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 Sundeepg98/kite-mcp-server --skill trade-checkgit clone --depth 1 https://github.com/Sundeepg98/kite-mcp-serverWrote 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/sundeepg98/kite-mcp-server/trade-check)<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/trade-check"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/trade-check/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/sundeepg98/kite-mcp-server/trade-check"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/trade-check.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 | $0.00084 | $0.01115 |
| Opus 5 | $0.00042 | $0.00558 |
| Sonnet 5 | $0.00017 | $0.00223 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
trade-check 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Trade Check
Before any order lands on Kite, run a pre-flight. This skill is the gate between "I want to trade"
and place_order.
1. Parse intent
From the user's prompt, extract:
- symbol (required) — default exchange
NSEif not prefixed - quantity (required)
- side — BUY or SELL (default BUY)
- order type — MARKET or LIMIT with price (default MARKET)
- product — CNC (delivery) or MIS (intraday); ask if ambiguous
If any required field is missing, ask before calling tools. Don't guess quantity.
2. Prefer the composite tool
order_risk_report (also surfaced as pre_trade_check in some deployments) bundles the five
checks below into one MCP call. Use it first:
- It returns current price, margin check, portfolio impact, existing positions, stop-loss suggestions, warnings, and a recommendation (PROCEED / PROCEED WITH CAUTION / BLOCKED).
- If available, skip straight to step 4 (present the report) with the composite output.
3. Fall back to individual tools
If no composite is available, call in parallel where possible:
get_ltp— current price for the instrument.get_order_margins— margin required for this specific order.get_margins— available funds.get_positions— existing exposure in this symbol.portfolio_concentration— current HHI / top-position weights.
4. Present the pre-flight report
## Pre-Trade Check: <SIDE> <QTY> <SYMBOL>
### Current Price
- LTP: <price> (<today's change>%)
- Order Type: <MARKET | LIMIT @ price>
- Order Value: <qty x price>
### Margin Check
- Required: <amt>
- Available: <amt>
- Utilization after trade: <pct>%
- Status: OK | WARNING | INSUFFICIENT
### Portfolio Impact
- This trade as % of portfolio: <pct>%
- Top-5 concentration after trade: <pct>%
- Existing position in this symbol: none | <qty, avg price, unrealized P&L>
### Risk Flags
<List concerns — only include applicable ones:>
- Margin utilization >70% after trade
- Concentration in one stock >15% after trade
- Trading against existing position (SELL when you already have open SELL, etc.)
- Order value >5% of portfolio
- MARKET order in a thinly-traded symbol
### Stop-Loss Suggestion
- For CNC (delivery): SL ~2% below entry → <price>
- For MIS (intraday): SL ~1% below entry → <price>
- GTT two-leg: trigger at SL + target; ask user before placing
### Recommendation
PROCEED | PROCEED WITH CAUTION | RECONSIDER
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.
- 11d ago First seen · 117 lines · 84 tokens per session scan A 0d8abb7aaafa
trade-check is a skill published in the GitHub repository Sundeepg98/kite-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 1,115 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
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.
strategy-optimizer
You are a top 0.1% quantitative strategy optimization agent.
mean-reversion-engineer
You are a top 0.1% quantitative trading engineer and Pine Script developer.
ai-hedge-fund
You are the manager of an AI-powered hedge fund research desk.