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 asttstxh/worldcup-Viewing-Lottery-Assistant-skill --skill worldcup-match-reportgit clone --depth 1 https://github.com/asttstxh/worldcup-Viewing-Lottery-Assistant-skillWrote 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/asttstxh/worldcup-viewing-lottery-assistant-skill/worldcup-match-report)<a href="https://agentmods.dev/skills/asttstxh/worldcup-viewing-lottery-assistant-skill/worldcup-match-report"><img src="https://agentmods.dev/badge/skills/asttstxh/worldcup-viewing-lottery-assistant-skill/worldcup-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/asttstxh/worldcup-viewing-lottery-assistant-skill/worldcup-match-report"><img src="https://agentmods.dev/badge/skills/asttstxh/worldcup-viewing-lottery-assistant-skill/worldcup-match-report.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 | $0.00095 | $0.01716 |
| Opus 5 | $0.00048 | $0.00858 |
| Sonnet 5 | $0.00019 | $0.00343 |
| Haiku 4.5 | $0.00010 | $0.00172 |
Grade A, and why
worldcup-match-report scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World Cup Match Report
Purpose
Produce a polished, phone-readable Chinese PDF report for one football match. The report must connect verified match evidence to score-range analysis and a concentrated, high-variance fixed-budget lottery plan. Keep user-facing copy formal, clear, neutral, and explicit about uncertainty.
Resources
- Read
references/report-spec.mdbefore generating or revising a report. - Read
references/betting-model.mdbefore producing score analysis or a lottery plan. - Use
assets/known-good-brazil-vs-morocco-2026-06-14.htmlonly as a legacy visual-density reference. Do not copy its match facts or section order. - Use
assets/reference-mobile-roster-*.pngas the required visual direction for parallel team rosters and the vertical combined pitch. - Use
scripts/render_pdf.pyto render the final PDF from a temporary print-ready HTML file.
Workflow
- Parse the requested match, date, competition, and user budget. If the date is missing, search current fixtures and state the inferred date; ask only if multiple plausible matches remain.
- Collect live evidence. Browse official or primary sources first, then reputable secondary sources. Verify current squads, injuries, odds, ranking, venue, exchange rate, coach, lottery rules, assigned referee, tournament-to-date referee statistics, venue surface or roof, weather, local kickoff conditions, travel, and rest.
- Build a source ledger while researching. Track what each source proves, the retrieval date, and whether the information is verified, unavailable, or inference.
- Prepare the match data model: teams, staff, full squad, player photos, Chinese names, aliases, club names in Chinese, market values in RMB, predicted starters, tactics, odds, probability estimates, referee profile, tournament officiating baseline, environment, score-impact adjustments, risks, and the default 100 RMB plan unless the user gives another budget.
- Establish an odds-derived baseline, then explicitly adjust the expected score range using referee and environment evidence. Keep verified observations separate from inferred effects.
- Create a concentrated plan with no more than three selections. Prefer one core path plus one or two high-payout score or handicap paths; do not spread the budget across every available play.
- Generate a temporary print-ready HTML file, then render the final PDF under
output/worldcup-betting-assistant/using a clear slug such asargentina-vs-algeria-2026-06-17.pdf. The PDF is the deliverable; do not deliver HTML unless the user explicitly asks for it. - Render the PDF to PNG pages and inspect it. Check page order, text size, line breaks, roster columns, player photos, combined pitch, betting plan prominence, source readability, absence of clipped or blank content, and clear vertical separation between every player name, age/value line, and extended-details line.
What ships with it
8 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.
- agents/openai.yaml 251 B
- assets/known-good-brazil-vs-morocco-2026-06-14.html 65 KB
- assets/reference-mobile-roster-01.png 550 KB
- assets/reference-mobile-roster-02.png 595 KB
- assets/reference-mobile-roster-03.png 765 KB
- references/betting-model.md 3.6 KB
- references/report-spec.md 8.0 KB
- scripts/render_pdf.py 3.3 KB runs code
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 · 85 lines · 95 tokens per session scan A e99414117a74
worldcup-match-report is a skill published in the GitHub repository asttstxh/worldcup-Viewing-Lottery-Assistant-skill (6 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,716 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
slides
Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…
ingest
Turn external URLs and documents into LLM-ready content — load + cache web pages (HQCC compression) and OCR PDFs/images to Markdown. Use whenever the user gives a URL, asks you to read a webpage, or attaches a PDF/scan that needs to be parsed before reasoning. Executes via the cloud load, cloud search, and cloud parse…
lov-any2deck
Generate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instructions, then generates individual slide images. Supports 16 visual styles, CJK/Latin mixed text, branding overlays, and PPTX/PDF export. Use when the user asks to "create slides", "make a presentation"…
lov-any2docx
Convert Markdown documents to professionally styled DOCX (Word) files with python-docx. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, cover pages, TOC field, watermarks, and page numbers. Supports multiple color themes matching any2pdf (Configurable Academic, Nord, GitHub Light, etc.) and is…
lov-rich-export
A content-export workflow that converts one source document into HTML, Markdown, DOCX, PDF, or an offline delivery package. It accounts for images, audio, video, embedded pages, and interactive charts in each format.