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 agentmods add instructions/buzzr-app/dfs-engine/agents-mdgit clone --depth 1 https://github.com/Buzzr-app/dfs-engineWhat 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 | $0.01643 | $0.01643 |
| Opus 5 | $0.00822 | $0.00822 |
| Sonnet 5 | $0.00329 | $0.00329 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
dfs-engine AGENTS.md 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Buzzr Sports Engines
Guidance for AI coding agents working in this monorepo or consuming the published @buzzr/* packages.
What this repo is
An npm workspaces monorepo (packages/*) publishing ten TypeScript packages for sports betting / DFS apps: three pure core engines, one stdio MCP server, one filesystem CLI, and five provider/UI/testing satellites. The core engines perform no I/O and have zero external runtime dependencies. Boundary packages have explicit jobs: the CLI reads files, provider packages call consumer-supplied loaders, and the MCP server uses the official MCP SDK plus Zod.
Package map and API entry points
Each package's public API is exactly what packages/<name>/src/index.ts exports. Do not import from deep paths — only the package root is a supported entry point.
| Package | Directory | Primary entry points |
|---|---|---|
@buzzr/dfs-engine |
packages/dfs-engine |
createDfsEngine, defineStatProvider, defineBookPolicy, engine.settleEntry, engine.settleEntries (v5 batch) |
@buzzr/bets-core |
packages/bets-core |
calculateNoVigFairLine, combineAmericanOdds, calculateParlayFairValue, calculateExpectedValue, calculateKellyStake, calculateClosingLineValue, calculateRollupByPeriod |
@buzzr/entertainment-engine |
packages/entertainment-engine |
resolveBuzzScores, enrichGameRowWithBuzzScores, isMustWatch, rankGamesForUser |
@buzzr/mcp |
packages/mcp |
MCP server, bins mcp / buzzr-mcp, 11 tools over the three engines |
@buzzr/dfs-cli |
packages/dfs-cli |
bin dfs-grade; runGrade, runGradeFromFiles |
@buzzr/dfs-react |
packages/dfs-react |
getSlipDisplayModel, getStatusTone, formatLegLabel, formatLegLine |
@buzzr/dfs-testkit |
packages/dfs-testkit |
makeDfsEntry, makeDfsLeg, makeGameLogEntry, createMockStatProvider, makeInvalidDfsEntry |
@buzzr/dfs-provider-espn |
packages/dfs-provider-espn |
createEspnStatProvider |
@buzzr/dfs-provider-sportradar |
packages/dfs-provider-sportradar |
createSportradarStatProvider, sportradarRowToGameLog |
@buzzr/dfs-engine-test-vectors |
packages/dfs-engine-test-vectors |
TEST_VECTORS engine regression fixtures |
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.
- yesterday First seen · 74 lines · 1,643 tokens per session scan A 5b81a1c03572
dfs-engine AGENTS.md is an instructions file published in the GitHub repository Buzzr-app/dfs-engine (0 stars, last pushed 20d ago), licensed MIT. It adds 1,643 tokens to every session, about $0.0082 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 instructions, from other repositories
turborepo AGENTS.md
Instructions for vercel/turborepo, covering agents.md, architecture, keeping documentation up to date, pull request guidelines and always run pre-commit/pre-push hooks.
nuxt-starter CLAUDE.md
Instructions for lazercaveman/nuxt-starter, covering claude.md — nuxt-starter, project, tech stack, directory layout and commands.
b2b-saas-starter AGENTS.md
Instructions for brandhaug/b2b-saas-starter, covering b2b saas starter, intent node index, setup, dependencies and cross-cutting rules.
wishlist CLAUDE.md
Claude Code instructions for ugho49/wishlist, covering claude.md, development commands, building and running, graphql codegen and testing and quality.
b2b-saas-starter CLAUDE.md
Instructions for brandhaug/b2b-saas-starter, a project described as: Cloudflare-first B2B SaaS monorepo starter. TanStack Start, Effect v4, Drizzle on D1, Better Auth, Alchemy v2, REST + MCP, React Email, Storybook, Vitest, Playwright, oxlint, oxfmt, Turbo, Bun.
sii CLAUDE.md
Claude Code instructions for dostertags/sii, covering project: sii — typescript core + cli + mcp for sii chile, what this project does, architecture, tech stack and conventions.