Borrowing it
Nothing to install: this file belongs to Alejandrehl/kainext-binance-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/Alejandrehl/kainext-binance-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Alejandrehl/kainext-binance-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/alejandrehl/kainext-binance-mcp/claude-md)<a href="https://agentmods.dev/instructions/alejandrehl/kainext-binance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alejandrehl/kainext-binance-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/alejandrehl/kainext-binance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alejandrehl/kainext-binance-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 | $0.01789 | $0.01789 |
| Opus 5 | $0.00894 | $0.00894 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
kainext-binance-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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — orientación para una sesión nueva
Este repo es dos cosas a la vez, y confundirlas es el error caro:
- Un servidor MCP de Binance spot, en producción, con dinero real. Publicado en PyPI
(
kainext-binance-mcp) y en el MCP Registry. Lo usa el operador a diario. 25 tools, 5 prompts, 8 recursoskb://. - Un motor de research de futuros USD-M, offline y sin keys, detrás del extra
[research]. No expone ninguna tool. Es la Fase 0 de Alpha, el programa de trading sistemático del operador.
Qué NO es: un bot de trading. La ejecución de órdenes es spot-only y requiere un clic humano en un proceso aparte. El motor de futuros investiga; no puede colocar una orden.
Invariantes — romper uno de estos es un incidente, no un bug
| Invariante | Por qué |
|---|---|
| El modelo nunca tiene una trade key | El servidor corre con key read-only. La trade key vive SOLO en el proceso confirmer, que el operador lanza aparte. Es la garantía central del producto |
futures/ es keyless y offline |
No importa un client, no lee una API key, no usa el secret. Lee archivos públicos. Si alguna vez necesita una key, el diseño está mal |
El servidor no importa futures/ |
Import perezoso. Sin el extra [research] el servidor arranca igual. Romperlo deja sin servidor a quien instala por uvx |
_INSTRUCTIONS (server.py) es comportamiento, no documentación |
FastMCP lo inyecta en toda sesión de todo cliente MCP. Editarlo cambia cómo se comporta cada sesión de IA. Ya causó un incidente: en mcp 2.0 el 2º posicional pasó de instructions a title, y pasarlo posicional dejaba la doctrina sin inyectar, en silencio |
instructions= va por nombre |
Ver arriba. tests/test_consistency.py lo verifica |
Nada de credenciales en .mcp.json |
El repo es público. El archivo se versiona pero solo declara MCPs remotos con OAuth; el gate rompe el build si aparece algo con forma de key |
La doctrina tiene dos regímenes (y no se mezclan)
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.
- 8d ago First seen · 121 lines · 1,789 tokens per session scan A cda800e19293
kainext-binance-mcp CLAUDE.md is an instructions file published in the GitHub repository Alejandrehl/kainext-binance-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 1,789 tokens to every session, about $0.0089 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.