide/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.

agentmods 80×15 button for wikipedia-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyanheads/wikipedia-mcp-server/wikipedia-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/wikipedia-mcp-server/wikipedia-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01705
Opus 5.5 $0.00034 $0.00682
Sonnet 5.5 $0.00017 $0.00341
Haiku 4.5 $0.00008 $0.00170

Measured today against content hash fb9c9cf5e725, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wikipedia-guide 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 today.

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.

skills/wikipedia-guide/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

Wikipedia prose in every language edition: full-text search, summaries, section and full-article reads, geotagged articles near a coordinate, an article's interlanguage links, and the footnotes it cites. Keyless and read-only.

Each call reads one edition. No tool searches several editions at once, and none covers Wikidata statements, page history, or other Wikimedia projects. For structured facts, or to turn a QID into titles, hand the wikibase_item QID to a Wikidata tool.

Identifiers

Identifier Where it comes from What to know
Title Search results, the resolved title of any read, languages[].title from wikipedia_get_languages Belongs to one edition. The same spelling can name a different subject elsewhere: Gift is the present article on en (Q184303) and the poison article on de (Q40867)
Edition (language) edition_code from wikipedia_get_languages Simple English is simple
section_index index from wikipedia_get_sections, or the (section_index: N) labels on an outlined full read Not the number column. On Seine, index 10 is section number "6"
QID (wikibase_item) wikipedia_get_summary, search results, and nearby results, each when present The same across editions (Seine is Q1471 on en, fr, and simple). Output only: as a title it fails not_found, and as a query it matches nothing
Coordinates latitude/longitude on wikipedia_get_summary Geotags belong to each edition's article. Seine has them on en but not on fr

Gates

Never carry a title across editions. Get the target edition's title from wikipedia_get_languages. If you found it by searching that edition instead, check that its wikibase_item matches the source article's before treating it as the same subject.

Check page_type before reading an ambiguous title in depth. Only wikipedia_get_summary flags a disambiguation page. wikipedia_get_sections and wikipedia_get_article read one as if it were an article: Mercury returns dozens of "sections" (Companies, Computing, Film and television …) with no flag. To pick the intended article:

  • Read the disambiguation page's sections. They list one candidate per line, title first ("Mercury Drug, a Philippine pharmacy chain").
  • Or search. On en, the disambiguation page's own result carries the description "Topics referred to by the same term", and the other results' descriptions separate the candidates.

Read the full file on GitHub · 70 lines

Changes

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.

  1. today First seen · 70 lines · 84 tokens per session scan A fb9c9cf5e725

Subscribe to this mod's changes

wikipedia-guide is a skill published in the GitHub repository cyanheads/wikipedia-mcp-server (4 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,705 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-29.

Related

Other skills, from other repositories

wikidata-guide

Use wikidata tools to identify entities, verify qualified claims, join external identifiers, and build SPARQL graph queries. Use for Wikidata research that needs identity disambiguation, statement evidence, or completeness checks.

cyanheads/wikidata-mcp-server · 48 tokens

openstates-guide

Identifier chains and gates for the openstates tools (US state legislatures via Open States). Use when tracing a state bill's fate, votes, or sponsors; finding who represents a location and their committees; finding hearings; or comparing states. Read before naming a bill, reporting who voted how, or concluding that a…

cyanheads/openstates-mcp-server · 78 tokens

onebusaway-guide

Resolve and interpret onebusaway transit results when choosing a boarding stop, tracking a route or trip, checking disruptions, or reading service-day schedules. Use for multi-step questions where direction, agency, missing telemetry, or scheduled versus predicted times change the answer.

cyanheads/onebusaway-mcp-server · 57 tokens

wsdot-guide

Plan Washington ferry trips with wsdot tools when a next-sailing, vehicle-eligibility, or capacity question needs schedule, service alerts, terminal space, and vessel evidence combined.

cyanheads/wsdot-mcp-server · 42 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…

cyanheads/wikidata-mcp-server · 155 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…

cyanheads/openstates-mcp-server · 155 tokens