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.
npx agentmods add skills/koniverse/koni-ea/koni-ea-devnpx skills add Koniverse/Koni-ea --skill koni-ea-devgit 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/skills/koniverse/koni-ea/koni-ea-dev)<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>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 | $0.00197 | $0.02676 |
| Opus 5 | $0.00098 | $0.01338 |
| Sonnet 5 | $0.00039 | $0.00535 |
| Haiku 4.5 | $0.00020 | $0.00268 |
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.
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, everyWebRequest(the domain allowlist ships empty, and a non-literal URL is always refused), the destructive file callsFileDelete/FolderDelete/FolderClean/FileMove, andSendFTP. 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
PrintFormatwith a bracketed tag, because the Journal is the only witness.
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.
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.
- 5d ago First seen · 171 lines · 197 tokens per session scan A 42e5c3d060fd
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.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.