koni-ea-dev

koni-ea-dev is a skill for Claude Code, Codex from Koniverse/Koni-ea. It costs 197 tokens per session (2,676 once invoked), scanned A, original, MIT.

A programming standard for MQL5 Expert Advisors and custom indicators in MetaTrader 5. An Expert Advisor is an automated trading program that runs on a linked trading account.

In plain words
What is it for?
Structuring trading programs, handling platform events, placing orders with CTrade, using indicators, detecting new bars, managing risk, and testing code honestly before deployment.
Why use it?
It addresses MQL5-specific lifecycle, timing, indicator, order, risk, compilation, and testing issues that can make trading code behave incorrectly.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/koniverse/koni-ea/koni-ea-dev
Any agent
npx skills add Koniverse/Koni-ea --skill koni-ea-dev
Clone the repo
git clone --depth 1 https://github.com/Koniverse/Koni-ea

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for koni-ea-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/koniverse/koni-ea/koni-ea-dev.svg)](https://agentmods.dev/skills/koniverse/koni-ea/koni-ea-dev)
Your own site
<a href="https://agentmods.dev/skills/koniverse/koni-ea/koni-ea-dev"><img src="https://agentmods.dev/badge/skills/koniverse/koni-ea/koni-ea-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00197 $0.02676
Opus 5 $0.00098 $0.01338
Sonnet 5 $0.00039 $0.00535
Haiku 4.5 $0.00020 $0.00268

Measured 5d ago against content hash 42e5c3d060fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

koni-ea-dev 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 5d 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.

skills/koni-ea-dev/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

koni-ea-dev — programming a correct MQL5 Expert Advisor

koni-ea-dev is the standard for programming a Koniverse MQL5 Expert Advisor correctly: the lifecycle and event model, the trading and risk mechanics, the MQL5 traps that only bite in production, and how to compile clean and test honestly. It is to MQL5 EAs what koni-qc is to test docs — a methodology for writing correct code, not a code generator. It is deliberately scoped to the programming; the operational lifecycle around a released EA (versioning, registry, deployment, per-version docs) is its sibling skill koni-ea-ops.

What you are building, and where it runs

An EA written to this standard is compiled and run by Senti. The author pastes .mq5 source into Senti's Author Studio, presses Compile, presses Save as EA, and deploys it to a linked broker account. Senti runs it on its own MT5 terminals — 24/5, in a datacenter near the broker.

The author does not need MetaEditor, an .ex5, a .set file, or a Windows machine. Do not tell them otherwise. A local MetaTrader is optional and useful only for running the Strategy Tester.

Three things follow that change how you write the code:

  • Senti runs a static safety scan before compiling. It blocks any #import, every WebRequest (the domain allowlist ships empty, and a non-literal URL is always refused), the destructive file calls FileDelete / FolderDelete / FolderClean / FileMove, and SendFTP. Never write these into a strategy; design around the restriction rather than trying to slip past it.
  • It must survive a restart. Senti restarts terminals after crashes, node reboots, and maintenance. The EA has to rebuild in-flight state from open positions and GlobalVariables — see self-recovery. On a desktop this is an edge case; here it is routine.
  • It runs unattended. Nobody is watching the chart. Every block, skip, and refusal needs a PrintFormat with a bracketed tag, because the Journal is the only witness.

Read the full file on GitHub · 171 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 171 lines · 197 tokens per session scan A 42e5c3d060fd

Subscribe to this mod's changes

koni-ea-dev is a skill published in the GitHub repository Koniverse/Koni-ea (11 stars, last pushed 1mo ago), licensed MIT. It adds 197 tokens to every session and 2,676 once invoked, about $0.0010 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 2026-08-30.