Borrowing it
Nothing to install: this file belongs to Brandon-Born/bga-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/Brandon-Born/bga-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Brandon-Born/bga-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/instructions/brandon-born/bga-mcp/agents-md)<a href="https://agentmods.dev/instructions/brandon-born/bga-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/brandon-born/bga-mcp/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/brandon-born/bga-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/brandon-born/bga-mcp/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 | $0.02914 | $0.02914 |
| Opus 5.5 | $0.01166 | $0.01166 |
| Sonnet 5.5 | $0.00583 | $0.00583 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
bga-mcp 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 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.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in bga-mcp
Instructions for any coding agent working in this repository, in the AGENTS.md format. This file is canonical; CLAUDE.md points here so Claude Code reads the same rules. Change this file, not a copy of it.
bga-mcp is a local, read-only MCP server that inspects and validates BoardGameArena game projects. It reads a developer's project from disk and reports cross-file defects. It never writes to a project. Network access is off by default; explicitly enabled documentation and experimental Studio reads use the reviewed policy boundaries recorded in the threat model.
docs/BACKLOG.md is the executable source of truth for planned work. CONTRIBUTING.md states the contribution rules; everything below is in addition to them.
For repository work, read the current checkout's docs/BACKLOG.md, docs/TESTING.md and docs/THREAT_MODEL.md; the immutable public links also serve installed-package readers.
Current capability inventory and permissions
Generated in a repository checkout by corepack pnpm docs:inventory from the capability manifest, release selection, topic table and policy defaults; installed MCP discovery checks both profiles.
Network access is off by default. The public command excludes network surfaces and refuses network/Studio flags. In the development profile, --allow-network enables documentation search, topic reads and framework-version reads; Studio reads additionally require --experimental-studio-logs, an authorized account and session. The experimental Studio reader cannot read the browser-rendered log panel. No profile provides synchronization, uploads or other mutations.
Resource templates are URI patterns returned by resources/templates/list; concrete resources are individually listed URIs returned by resources/list. Counts below include each separately, including the fixed documentation-topic expansions.
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 Changed · +73 lines · +1,861 tokens per session 1dda4e5b3ddd
- 2mo ago First seen · 53 lines · 1,053 tokens per session scan A 57ed2aac4b33
bga-mcp AGENTS.md is an instructions file published in the GitHub repository Brandon-Born/bga-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 2,914 tokens to every session, about $0.0117 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.
bga-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bga-mcp AGENTS.mdBrandon-Born/bga-mcp | Instructions file | 0 | today | Apache-2.0 | A | 2,914 | 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 | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | 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 |