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 Mooooooon/liquipedia-dota2-mcp --skill liquipedia-dota2git clone --depth 1 https://github.com/Mooooooon/liquipedia-dota2-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/mooooooon/liquipedia-dota2-mcp/liquipedia-dota2)<a href="https://agentmods.dev/skills/mooooooon/liquipedia-dota2-mcp/liquipedia-dota2"><img src="https://agentmods.dev/badge/skills/mooooooon/liquipedia-dota2-mcp/liquipedia-dota2/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/mooooooon/liquipedia-dota2-mcp/liquipedia-dota2"><img src="https://agentmods.dev/badge/skills/mooooooon/liquipedia-dota2-mcp/liquipedia-dota2.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 | $0.00074 | $0.00629 |
| Opus 5 | $0.00037 | $0.00315 |
| Sonnet 5 | $0.00015 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
liquipedia-dota2 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 11d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Liquipedia Dota 2
Use the read-only MCP tools to answer Dota 2 esports questions with revision-level provenance. Treat missing or unparsed data as unknown.
Workflow
- Identify whether the request concerns a tournament, team, player, roster, schedule, score, or result.
- Call
search_dota2_entitiesunless the conversation already contains an exactcanonical_titlereturned by that tool. - When search returns multiple plausible candidates, present the candidates and ask the user to choose. Stop before calling a detail tool. Never select solely from search rank.
- Call exactly one matching detail tool:
- Use
get_dota2_tournamentfor tournament metadata, participants, and placements. - Use
get_dota2_teamfor team metadata, roster, and coaches. - Use
get_dota2_playerfor player identity, current team, role, aliases, and team history.
- Use
- Call
list_dota2_matchesonly when the user asks for matches, schedules, scores, or results. Pass the confirmed tournament or teamcanonical_title. - Inspect
ok,coverage,warnings, andsourcebefore composing the answer. Read references/schema.md when exact result semantics or error recovery is needed.
Answering rules
- Answer in the user's language while preserving official names and handles.
- Use only returned fields for Liquipedia-backed claims. Do not fill
null,partial, orunavailablefields from memory. - Distinguish an empty result from unavailable parsing. Explain relevant warnings briefly.
- Convert UTC dates to the user's requested timezone only when the timezone is known; retain UTC otherwise.
- End with the Liquipedia page link and the
source.fetched_attime. Mention stale cache whensource.is_staleis true. - Attribute the data to Liquipedia. Do not imply that Liquipedia or Team Liquid endorses the answer.
Failure handling
- If an MCP tool is unavailable, tell the user that the local
liquipedia-dota2-mcpserver must be configured; do not substitute HTML scraping. - For
ambiguous, showerror.candidatesand request confirmation. - For
rate_limited, reportretry_after_secondsand avoid immediate retry loops. - For
not_found, offer a narrower spelling or entity-type search. - For
parse_failedorcoverage: unavailable, state that the page structure is unsupported and link the source when provided. - For
upstream_unavailable, use stale data only when the tool explicitly returned it as a successful envelope.
What ships with it
2 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.
- 11d ago First seen · 39 lines · 74 tokens per session scan A c07e6eff8d23
liquipedia-dota2 is a skill published in the GitHub repository Mooooooon/liquipedia-dota2-mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 74 tokens to every session and 629 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 2026-08-31.
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
Control Unity Editor from the CLI with the isuzu-unity-cli command. Execute C# code, browse scene hierarchy, inspect/modify GameObjects, capture screenshots, read console logs, check compile status, control play mode, and execute menu items. Use when: user wants to interact with Unity Editor programmatically, run C#…
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…
add-mechanic
Add game mechanics with correct GDScript 4.x patterns -- movement, health, inventory, save/load.
debug-issue
Systematic Godot debugging decision trees for physics, signals, rendering, navigation, and input issues.
build-scene
Pattern-based Godot scene construction with node hierarchy templates and companion node rules.