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 skills add EternaHybridExchange/mcp-trading-agent --skill scalpgit clone --depth 1 https://github.com/EternaHybridExchange/mcp-trading-agentWrote 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/eternahybridexchange/mcp-trading-agent/scalp)<a href="https://agentmods.dev/skills/eternahybridexchange/mcp-trading-agent/scalp"><img src="https://agentmods.dev/badge/skills/eternahybridexchange/mcp-trading-agent/scalp/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/skills/eternahybridexchange/mcp-trading-agent/scalp"><img src="https://agentmods.dev/badge/skills/eternahybridexchange/mcp-trading-agent/scalp.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 | $0.00024 | $0.00582 |
| Opus 5.5 | $0.00010 | $0.00233 |
| Sonnet 5.5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
scalp 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Momentum Scalping
A short-term scalping strategy that identifies momentum moves and captures quick profits with tight risk management.
Parameters
- Take-Profit: 1.0% from entry
- Stop-Loss: 0.6% from entry
- Risk per trade: 1-2% of available balance
- Max concurrent positions: 3
- Leverage: 10x (default)
Workflow
1. Scan for Momentum
Call get_tickers with no symbol to retrieve all tickers. Filter for:
- Long candidates:
price24hPcnt> 3% (strong upward momentum) - Short candidates:
price24hPcnt< -3% (strong downward momentum) - Volume filter: prioritize symbols with above-average 24h volume
Sort candidates by absolute price24hPcnt to find the strongest movers.
2. Check Current Positions
Call get_positions to see how many positions are open. Do not exceed 3 concurrent scalp positions. If already at the limit, skip or close the weakest position first.
3. Orderbook Confirmation
For each candidate, call get_orderbook and analyze:
- For longs: bid volume should be at least 1.5x ask volume in the top 5 levels (buying pressure)
- For shorts: ask volume should be at least 1.5x bid volume in the top 5 levels (selling pressure)
If the orderbook does not confirm the direction, skip the symbol.
4. Execute the Trade
For confirmed candidates:
- Call
get_instrumentsto get lot size and tick size - Call
get_balanceto check available margin - Calculate position size (risk 1-2% of balance)
- Call
set_leverageto set 10x leverage - Call
place_orderas a market order with:- Take-profit at 1.0% from current price
- Stop-loss at 0.6% from current price
5. Monitor and Cycle
After placing a trade:
- Call
get_positionsto verify entry - Report the trade details
- If fewer than 3 positions are open, scan for the next candidate
- Repeat the cycle
Notes
- This strategy works best during high-volatility periods
- Avoid scalping during low-volume hours
- If a symbol has already been scalped and closed at SL, do not re-enter the same symbol in the same session
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 · 65 lines · 24 tokens per session scan A 673e7e2cadf9
scalp is a skill published in the GitHub repository EternaHybridExchange/mcp-trading-agent (6 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 582 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
quant-mathematician
You are a world-class applied mathematician, statistical researcher, and quantitative strategy architect.
position-optimizer
You are a top 0.1% quantitative position-sizing and risk-optimization agent.
ai-trading-agent
You are an AI trading research assistant connected to Trader Dev MCP.
mean-reversion-engineer
You are a top 0.1% quantitative trading engineer and Pine Script developer.
strategy-optimizer
You are a top 0.1% quantitative strategy optimization agent.
eterna-trading-guide
Comprehensive trading guide for the Eterna MCP Gateway. Covers risk management rules, position sizing, deposit flow, and order lifecycle for Bybit perpetual futures trading via executecode + eterna. SDK.