What is Sports-Context-Protocol AGENTS.md?

A project instruction file for SCP Golf, a local server that gives golf-related AI agents synthetic course information before they act. It records the project goal, technology choices, and rules for safe output.

Use it when building or changing the TypeScript MCP server, its JSON data, tools, prompts, or golfer-facing explanations.

It gives coding agents the constraints they must follow while working on the project. In particular, it keeps the alpha based on demo data and prevents internal policy details from being shown to golfers.

How Dswane/Sports-Context-Protocol configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Dswane/Sports-Context-Protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Dswane/Sports-Context-Protocol/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Dswane/Sports-Context-Protocol

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dswane/sports-context-protocol/agents-md/github.svg)](https://agentmods.dev/instructions/dswane/sports-context-protocol/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dswane/sports-context-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/dswane/sports-context-protocol/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dswane/sports-context-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/dswane/sports-context-protocol/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 460 This file is loaded in full into every session.

When invoked 460 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00460	$0.00460
Opus 5.5	$0.00184	$0.00184
Sonnet 5.5	$0.00092	$0.00092
Haiku 4.5	$0.00046	$0.00046

Measured 2mo ago against content hash 03b5e2d3ebda, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Sports-Context-Protocol 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 2mo 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.

AGENTS.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SCP Golf — Build Instructions for Codex

Project goal

Build and extend SCP Golf, a local MCP server for golf operations. SCP Golf gives AI golf agents course context before they book, price, move, message, or recommend anything. The alpha uses only synthetic demo data. Do not reference real courses, real tee-sheet providers, real golfer data, or real customers.

Core product principle

Before a golf agent acts, it checks SCP. Then SCP learns from what happened.

Technical choices

TypeScript, Node.js (ESM, NodeNext module resolution)
@modelcontextprotocol/sdk (high-level McpServer + registerTool/Resource/Prompt)
zod for input schemas
JSON file storage in src/data/ for the alpha — no database
MCP stdio transport
No external APIs, no dashboard, no auth in the alpha

Hard rules

NEVER write logs to stdout. stdio transport uses stdout for JSON-RPC. All logging goes to stderr (see the log() helper in src/index.ts).
Golfer-facing output must never expose internal policy language (no "protected member inventory", "league block", "operator override"). The explain.ts golferSafe() filter is the safety net; do not bypass it.
"Learning" means updating operational memory from feedback. Never implement model training, embeddings, or a nightly retrain.
Every decision tool call must write a DecisionEvent to the ledger.
Run npm run typecheck and npm run test after any change.
Update docs/ when behavior changes.

The learning loop is the product

The single most important behavior: ask for Saturday ~09:00, have an operator override it once, ask again, and SCP shifts its recommendation. The decision fingerprint (src/core/fingerprint.ts) is the contract that makes this deterministic — do not change the fingerprint key field order without a migration. See docs/LEARNING_LOOP.md.

Quality expectations

Small, pure, readable functions. Friendly errors for missing data files.
Keep the alpha synthetic-only. New features go behind the same JSON-file storage layer until Phase 2.

Read the full file on GitHub · 43 lines

Changes

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.

2mo ago First seen · 43 lines · 460 tokens per session scan A 03b5e2d3ebda

Subscribe to this mod's changes

Sports-Context-Protocol AGENTS.md is an instructions file published in the GitHub repository Dswane/Sports-Context-Protocol (0 stars, last pushed 5mo ago), licensed MIT. It adds 460 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Sports-Context-Protocol AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Sports-Context-Protocol AGENTS.mdDswane/Sports-Context-Protocol	Instructions file	0	5mo ago	MIT	A	460	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

Sports-Context-Protocol: Instructions file for Codex