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 mayor-modder/Cities2-MCP --skill cities2-knowledgegit clone --depth 1 https://github.com/mayor-modder/Cities2-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/mayor-modder/cities2-mcp/cities2-knowledge)<a href="https://agentmods.dev/skills/mayor-modder/cities2-mcp/cities2-knowledge"><img src="https://agentmods.dev/badge/skills/mayor-modder/cities2-mcp/cities2-knowledge/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/mayor-modder/cities2-mcp/cities2-knowledge"><img src="https://agentmods.dev/badge/skills/mayor-modder/cities2-mcp/cities2-knowledge.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 | $0.00029 | $0.01476 |
| Opus 5.5 | $0.00012 | $0.00590 |
| Sonnet 5.5 | $0.00006 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
cities2-knowledge 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cities2 Knowledge
Use this skill when answering Cities: Skylines II gameplay questions with Cities2-MCP. The goal is to retrieve focused evidence from both available sources and synthesize a normal answer, not to show raw search results.
Trigger this skill for plain questions like "How do I grow office demand?", "What changed in the latest patch?", "Did traffic change?", "What makes citizens healthier?", "Why is housing demand low?", or "How does zoning/pollution/education/transit work?", even when the user does not mention this plugin, wiki, encyclopedia, patch notes, or sources.
Source roles
- Game encyclopedia: More authoritative for current in-game wording, broad current mechanics, and terminology because it is read from the user's installed game files.
- Wiki corpus: Usually better for player advice, tables, examples, patch history, guide context, and fuller explanations.
- Research corpus:
cities2-researchcontains curated summaries of talks, interviews, and similar sources. It adds design rationale and historical context, but it is time-bounded evidence rather than confirmation of current gameplay or APIs. Inspect and retain each research result'spublished_atdate. - Conflict handling: If sources disagree, say so plainly. Prefer the game encyclopedia for current in-game terminology/mechanics, unless the wiki result is clearly a newer patch-specific note.
Workflow
- Call
source_status()first. - Extract 4-10 keyword terms from the user's question. Do not send the whole natural-language question as the primary query.
- Search the bundled wiki and research corpora with
search(query, limit=5). Usequery_reference(query, limit=5)if page-level routing would help. Inspectdataseton every result before deciding its source role. - Search the game encyclopedia with
search_encyclopedia(query, limit=5)whensource_status()reports it is available. - Fetch fuller evidence:
- Use
get_page(page_id)for the best bundled page or research report when snippets are not enough. - Use
get_encyclopedia_entry(entry_id)for the best encyclopedia entries.
- Use
- Keep track of source identity and timing:
- For
cities2-docs, keep the wiki page title andurlfromget_pageor search results. - For
cities2-research, keep the report title,url,dataset, andpublished_at. State the publication date when using the result and do not present its claim as current unless a current source independently confirms it. - Game encyclopedia entry titles from
get_encyclopedia_entry.
- For
- Answer from the retrieved material. Explain what to do and why, with short source labels such as
wiki,research published YYYY-MM-DD, andgame encyclopediawhen useful.
What ships with it
1 file 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.
- 1mo ago First seen · 86 lines · 29 tokens per session scan A 6ab575236339
cities2-knowledge is a skill published in the GitHub repository mayor-modder/Cities2-MCP (10 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,476 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
okx-cex-portfolio
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…
isuzu-unity-cli
Drive the open Unity Editor from the shell with the isuzu-unity-cli command: console errors, compiling and tests, scenes, GameObjects and components, prefabs, play mode, uGUI clicks, and C# run inside the Editor. SKILL.md gives a command for each common task, so no tool list is needed.
maya-import-to-scene
Pipeline stage — structured asset import. Consume an AssetDescriptor produced by maya-asset-source and import the asset (FBX, OBJ, USD) into the current Maya scene via cmds.file(). Handles axis/unit conversion, MaterialMode, PlacementHint, and optional target collection grouping. Returns an ImportToSceneResult with…
minecraft-dev
Use this skill whenever the user wants to look up Minecraft source, mod source, mod loader source, mappings, registries, versions, version differences, access transformers, mixin information, documentation, or code search results with minecraft-dev-cli. Also use it for Fabric, Forge, Quilt, and NeoForge source lookups.
kernelcad-sdformat
Export multi-part assemblies to SDFormat — closed kinematic loops, native ball joints, solved per-link poses, per-link inertial/visual/collision with mesh files. Use when the downstream simulator ingests SDFormat directly or the assembly needs closed-loop / native-spherical-joint support.
blockout-model
Coarse parametric blockout of the primary masses before committing to detail. Establishes the bounding envelope, canonical-view alignment, and reference-image plane, then confirms the blockout is plausible before detail work begins.