{
  "markdown": "# stillos-edge-gate\n\n**A callable trust primitive. Grade a track record *before* you commit capital.**\n\nA real edge is not a prediction — it is a repeatable, out-of-sample, fee-adjusted\ndecision advantage that survives a regime change. This tells you, in one word, whether\na strategy has one:\n\n```\nREAL_EDGE | REGIME_LUCK | NEGATIVE_EV | INSUFFICIENT_DATA\n```\n\nFail-closed: anything that isn't a surviving, fee-adjusted, regime-stable edge is rejected.\nEvery verdict ships with a signed, independently verifiable receipt.\n\n## Install\n```bash\nnpx stillos-edge-gate grade trades.json\n```\nor add as an MCP server (Claude Desktop / any MCP client):\n```json\n{ \"mcpServers\": { \"stillos-edge-gate\": { \"command\": \"npx\", \"args\": [\"stillos-edge-gate\", \"mcp\"] } } }\n```\n\n## Input\n```json\n[ { \"t\": \"2026-06-01T12:00:00Z\", \"price\": 0.62, \"side\": \"no\", \"outcome\": 1 }, ... ]\n```\n`price` = entry price 0..1 · `side` = yes|no · `outcome` = 1 won / 0 lost.\n\n## How it decides\n- chronological **70/30 out-of-sample holdout** (most-recent 30% is the test)\n- **fee + slippage** adjusted per trade\n- **significance test** (t ≥ 1.5) on fee-adjusted EV\n- `REAL_EDGE` only if +EV in **both** splits after fees, significant.\n\n## Why trust it\nWe ran it on our own live trading book first. It returned **NEGATIVE_EV** — and we\npublished the signed receipt. We don't sell edges; we tell you whether yours is real.\n\n## Library\n```js\nconst { gradeStrategy } = require('stillos-edge-gate');\nconst v = gradeStrategy(trades); // { verdict, train, test, t_stat, reasons }\n```\n\nMIT. https://nolawealthfinancial.com/notary\n",
  "bytes": 1587,
  "sha": "78e176e90b6c848ff59d5c0295ddac3c366eaf2986ae40f70ac81ba2816e544f",
  "repo_slug": "stillmarcus24/stillos-edge-gate",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_stillmarcus24_stillos_edge_gat_a1ba21fa/readme"
}