scorezilla-mcp: Instructions file for Claude Code

CLAUDE.md

scorezilla-mcp CLAUDE.md is an instructions file for Claude Code from isco-tec/scorezilla-mcp. It costs 1,073 tokens per session, scanned A, original, MIT.

A set of project instructions for developing and releasing the Scorezilla MCP server, a tool for managing game leaderboards. It documents the codebase, commands, testing rules, and publishing process.

In plain words
What is it for?
Use it when changing, testing, building, versioning, or preparing the Scorezilla server for its automated npm release.
Why use it?
It gives an AI coding assistant the project-specific rules needed to make safe changes and release them correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md.

This is isco-tec/scorezilla-mcp's own configuration. It tells Claude Code how to work on scorezilla-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scorezilla-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to isco-tec/scorezilla-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/isco-tec/scorezilla-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/isco-tec/scorezilla-mcp

Made for: Claude Code.

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 scorezilla-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/isco-tec/scorezilla-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/isco-tec/scorezilla-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/isco-tec/scorezilla-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/isco-tec/scorezilla-mcp/claude-md/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 scorezilla-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/isco-tec/scorezilla-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/isco-tec/scorezilla-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,073 This file is loaded in full into every session.
When invoked 1,073 The same file — it is already loaded in full.
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 $0.01073 $0.01073
Opus 5.5 $0.00429 $0.00429
Sonnet 5.5 $0.00215 $0.00215
Haiku 4.5 $0.00107 $0.00107

Measured 5d ago against content hash 80d43926644b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scorezilla-mcp CLAUDE.md 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 5d 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.

CLAUDE.md · 39 lines

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.

CLAUDE.md

Official MCP server for Scorezilla (scorezilla.dev) — a stdio CLI (npx -y @scorezilla/mcp) that lets AI coding assistants manage game leaderboards. Thin client of api.scorezilla.dev; no hosted component here. This repo is PUBLIC — never commit tokens, secrets, or private-monorepo internals.

Stack

TypeScript (ESM), Node >= 20, @modelcontextprotocol/sdk, zod v4. tsup bundles to dist/index.js (the published bin), vitest for tests, changesets for versioning.

Commands

Package manager is pnpm (v9 in CI) — never npm/yarn.

  • pnpm typecheck — tsc --noEmit (also enforces compile-time contract assertions)
  • pnpm test — vitest run
  • pnpm build — tsup
  • node dist/index.js --version — bin smoke test (run after build, CI does)
  • pnpm release:check — package.json ↔ server.json version sync guard
  • pnpm changeset — add a changeset (required for any user-facing change)

Deploy (npm publish)

  • Publishing is CI-only via .github/workflows/release.yml — never run npm publish or bash scripts/publish.sh manually (the manual path skips provenance; it exists only as a documented disaster fallback).
  • Actual flow (changesets, NOT tag-based): merge to main → Release workflow (every run pauses for manual approval via the npm-publish GitHub Environment) → changesets opens/updates a "Version Packages" PR → merging that PR publishes to npm with --provenance (+ @scorezilla/mcp@<version> git tag and GitHub release), runs a post-publish install smoke test, then publishes to the MCP Registry (mcp-publisher; waits for npm propagation and retries the Registry's "version not found").
  • Never bump versions by hand — changesets only. package.json and server.json must stay in sync (scripts/sync-server-json-version.mjs; release:check guards it).
  • workflow_dispatch input registry_resync: true re-publishes the current version to the MCP Registry only — recovery for "npm published, registry step failed".

Rules & gotchas

  • Contract mirror: src/contract.ts is a hand-maintained MIRROR of the private monorepo's MCP wire contract. When test/contract-drift.test.ts fails after an upstream sync, update src/contract.ts to match the vendored test/contract/mcp.generated.ts — NEVER edit the vendored file, never invent fields, never "fix" the test. A red drift check after upstream changes is by design, not a bug.
  • Part of the drift guard is compile-time (expectTypeOf) — it fails pnpm typecheck, not pnpm test. Run both.
  • Base URL is HTTPS-only (localhost exempted); write tools send content-derived Idempotency-Key headers — preserve both behaviors when touching the HTTP layer.
  • Runtime env vars (users', not CI): SCOREZILLA_TOKEN, SCOREZILLA_BASE_URL, SCOREZILLA_BETA_TOKEN. Reference names only; never write values anywhere.
  • MCPB bundle for Claude Desktop: after each release, run pnpm pack:mcpb on main and attach the output to the new GitHub release under the stable name scorezilla-mcp.mcpb (gh release upload "@scorezilla/mcp@<version>" scorezilla-mcp.mcpb). The README links releases/latest/download/scorezilla-mcp.mcpb, so a release without it breaks that link. (Smithery was the other MCPB consumer; it shut down publishing on 2026-10-31 — don't target it.)
  • Claude plugin (plugin/) is submitted to Anthropic's plugin directory, which tracks main. It pins the MCP server via plugin/package.json + plugin/package-lock.json (npm, not pnpm; needed for the directory's Verified badge). After each @scorezilla/mcp release: bump the pin, run npm install --package-lock-only --ignore-scripts in plugin/, bump version in plugin/.claude-plugin/plugin.json, then claude plugin validate --strict ./plugin. Before testing with claude --plugin-dir ./plugin, run npm ci --ignore-scripts in plugin/ (in-place loads skip the dependency install).
  • The README has no version-specific text (the old "Status" blurb was removed in #75); the version lives in plugin/README.md, bumped with the plugin pin.
  • Pre-flight before any PR: pnpm typecheck && pnpm test && pnpm build && node dist/index.js --version.

Read the full file on GitHub · 39 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. 5d ago Changed · +19 tokens per session 80d43926644b
  2. 10d ago Changed · +1 lines · +124 tokens per session bd48dc22c2f8
  3. 14d ago Changed · +1 lines · +149 tokens per session c3643592d17d
  4. 20d ago Changed · +32 tokens per session 7fcbc1c6f032
  5. 2mo ago First seen · 37 lines · 749 tokens per session scan A 5e52b9835cd9

Subscribe to this mod's changes

scorezilla-mcp CLAUDE.md is an instructions file published in the GitHub repository isco-tec/scorezilla-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 1,073 tokens to every session, about $0.0043 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens