Borrowing it
Nothing to install: this file belongs to mcp-gtw/demo-game. 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/mcp-gtw/demo-game/main/AGENTS.mdgit clone --depth 1 https://github.com/mcp-gtw/demo-gameWrote 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/instructions/mcp-gtw/demo-game/agents-md)<a href="https://agentmods.dev/instructions/mcp-gtw/demo-game/agents-md"><img src="https://agentmods.dev/badge/instructions/mcp-gtw/demo-game/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.
<a href="https://agentmods.dev/instructions/mcp-gtw/demo-game/agents-md"><img src="https://agentmods.dev/badge/instructions/mcp-gtw/demo-game/agents-md.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 | $0.11360 | $0.11360 |
| Opus 5.5 | $0.04544 | $0.04544 |
| Sonnet 5.5 | $0.02272 | $0.02272 |
| Haiku 4.5 | $0.01136 | $0.01136 |
Grade B, and why
demo-game AGENTS.md scanned grade B with 1 finding 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 1mo 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
(mcp.json, the pretty-printed JSON with one Copy button), Endpoint + token (the two shown separately, How it starts
The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for working in this repository.
What this is
mcp-gateway-demo is a multiplayer, top-down action game where every agent is controlled only
through MCP tools. It is the reference extension of
mcp-gtw: one AppGateway(Gateway) subclass adds an
authoritative grid world, its HTTP/WebSocket surface and a self-hosted Phaser client.
The internal package name is intentionally generic (app) so the demo is easy to port or reuse.
It requires mcp-gtw>=0.0.12, resolved from PyPI by the lockfile. Development, CI and Docker builds work without a sibling gateway checkout. See docs/oauth.md for deployment.
Documentation map
- OAuth — public endpoint before login, client-first authorization, dark pages and finite login deadlines: docs/oauth.md.
- Session resumption — tab-specific method restoration, same-account cookie reuse and finite MCP activity retention: acceptance scenarios.
- Modern MCP discovery — the browser and proxy gates exercise per-request discovery and actual tool execution with the published gateway: docs/oauth.md.
- OAuth budgets and scoped grants — BFF limits are configurable by IP and verified account, and grants retain explicit client scopes. Extension points and invariants: docs/oauth.md.
- Full OAuth acceptance checklist — gateway checklist tracks architecture, SEC/GAME/SDK/HOST/UPG requirements and external checks.
- CI — the game matrix tests locked PyPI dependencies independently, and Python 3.12 also gates real HTTPS cross-origin embedded consent in Chromium. The gateway OAuth acceptance workflow checks out all three full SHAs and runs Chrome/Inspector/Docker tests. See docs/oauth.md and tests/e2e/README.md.
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.
- 1mo ago First seen · 512 lines · 11,360 tokens per session scan B 9d50267b83fd
demo-game AGENTS.md is an instructions file published in the GitHub repository mcp-gtw/demo-game (3 stars, last pushed 1mo ago), licensed MIT. It adds 11,360 tokens to every session, about $0.0454 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
demo-game AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| demo-game AGENTS.mdmcp-gtw/demo-game | Instructions file | 3 | 1mo ago | MIT | B | 11,360 | 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 ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |