Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/machina-sports/sports-skillsnpx agentmods add skills/machina-sports/sports-skills/world-cupWrote 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/machina-sports/sports-skills/world-cup)<a href="https://agentmods.dev/skills/machina-sports/sports-skills/world-cup"><img src="https://agentmods.dev/badge/skills/machina-sports/sports-skills/world-cup/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/machina-sports/sports-skills/world-cup"><img src="https://agentmods.dev/badge/skills/machina-sports/sports-skills/world-cup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 85 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
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 | $0.00293 | $0.02520 |
| Opus 5 | $0.00147 | $0.01260 |
| Sonnet 5 | $0.00059 | $0.00504 |
| Haiku 4.5 | $0.00029 | $0.00252 |
Grade A, and why
world-cup scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/machina-sports/machina-cli/main/install.sh -o /tmp/machina-install.sh How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World Cup 2026 Intelligence (Premium)
A hosted, read-only intelligence layer for the FIFA World Cup 2026. It joins three things that are normally separate — official match truth, live prediction-market state, and AI-grounded context — under one canonical id space, so an agent can go from a market to the fixture to the teams in a single hop and reason about why a price is moving.
This skill itself runs no code. Like the machina
gateway it builds on, it shells out to machina-cli, selects the hosted World
Cup Intelligence project, and the agent harness talks to that project's MCP
server. Tenant routing, provider keys, rate limits, and caching all live
server-side. You never call a raw HTTP API or hold a provider key.
Read-only intelligence — not advice. Every output is informational sports market intelligence. Not betting, trading, financial, or investment advice. This layer has no order-placement, trading, or portfolio endpoints. If the user wants to act on a signal, that execution happens in their own agent, on their own account and keys — never here.
Premium / billing
This is a paid, metered layer (Machina Credits — see your project's credit-cost
classes). Free public data does not flow through here. Where your agent
harness supports agent-native pay-per-call (x402), the MCP server advertises price
per tool; otherwise calls draw from the project's credit balance. If a call
returns a 402 / "payment required" / "insufficient credits" error, surface it to
the user and stop — do not retry-loop.
Quick Start
# 1. Install the Machina CLI (one-time) — shared with the `machina` skill
pipx install machina-cli
# or: uv tool install machina-cli
# or: python -m pip install --user machina-cli
# 2. Authenticate
machina login # interactive (browser)
# machina login --api-key <project-api-key> # non-interactive (CI/CD)
# 3. Select the World Cup Intelligence project (REQUIRED)
machina project list
machina project use <world-cup-project-id>
# 4. Connect the MCP server
# `machina project use` (or `machina template install`) returns the MCP URL +
# headers. Point your harness's MCP config at it (e.g. .claude/mcp.json for
# Claude Code), then reload the harness so it re-reads the config.
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.
- 12d ago First seen · 208 lines · 293 tokens per session scan A c71cdf73f120
world-cup is a skill published in the GitHub repository machina-sports/sports-skills (218 stars, last pushed 4d ago), licensed MIT. It adds 293 tokens to every session and 2,520 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…