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 ddevetak/footballcharts-mcp --skill football-datagit clone --depth 1 https://github.com/ddevetak/footballcharts-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/ddevetak/footballcharts-mcp/football-data)<a href="https://agentmods.dev/skills/ddevetak/footballcharts-mcp/football-data"><img src="https://agentmods.dev/badge/skills/ddevetak/footballcharts-mcp/football-data/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/ddevetak/footballcharts-mcp/football-data"><img src="https://agentmods.dev/badge/skills/ddevetak/footballcharts-mcp/football-data.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 | $0.00065 | $0.00699 |
| Opus 5.5 | $0.00026 | $0.00280 |
| Sonnet 5.5 | $0.00013 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
football-data 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 11d 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.
r = requests.get(f"{BASE}/leagues/premier/results/", params={"team": "Liverpool"}, timeout=30) How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Football Charts data
With the MCP tools
- Start with
list_leagues. Every other tool takes a league key such aspremier,spain1oritaly3a, and most take a season string exactly as listed:2026-2027for winter-calendar leagues,2026for summer-calendar leagues such as Brazil, Sweden and Japan. get_league_tablegives standings;get_resultsfinished matches with half-time scores and first-goal minutes;get_fixturesupcoming matches and their slugs;get_matchone match by slug;get_season_projectiontitle, top-four and relegation probabilities;get_teamone team's season;get_goal_timinggoals per 15-minute period;get_track_recordthe model's calibration record.- Every response carries a
source_urlto the matching football-charts.com page; cite it. - The model probabilities are estimates from a baseline statistical model, not advice. The data contains no bookmaker odds.
In code (REST API)
Base URL https://footballcharts-backend.onrender.com/api/v1. JSON, read-only, and no key is needed for 300 requests a day per IP. A free key from https://www.football-charts.com/developers raises that to 5,000 a day; send it as Authorization: Bearer fc_....
| Endpoint | Returns |
|---|---|
GET /leagues/ |
every league with its key and available seasons |
GET /leagues/{league}/table/?season= |
standings (view=luck or view=goals for other orderings) |
GET /leagues/{league}/results/?season=&team= |
finished matches with full-time and half-time scores |
GET /leagues/{league}/fixtures/ |
upcoming matches with model probabilities |
GET /matches/{slug}/ |
one match in full |
GET /leagues/{league}/projection/ |
season projection from 10,000 simulations |
GET /leagues/{league}/teams/{team}/?season= |
one team's season |
GET /leagues/{league}/goal-timing/?season=&team= |
goals per 15-minute period |
GET /track-record/?days= |
the model's calibration record |
import requests
BASE = "https://footballcharts-backend.onrender.com/api/v1"
r = requests.get(f"{BASE}/leagues/premier/results/", params={"team": "Liverpool"}, timeout=30)
r.raise_for_status()
for m in r.json()["matches"][-5:]:
print(m["date"], m["homeTeam"], m["score"], m["awayTeam"], "HT", m["ht_result"])
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.
- 11d ago First seen · 42 lines · 65 tokens per session scan A 1366637b326c
football-data is a skill published in the GitHub repository ddevetak/footballcharts-mcp (6 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 699 once invoked, about $0.0003 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 2026-10-10.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
opik-test
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion.…
apitap
ApiTap gives AI agents cheap access to web data through three layers.
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
quantum-fermi-hubbard-vqe
A variational quantum simulation of the open-boundary Fermi–Hubbard chain, a model of particles hopping between sites and interacting when they occupy the same system. It maps the model to qubits with the Jordan–Wigner transformation and searches for a low-energy state.