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 OpenLinkSoftware/ai-agent-skills --skill wc2026-match-reportgit clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-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/openlinksoftware/ai-agent-skills/wc2026-match-report)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/wc2026-match-report"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/wc2026-match-report/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/openlinksoftware/ai-agent-skills/wc2026-match-report"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/wc2026-match-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.05067 |
| Opus 5 | $0.00046 | $0.02534 |
| Sonnet 5 | $0.00018 | $0.01013 |
| Haiku 4.5 | $0.00009 | $0.00507 |
Grade A, and why
wc2026-match-report 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.
2. **Inline build** — fetch data via curl + construct HTML section-by-section per `references/query-templates.md` How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FIFA World Cup 2026 Match Intelligence Report Skill
Three report types:
| Type | Subject | Script |
|---|---|---|
| Match report (default) | a fixture (Team A vs Team B) | scripts/report_template_create.py <match_id> <out> |
| Player report | a single player across the tournament | scripts/player_report_create.py <player_id|name> [--out …] |
| Analytics scatter report | tournament-wide player comparisons | scripts/analytics_scatter_report_create.py [--chart …] [--out …] |
Pick the player report whenever the request is about one person ("create a player report for Jude Bellingham", "player intelligence for Olise"). Pick the analytics scatter report for tournament-wide cross-player comparisons ("running data report", "passing volume vs accuracy", "Simon Brunson-style chart"). Everything below with no specific heading refers to the match report.
Analytics Scatter Report Mode
Use scripts/analytics_scatter_report_create.py when the request is about comparing all players across one or two metrics — running data, passing efficiency, physical load, attacking output. This produces a Simon Brunson-style infographic: cream background, bold print-inspired header, numbered Chart.js scatter cards with zoom/pan, auto-generated insights, and click-through to player /describe/ profiles. Data is fetched live by the browser at page-load time — no server-side SPARQL needed.
Trigger phrases:
- "running data report", "Simon Brunson-style report", "scatter chart for all players"
- "compare [metric] vs [metric] across the tournament"
- "passing volume vs accuracy chart", "physical load comparison"
- "who covers the most distance", "speed vs sprint metres"
Script location: scripts/analytics_scatter_report_create.py in simon-bronwell/ style output
Output directory: simon-bronwell/ under the working directory (or specify with --out)
# Running data (reproduces the existing fatigue-index example):
python3 scripts/analytics_scatter_report_create.py \
--title "RUNNING DATA" --emoji "🏃" \
--subtitle "Player-Level Relationships" \
--desc "How total volume, high-speed work, top speed and sprint metres are connecting" \
--note "Players with 45+ tournament minutes" \
--chart "totalDistance,highSpeedDistance,Total distance (m),High-speed distance (m),Total Distance vs High-Speed Distance" \
--chart "topSpeed,sprintMetres,Top speed (km/h),Sprint metres (m),Top Speed vs Sprint Metres" \
--out simon-bronwell/YYYYMMDD-running-data.html
# Passing intelligence:
python3 scripts/analytics_scatter_report_create.py \
--title "PASSING INTELLIGENCE" --emoji "🎯" \
--subtitle "Volume & Accuracy" \
--desc "How passing volume and accuracy relate across all outfield players" \
--chart "passes,passAccuracy,Total Passes,Pass Accuracy (%),Volume vs Accuracy" \
--chart "passes,assists,Total Passes,Assists,Pass Volume vs Creativity" \
--out simon-bronwell/YYYYMMDD-passing-intelligence.html
# Attacking output:
python3 scripts/analytics_scatter_report_create.py \
--title "ATTACKING OUTPUT" --emoji "⚽" \
--subtitle "Shots, Goals & Creativity" \
--desc "Comparing shot volume, on-target accuracy and assist creation across forwards and midfielders" \
--chart "shots,goals,Shots,Goals,Shot Volume vs Goals" \
--chart "shots,shotsOnTarget,Shots,Shots on Target,Shot Volume vs Accuracy" \
--out simon-bronwell/YYYYMMDD-attacking-output.html
What ships with it
6 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.
- 12d ago First seen · 349 lines · 92 tokens per session scan A 71c14bbf9565
wc2026-match-report is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 5,067 once invoked, about $0.0005 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…