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 agentmods add instructions/isco-tec/scorezilla-mcp/claude-mdgit 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/instructions/isco-tec/scorezilla-mcp/claude-md)<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="Measured on agentmods" 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 | $0.00749 | $0.00749 |
| Opus 5 | $0.00375 | $0.00375 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
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 4d 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 — 37 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 runpnpm build— tsupnode dist/index.js --version— bin smoke test (run after build, CI does)pnpm release:check— package.json ↔ server.json version sync guardpnpm changeset— add a changeset (required for any user-facing change)
Deploy (npm publish)
- Publishing is CI-only via
.github/workflows/release.yml— never runnpm publishorbash scripts/publish.shmanually (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 thenpm-publishGitHub Environment) → changesets opens/updates a "Version Packages" PR → merging that PR publishes to npm with--provenanceand to the MCP Registry (mcp-publisher), then runs a post-publish install smoke test. - Never bump versions by hand — changesets only.
package.jsonandserver.jsonmust stay in sync (scripts/sync-server-json-version.mjs;release:checkguards it). workflow_dispatchinputregistry_resync: truere-publishes the current version to the MCP Registry only — recovery for "npm published, registry step failed".
Rules & gotchas
- Contract mirror:
src/contract.tsis a hand-maintained MIRROR of the private monorepo's MCP wire contract. Whentest/contract-drift.test.tsfails after an upstream sync, updatesrc/contract.tsto match the vendoredtest/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 failspnpm typecheck, notpnpm test. Run both. - Base URL is HTTPS-only (localhost exempted); write tools send content-derived
Idempotency-Keyheaders — 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. - README "Status" blurb tends to lag releases — refresh it when shipping a version.
- Pre-flight before any PR:
pnpm typecheck && pnpm test && pnpm build && node dist/index.js --version.
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.
- 4d ago First seen · 37 lines · 749 tokens per session scan A 5e52b9835cd9
scorezilla-mcp CLAUDE.md is an instructions file published in the GitHub repository isco-tec/scorezilla-mcp (1 stars, last pushed 11d ago), licensed MIT. It adds 749 tokens to every session, about $0.0037 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 instructions, from other repositories
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.