Borrowing it
Nothing to install: this file belongs to Koniverse/Koni-ea. 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/Koniverse/Koni-ea/main/AGENTS.mdgit clone --depth 1 https://github.com/Koniverse/Koni-eaWrote 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/koniverse/koni-ea/agents-md)<a href="https://agentmods.dev/instructions/koniverse/koni-ea/agents-md"><img src="https://agentmods.dev/badge/instructions/koniverse/koni-ea/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/koniverse/koni-ea/agents-md"><img src="https://agentmods.dev/badge/instructions/koniverse/koni-ea/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 | $0.03141 | $0.03141 |
| Opus 5.5 | $0.01256 | $0.01256 |
| Sonnet 5.5 | $0.00628 | $0.00628 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
Koni-ea 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — koni-ea
This file is the single source of truth for all AI agent instructions in this project. Cursor, Gemini, Codex CLI, Copilot CLI, and Claude Code all read it.
CLAUDE.mdis a thin pointer back here plus a Koni-Docs config block; on any conflict, AGENTS.md wins.
What this repo is
koni-ea gives partners, customers, and users of Senti everything needed to
build a trading bot and deploy it — an agent skill set that encodes the MQL5
standard, and a working template to copy.
Senti is a trading-bot platform. It runs bots on its own MT5 terminals — Windows
VPS hosts in a datacenter near the broker, running 24/5 — logged into the broker
account the user linked. A bot reaches it as a compiled .ex5 plus its .set preset,
uploaded to the user's private catalog.
The framing you must never get wrong
The user writes MQL5 source. Senti compiles it and runs it.
They paste .mq5 into Senti's Author Studio, press Compile, press Save as EA, and
deploy. Senti runs a static safety scan, compiles headlessly on its own build host,
and builds the preset from the source's input defaults.
Never tell a user they need MetaEditor, an .ex5, a .set file, or a Windows
machine. They need a browser. A local MetaTrader is optional and only useful for
running the Strategy Tester themselves.
Three things follow, and they are worth saying unprompted:
- The bot goes live when Senti deploys it, never when it is attached to a local chart.
- Their machine can be off. Once deployed, nothing on their computer participates.
- Any local MT5 stays on a demo account. The same bot on their machine and on Senti against one broker account doubles every position and leaves each instance managing trades the other opened. Silent, and the most expensive mistake available.
Code that will not pass the safety scan. Blocked before compiling: any #import;
every WebRequest (the allowlist ships empty, and a non-literal URL is always
refused); FileDelete, FolderDelete, FolderClean, FileMove; SendFTP. Do not
write them into a strategy and do not suggest them — design around the restriction.
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 First seen · 261 lines · 3,141 tokens per session scan A 96a4de185fe4
Koni-ea AGENTS.md is an instructions file published in the GitHub repository Koniverse/Koni-ea (11 stars, last pushed 2mo ago), licensed MIT. It adds 3,141 tokens to every session, about $0.0126 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.