Borrowing it
Nothing to install: this file belongs to playbattlegrid/battlegrid-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/playbattlegrid/battlegrid-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/playbattlegrid/battlegrid-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/playbattlegrid/battlegrid-mcp/claude-md)<a href="https://agentmods.dev/instructions/playbattlegrid/battlegrid-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/playbattlegrid/battlegrid-mcp/claude-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/playbattlegrid/battlegrid-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/playbattlegrid/battlegrid-mcp/claude-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 | $0.04099 | $0.04099 |
| Opus 5.5 | $0.01640 | $0.01640 |
| Sonnet 5.5 | $0.00820 | $0.00820 |
| Haiku 4.5 | $0.00410 | $0.00410 |
Grade A, and why
battlegrid-mcp CLAUDE.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 20d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Maintainer instructions for @battlegrid/mcp-server — a thin stdio proxy to BattleGrid's remote
MCP server.
Not to be confused with AGENTS.md, which is the machine-readable discovery file telling external
agents how to connect. This file is for whoever is changing the code in this repo.
What this package is, and is not
src/index.ts is the whole proxy. It embeds no schemas, hardcodes no tool catalog, and pins no
contract version — it authenticates, connects upstream, and forwards every argument but account verbatim. Almost
every "the server changed" question therefore needs nothing here.
Before adding anything to this package, check whether it belongs in battlegrid-app instead. Tool
schemas, contract semantics, and error vocabularies all live there.
skills/battlegrid-* is generated — never edit it here
The nine skills/battlegrid-* directories, skills/EXPORT.json, and
src/__fixtures__/authoring-contract-digest.json are written by
battlegrid-app/server/scripts/export-mcp-skills.mjs and arrive by pull request from
battlegrid-app/server/scripts/publish-mcp-skills.mjs, which every production deploy of BattleGrid
runs as its last step. It exports only the commit production serves, so the skills here describe the
contract a connected proxy reaches. They are the same instructions BattleGrid's in-app Commander runs
on, which is what makes them true about the tools this proxy forwards.
To change a published skill, change it upstream in battlegrid-app/server/src/skills/<name>/ and
let the export lane bring it here. An edit made in this repository fails
src/__tests__/skill-provenance.test.ts by filename, and would in any case be silently reverted by
the next export.
This is not a style rule. It replaces a real arrangement that cost three pull requests (#47, #48,
#52) and shipped a fork: skills/battlegrid-strategy-studio/ was hand-authored here, drifted from
the server's own document, and needed a gate of its own to notice. One author, one gate.
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.
- 20d ago Changed · +4 tokens per session e83cd71dfdb6
- 21d ago Changed · +7 tokens per session 282a3eec2c71
- 28d ago Changed · +3 lines · +74 tokens per session 0502e9185d67
- 1mo ago Changed · +2 lines · +54 tokens per session 0fb40ab91fbe
- 1mo ago Changed · +71 lines · +1,118 tokens per session d72cb710e209
- 2mo ago Changed 109ceec6b64c
- 2mo ago Changed · +48 lines · +715 tokens per session 7aa6ea430d67
- 2mo ago Changed · +42 lines · +630 tokens per session efd88a8702dd
- 2mo ago First seen · 131 lines · 1,497 tokens per session scan A 2d96f3662dc4
battlegrid-mcp CLAUDE.md is an instructions file published in the GitHub repository playbattlegrid/battlegrid-mcp (0 stars, last pushed today), licensed MIT. It adds 4,099 tokens to every session, about $0.0164 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.
battlegrid-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| battlegrid-mcp CLAUDE.mdplaybattlegrid/battlegrid-mcp | Instructions file | 0 | today | MIT | A | 4,099 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |