Borrowing it
Nothing to install: this file belongs to Ninjabeam20/SportIQ-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Ninjabeam20/SportIQ-MCP/main/.agents/skills/monte-carlo-bracket/SKILL.mdgit clone --depth 1 https://github.com/Ninjabeam20/SportIQ-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/ninjabeam20/sportiq-mcp/monte-carlo-bracket)<a href="https://agentmods.dev/skills/ninjabeam20/sportiq-mcp/monte-carlo-bracket"><img src="https://agentmods.dev/badge/skills/ninjabeam20/sportiq-mcp/monte-carlo-bracket/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/ninjabeam20/sportiq-mcp/monte-carlo-bracket"><img src="https://agentmods.dev/badge/skills/ninjabeam20/sportiq-mcp/monte-carlo-bracket.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 | $0.00060 | $0.00888 |
| Opus 5 | $0.00030 | $0.00444 |
| Sonnet 5 | $0.00012 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
monte-carlo-bracket 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monte Carlo Bracket Skill
WC 2026 format (do NOT use the old 32-team bracket)
- 48 teams, 12 groups (A–L) of 4.
- Group stage: 4-team round-robin, 3/1/0 points. Equal-points cohorts use available FIFA fields: head-to-head points → head-to-head GD → head-to-head goals → overall GD → overall GF. Missing conduct/latest-ranking data falls back visibly to model rating, then RNG only for equal ratings.
- Advancement: top 2 of each group (24) + 8 best third-placed teams = 32 → Round of 32.
- Knockout: R32 → R16 → QF → SF → Final (single elimination).
- Encoded in
football/data/wc2026.json,elo_seed.json, andwc2026_bracket.json(official R32 template, fixed tree, and all 495 best-third group combinations from Annex C).
Match engine (poisson_xg.py)
lambdas_from_elo(elo_home, elo_away, home_advantage): supremacy =(elo_home + adv - elo_away) * 0.004; split aroundavg_total_goals=2.6; clamp to >= 0.05.scoreline_matrix/outcome_probabilities: independent Poisson grid (truncated at 10 goals); tril = home win, diagonal = draw, triu = away win.- Home advantage at the World Cup is 0 (neutral venues) except for the hosts if you choose to model it.
Elo (elo.py)
expected_score(Ra, Rb, H) = 1 / (1 + 10^(-((Ra+H)-Rb)/400)). Used for the knockout shootout coin flip on a drawn tie.
Sims
group_sim.simulate_group_once(rng, teams, ratings)-> ranked standings (composed by the bracket sim).group_sim.simulate_group_stage(...)-> all 12 groups, contextual best thirds, per-teamp_auto_advance,p_best_third_advance, combinedp_advance, and fallback counts.bracket_sim.simulate_tournament(groups, ratings, n_iter, seed)-> per-team{reach_r32..win}+champion.
Fixture conditioning preserves provider match_id, stage, and explicit winner. Deduplicate by
ID, otherwise stage class + pairing; never let a same-pair knockout overwrite its group result.
Level knockout scores lock only with an explicit penalty winner.
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 · 58 lines · 60 tokens per session scan A f75a0f3ab920
monte-carlo-bracket is a skill published in the GitHub repository Ninjabeam20/SportIQ-MCP (10 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 888 once invoked, about $0.0003 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…