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 isco-tec/scorezilla-mcp --skill add-leaderboardgit clone --depth 1 https://github.com/isco-tec/scorezilla-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/isco-tec/scorezilla-mcp/add-leaderboard)<a href="https://agentmods.dev/skills/isco-tec/scorezilla-mcp/add-leaderboard"><img src="https://agentmods.dev/badge/skills/isco-tec/scorezilla-mcp/add-leaderboard/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/isco-tec/scorezilla-mcp/add-leaderboard"><img src="https://agentmods.dev/badge/skills/isco-tec/scorezilla-mcp/add-leaderboard.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 | $0.00050 | $0.01030 |
| Opus 5.5 | $0.00020 | $0.00412 |
| Sonnet 5.5 | $0.00010 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
add-leaderboard 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a leaderboard to this game
Uses the scorezilla MCP server from this plugin. The flow is: find or create the game and board, get
integration code, put it into the project, then confirm a real score arrives.
1. Look at the project first
Before calling any tool, read enough of the project to answer:
- Where the run ends. Find the game-over / level-complete / finish code where the final score is known.
- What the score is. Points where higher wins, or a time where lower wins (a time trial)? Whole numbers, milliseconds or decimals?
- Where it runs. Browser only, or is there a server the game already talks to?
Ask the user only what the code can't tell you, such as the game's display name.
2. Find or create the board
- Call
list_gamesand look for this game by name. - This game isn't in the account yet (even if other games are): call
bootstrap_leaderboard. It creates the game and its first board in one call and returnssnippets.sdk,snippets.widgetand arecommendation.gameNamefrom the project (package name, title screen, README);gameSlugderived from it (lowercase, hyphens, 2–42 characters).boardName/boardSlug: something like "High Scores" /high-scores.sortDir:descwhen higher wins,ascwhen lower wins.scoreKind:integer,duration_msfor time trials, orfloat.
- The game already exists: call
list_boardswith itsgameId. Reuse a matching board, or callcreate_boardto add one. Don't callbootstrap_leaderboardfor a game that already exists.
3. Get the integration code
Call get_sdk_snippet with the gameId and boardId. If you just bootstrapped, you already have the code,
and only call it again to change the setup.
Pick the setup from what you learned in step 1:
- Default (browser game, casual board): leave the optional arguments out. The browser uses the public key, which is safe to embed. Scores are trusted from the client, so say plainly that this setup has no anti-cheat.
- Competitive board where cheating matters, and the project has a server: pass
hostingPattern: "client_with_server"(andserverLanguageif the server isn't TypeScript). The server signs submissions with the game's secret key. The secret key is never returned over MCP: tell the user to copy it from https://dashboard.scorezilla.dev into an environment variable on their server. - Players already sign in (Supabase, Clerk, Auth0, Firebase, Google): pass
playerIdentityStrategy: "auth_provider"and the matchingauthProvider.
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.
- today First seen · 77 lines · 50 tokens per session scan A 615d81df4471
add-leaderboard is a skill published in the GitHub repository isco-tec/scorezilla-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,030 once invoked, about $0.0002 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 2026-10-18.
Other skills, from other repositories
roblox-animation-vfx
Use when adding, changing, or fixing Roblox animations, particles, beams, trails, tweens, camera shake, or other visual effects.
roblox-audio
Use when adding, changing, or fixing Roblox audio: playback, spatial sound, music, sound effects, SoundGroups, or dynamic effects.
roblox-camera
Use when scripting or fixing Roblox camera behavior: CFrame placement, screen raycasts, first/third-person, shoulder views, cutscenes.
roblox-lighting
Use when setting up or changing Roblox lighting, atmosphere, day/night cycles, or post-processing effects.
roblox-localization
Use when adding or fixing Roblox translation: localization tables, auto-translation, locale-specific content, or region detection.
roblox-luau-core
Use when writing, editing, or debugging any Luau: tables, control flow, string patterns, scope, closures, and errors ported from JS/Python.