withqwerty/nutmeg
Football data analytics toolkit for Claude Code. Covers Opta, StatsBomb, Wyscout, SportMonks, and free sources.
field: Data & analytics workflow: Data / ETLPlanning & specsCI/CD & deployPR / code reviewFrontend & design
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~4.6k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add football-docs -- npx -y football-docs@0.17.4 $ npx degit withqwerty/nutmeg/agents ./rig-nutmeg/agents $ npx degit withqwerty/nutmeg/skills ./rig-nutmeg/skills $ npx degit withqwerty/nutmeg/hooks ./rig-nutmeg/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add football-docs -- npx -y football-docs@0.17.4 $ npx degit withqwerty/nutmeg/skills/acquire .claude/skills/acquire $ npx degit withqwerty/nutmeg/skills/analyse .claude/skills/analyse $ npx degit withqwerty/nutmeg/skills/brainstorm .claude/skills/brainstorm $ npx degit withqwerty/nutmeg/skills/compute .claude/skills/compute $ npx degit withqwerty/nutmeg/skills/heal .claude/skills/heal $ npx degit withqwerty/nutmeg/skills/learn .claude/skills/learn $ npx degit withqwerty/nutmeg/skills/nutmeg .claude/skills/nutmeg $ npx degit withqwerty/nutmeg/skills/research .claude/skills/research $ npx degit withqwerty/nutmeg/skills/review .claude/skills/review $ npx degit withqwerty/nutmeg/skills/store .claude/skills/store $ npx degit withqwerty/nutmeg/skills/wrangle .claude/skills/wrangle
$ curl -fsSL --create-dirs -o .claude/agents/chart-reviewer.md https://raw.githubusercontent.com/withqwerty/nutmeg/main/agents/chart-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-reviewer.md https://raw.githubusercontent.com/withqwerty/nutmeg/main/agents/data-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/pipeline-builder.md https://raw.githubusercontent.com/withqwerty/nutmeg/main/agents/pipeline-builder.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| football-docs | npm | 2.5k |
Skills (11)
nutmeg-acquirenutmeg-analysenutmeg-brainstormnutmeg-computenutmeg-healnutmeg-learnnutmegnutmeg-researchnutmeg-reviewnutmeg-storenutmeg-wrangle
Subagents (3)
| chart-reviewer model: sonnet | Reviews football chart and visualisation code for correctness, conventions, and rendering issues. Optionally inspects the rendered output in a browser. |
| data-reviewer model: sonnet | Reviews football data code for common mistakes. Use after the user writes data processing, analysis, or visualisation code that works with football event data, stats, or metrics. |
| pipeline-builder model: sonnet | Designs end-to-end football data pipelines. Use when the user describes a goal ('I want to analyse pressing in the Premier League') and needs help planning the full workflow from data acquisition to o |
Similar rigs
Mohammed-Abdelhady/hyperflow
Rules, multi-session project memory, task templates, and a reviewed multi-agent chain for AI coding CLIs. Issue to PR when you need it.
Orchestrator 1.6k tok · · Q8
sentientsky/ForgeLoop
A GitHub starter template for disciplined, token-aware AI-assisted engineering.
Orchestrator 3.1k tok · · Q5
Dimkox/Getzilla
AI speed. Engineering discipline. Getzilla lets an AI write code for your project and checks that code before it is allowed to stay.
Orchestrator 13.7k tok · · Q25
Nmor/the-council
The Council: shared engineering and domain guidance for Claude Code and Codex. On-demand skills, specialist reviews, runtime-specific hooks, verification and context controls. MIT.
Orchestrator 13.7k tok · · Q25