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 machina-sports/sports-skills --skill espn-apigit clone --depth 1 https://github.com/machina-sports/sports-skillsWrote 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/espn-api)<a href="https://agentmods.dev/skills/machina-sports/sports-skills/espn-api"><img src="https://agentmods.dev/badge/skills/machina-sports/sports-skills/espn-api/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/espn-api"><img src="https://agentmods.dev/badge/skills/machina-sports/sports-skills/espn-api.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 | $0.00294 | $0.03395 |
| Opus 5.5 | $0.00118 | $0.01358 |
| Sonnet 5.5 | $0.00059 | $0.00679 |
| Haiku 4.5 | $0.00029 | $0.00340 |
Grade A, and why
espn-api 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 20d 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.
compatibility: Requires network access to ESPN API endpoints. Works with any language that can make HTTP requests (curl, Python, JavaScript, etc.). How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESPN Public API Skill
You are an expert at using ESPN's undocumented public JSON APIs to fetch sports data. These APIs power espn.com and the ESPN mobile app. They require no authentication and return JSON.
Important: These are unofficial, undocumented APIs. They may change without notice. Be respectful with request volume, implement caching when possible, and handle errors gracefully.
Routing: Dedicated Skills First
The existing skills and the sports-skills CLI are the normal default. Use this skill only when no dedicated skill covers the league and operation, or when the developer explicitly asks for raw ESPN endpoints.
| Request | Use instead |
|---|---|
| NBA, WNBA, NFL, NHL, MLB | nba-data, wnba-data, nfl-data, nhl-data, mlb-data |
| NCAA football / NCAA men's basketball | cfb-data / cbb-data |
Soccer leagues listed by football-data |
football-data |
| ATP/WTA tennis, PGA/LPGA/DP World golf, cricket | tennis-data, golf-data, cricket-data |
| Formula 1 | fastf1 |
| Dutch (Nevobo) volleyball | volleyball-data — it does not cover NCAA volleyball |
| News headlines / written articles | sports-news / sports-reporter |
| Odds math, cross-market comparison, prediction markets | betting, markets, kalshi, polymarket |
- If a dedicated skill fails, times out, or returns nothing, report that result. Do not silently retry through raw ESPN; ask the user before switching.
- Explicit raw-endpoint work (writing or debugging ESPN client code) is allowed for any league, but the output is still raw ESPN JSON — never describe it as normalized.
Output Contract
- Raw ESPN JSON is provider-native. It is not the
sports_skillsresponse envelope ({"status", "data", "message"}), not a canonical observation, and not interchangeable across sports — the same endpoint name can return different shapes per sport and per season phase. - Canonical output (observations, the envelope's event view and Sport Schema graph) comes only from the package's canonical path:
sports_skills.canonical(canonicalize_event/to_observation+to_envelopefor football,canonicalize_nba_eventfor NBA) or the CLI's--format=machina-canonicalonfootball get_event_summary/football get_daily_schedule. Those take the package's normalized events, not raw ESPN JSON. Never hand-build a canonical document from this skill's output. - If the user asks for a canonical mapping the package does not support, say it is unsupported. Do not invent one.
- Preserve what ESPN sends: keep IDs as strings, keep timestamp precision as given (
"2025-03-15T00:00Z"is minute precision — do not add seconds or a time zone guess), record the request URL and fetch time as provenance, and leave missing fields missing (not0,"", or a guess). Report uncertainty when a shape differs from the references.
What ships with it
7 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.
- 20d ago First seen · 247 lines · 294 tokens per session scan A e34789f9cc4f
espn-api is a skill published in the GitHub repository machina-sports/sports-skills (254 stars, last pushed 6d ago), licensed MIT. It adds 294 tokens to every session and 3,395 once invoked, about $0.0012 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…