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 Buzzr-app/dfs-engine --skill buzzr-sports-enginegit clone --depth 1 https://github.com/Buzzr-app/dfs-engineWrote 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/buzzr-app/dfs-engine/buzzr-sports-engine)<a href="https://agentmods.dev/skills/buzzr-app/dfs-engine/buzzr-sports-engine"><img src="https://agentmods.dev/badge/skills/buzzr-app/dfs-engine/buzzr-sports-engine.svg" alt="Measured on agentmods" 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 | $0.00110 | $0.01278 |
| Opus 5 | $0.00055 | $0.00639 |
| Sonnet 5 | $0.00022 | $0.00256 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
buzzr-sports-engine 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buzzr Sports Engine
Use Buzzr when the user needs auditable sports math instead of an estimated calculation. Prefer the MCP server for interactive analysis and the @buzzr/* packages for application code, custom policies, provider adapters, or high-volume pipelines.
Route the request
- Identify the domain:
- DFS settlement:
list_book_policies,validate_dfs_entry,grade_dfs_entry, orgrade_dfs_entries. - Odds and bankroll math:
fair_line,closing_line_value,parlay_value, orkelly_stake. - Historical analysis:
summarize_bet_history. - Entertainment scoring:
predict_game_buzzorrank_games.
- DFS settlement:
- Use the MCP tools when they are available in the current session.
- If the tools are unavailable, help configure the local server or use the matching npm package in code. Do not imitate a tool result and present it as engine output.
- Read references/mcp-tools.md for the 11-tool catalog, limits, and response contracts.
- Before any operator-specific DFS conclusion, follow references/operator-safety.md.
Configure the local MCP server
For repeatable work, pin the reviewed published version:
[mcp_servers.buzzr]
command = "npx"
args = ["-y", "@buzzr/[email protected]"]
Use @buzzr/mcp@latest only when automatic upgrades are acceptable. The server uses stdio, writes protocol messages only to stdout, and needs no API key. Restart the client after changing its MCP configuration.
If startup fails, check these in order:
- Node.js is version 22 or newer.
- The package version exists:
npm view @buzzr/[email protected] version. - The executable starts cleanly:
npx -y @buzzr/[email protected]. - The client launches the command directly rather than through an interactive shell.
Settle DFS entries
Call list_book_policies before grading. Use only a policy/play type reported as executable: true. A draft fixture is documentation, not a grading implementation.
Supply the slip's own bookId, playTypeId, displayedMultiplier, stake, placed timestamp, and leg details. Supply observed stats as actual or actualsByLegId; the MCP server does not fetch box scores. Mark DNP, void, or other operator rulings explicitly when known.
What ships with it
3 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.
- 8d ago First seen · 92 lines · 110 tokens per session scan A 95d1aa3b9d75
buzzr-sports-engine is a skill published in the GitHub repository Buzzr-app/dfs-engine (0 stars, last pushed 5d ago), licensed MIT. It adds 110 tokens to every session and 1,278 once invoked, about $0.0006 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
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
Unit Test Scaffold (TypeScript)
Generate TypeScript unit test skeletons (Jest/Vitest) from specifications.
upgrade-packages-js
Safely upgrade JavaScript packages with breaking change detection, migration guidance, and automated code migrations (npm/pnpm/yarn). Cross-platform with git safety branch enforcement.
modern-tooling
Opinionated tooling and conventions for modern JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier, monorepos, library publishing, or establishing coding standards.
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.