Borrowing it
Nothing to install: this file belongs to kschltz/lorcana-mcp-platform. 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/kschltz/lorcana-mcp-platform/main/AGENTS.mdgit clone --depth 1 https://github.com/kschltz/lorcana-mcp-platformWrote 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/kschltz/lorcana-mcp-platform/agents-md)<a href="https://agentmods.dev/instructions/kschltz/lorcana-mcp-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/kschltz/lorcana-mcp-platform/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/kschltz/lorcana-mcp-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/kschltz/lorcana-mcp-platform/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 | $0.00742 | $0.00742 |
| Opus 5.5 | $0.00297 | $0.00297 |
| Sonnet 5.5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
lorcana-mcp-platform 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
This repo is the Lorcana MCP Playtest Platform — an npm-workspaces monorepo (Node 20+, TypeScript ESM) with five packages under packages/:
@lorcana/engine— deterministic rules engine (library, no process).@lorcana/card-data— buildsdist-data/*.jsoncard definitions/scripts (library; artifacts committed).@lorcana/mcp-server— the one long-running service: MCP endpoint + spectator REST/SSE API + serves the built UI. Default port 8787.@lorcana/ui— React spectator app (Vite). In prod it is static files served bymcp-server;npm run dev -w @lorcana/uiruns a separate Vite dev server on:5173that proxies/api→:8787.@lorcana/bots— CLI (not a daemon) that drives AI-vs-AI matches over MCP.
Running / building / testing (standard commands live in root package.json and README.md)
- Build all packages:
npm run build(order matters: card-data → engine → mcp-server → bots → ui). The build is also the type-check/lint step — there is no ESLint config; correctness relies ontsc. - Run the server (dev, hot reload):
npm run dev(tsx watch on mcp-server). Production entrypoint:npm start. - Tests:
npm test(Vitest across all workspaces). No running services needed for tests.
Non-obvious caveats
- The server serves the spectator UI only if
packages/ui/distexists.npm run dev(mcp-server) does NOT build the UI. If you want the browser UI athttp://localhost:8787/, runnpm run build(or at leastnpm run build -w @lorcana/ui) first. Otherwise use the@lorcana/uiVite dev server on:5173. mcp-serverdynamically imports@lorcana/engineat runtime; if the engine'sdistis missing it silently falls back to a limited StubEngine (logs a warning). Alwaysnpm run buildbefore running for full rules behavior.- Sample decks in
data/acceptance/*.txtreference some card names not in the committed pool; the bot runner auto-substitutes them (prints substitution notes) — this is expected, not an error. - Persistence is plain JSON on disk (
packages/mcp-server/data/matches/*.json, gitignored) — no external DB/Docker. Matches resume across server restarts. - Optional LLM bot seats (
--llmSeat) require a local Ollama at:11434; heuristic bots need nothing extra.
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 · 40 lines · 742 tokens per session scan A 24bdea6aaa47
lorcana-mcp-platform AGENTS.md is an instructions file published in the GitHub repository kschltz/lorcana-mcp-platform (0 stars, last pushed 3mo ago), licensed MIT. It adds 742 tokens to every session, about $0.0030 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.
lorcana-mcp-platform AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lorcana-mcp-platform AGENTS.mdkschltz/lorcana-mcp-platform | Instructions file | 0 | 3mo ago | MIT | A | 742 | Codex, OpenCode |
| 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 |