What is options-sanity-check?

A checklist for reviewing Indian options trades before entry. It examines implied volatility, Greeks such as delta and theta, margin, liquidity, and possible profit or loss for NIFTY, BANKNIFTY, and stock options through Zerodha Kite.

Use it to review single-option positions or multi-leg strategies such as spreads, straddles, strangles, iron condors, and butterflies.

It helps expose key risks and trade details before an order is placed; it does not recommend trades.

options-sanity-check — Skill for Claude Code by Sundeepg98

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.

Any agent

npx skills add Sundeepg98/kite-mcp-server --skill options-sanity-check

Clone the repo

git clone --depth 1 https://github.com/Sundeepg98/kite-mcp-server

Made for: Claude Code.

Or install kite, the plugin that ships this one along with the rest of its 8 skills, 3 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/options-sanity-check/github.svg)](https://agentmods.dev/skills/sundeepg98/kite-mcp-server/options-sanity-check)

Your own site

<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/options-sanity-check"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/options-sanity-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sundeepg98/kite-mcp-server/options-sanity-check"><img src="https://agentmods.dev/badge/skills/sundeepg98/kite-mcp-server/options-sanity-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,242 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin fork From a forked repository.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00119	$0.01242
Opus 5	$0.00060	$0.00621
Sonnet 5	$0.00024	$0.00248
Haiku 4.5	$0.00012	$0.00124

Measured 10d ago against content hash ffb06fc1a1fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

options-sanity-check scanned grade C with 1 finding 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 10d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

options module before proceeding. Don't refuse to help, but flag the education gap.

skills/options-sanity-check/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Options Sanity Check (NIFTY / BANKNIFTY / Stock F&O)

Options are high-gamma, high-theta instruments. This skill forces the user to look at Greeks, liquidity, and margin before clicking. It is NOT a trade recommender.

1. Identify the leg(s)

From the user's prompt, extract each leg:

Underlying (NIFTY, BANKNIFTY, RELIANCE, etc.)
Expiry (weekly or monthly — ask if ambiguous)
Strike
Option type (CE = call, PE = put)
Side (BUY or SELL)
Lots (not shares — NIFTY lot size changes, confirm)

If the user says "sell 24500 PE expiring next Thursday", that's one leg. Multi-leg strategies (straddle, strangle, spread, iron condor, butterfly) are 2-4 legs.

2. Pull the chain + Greeks

Call get_option_chain for the underlying + expiry — returns strikes, OI, IV.
Call options_greeks for the specific leg(s) — returns delta, gamma, theta, vega, IV using Black-Scholes.
For multi-leg strategies, call options_payoff_builder — returns payoff diagram points, max profit, max loss, breakevens.
Call get_quotes on each leg for bid/ask spread and volume (liquidity check).
Call get_order_margins (or get_basket_margins for multi-leg) — options margins differ wildly between buy and sell.

3. Present the sanity report

## Options Sanity Check: <strategy name or leg summary>

### Legs
1. <BUY|SELL> <lots> <underlying> <expiry> <strike> <CE|PE> @ <current premium>
2. ...

### Greeks (per leg, for 1 lot)
| Leg | Delta | Gamma | Theta | Vega | IV |
|---|---|---|---|---|---|
| 1 | <d> | <g> | <t>/day | <v> | <iv>% |

### Liquidity
- Bid-ask spread: <pct>% of premium — flag if >5%
- Today's volume: <n> contracts — flag if <100
- Open interest: <n>

### Payoff (multi-leg)
- Max profit: <amt> at <underlying price>
- Max loss: <amt> at <underlying price>
- Breakeven(s): <price1>, <price2>
- Net premium: debit <amt> | credit <amt>

### Margin
- Required (SPAN+Exposure): <amt>
- Available: <amt>
- Utilization after: <pct>%

### Risk Flags
<Only include applicable:>
- IV in top quintile — short-vol strategies face mean reversion risk
- IV in bottom quintile — long-vol strategies face decay without catalyst
- Theta > <X>% of premium/day — time decay is significant
- Undefined-risk leg (naked SELL without hedge) — margin locks up, tail risk is infinite
- Expiry within 7 days — gamma acceleration / pin risk
- Wide bid-ask — execution slippage likely

Read the full file on GitHub · 109 lines

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.

10d ago First seen · 109 lines · 119 tokens per session scan C ffb06fc1a1fd

Subscribe to this mod's changes

options-sanity-check is a skill published in the GitHub repository Sundeepg98/kite-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 1,242 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). It comes from a forked repository.

Finance and fintech ai-trading algorithmic-trading backtesting chatgpt claude fintech

options-sanity-check

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Tells the agent never to refusehighAnti-refusal

How it starts

Options Sanity Check (NIFTY / BANKNIFTY / Stock F&O)

1. Identify the leg(s)

2. Pull the chain + Greeks

3. Present the sanity report

What this file has done since we first saw it

Other skills, from other repositories

quant-mathematician

position-optimizer

ai-trading-agent

strategy-optimizer

mean-reversion-engineer

ai-hedge-fund