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 evan-thedev/kalshi --skill kalshi-tradinggit clone --depth 1 https://github.com/evan-thedev/kalshiWrote 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/evan-thedev/kalshi/kalshi-trading)<a href="https://agentmods.dev/skills/evan-thedev/kalshi/kalshi-trading"><img src="https://agentmods.dev/badge/skills/evan-thedev/kalshi/kalshi-trading/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/evan-thedev/kalshi/kalshi-trading"><img src="https://agentmods.dev/badge/skills/evan-thedev/kalshi/kalshi-trading.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 | $0.00000 | $0.00883 |
| Opus 5.5 | $0.00000 | $0.00353 |
| Sonnet 5.5 | $0.00000 | $0.00177 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
kalshi-trading 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kalshi Trading Skill
ALWAYS read this file before using any Kalshi tools.
Trading Safety Rules
Read-Only Tools (Safe to Use)
These tools are safe to call any time:
kalshi_get_balance- Check account balancekalshi_list_markets- Browse available marketskalshi_get_market- Get details about a specific marketkalshi_get_orderbook- View current orderbookkalshi_get_positions- View current positionskalshi_list_orders- View current orders
Write Tools (Require User Approval)
NEVER use these tools unless the user explicitly requests a specific trade:
kalshi_create_order- Place an orderkalshi_cancel_order- Cancel an order
Before Placing ANY Order
When the user asks to place a trade, you MUST:
- Confirm the market - Show the user the market details (ticker, title, current prices)
- Confirm the side - Ask: "You want to buy YES at X?" or "You want to sell YES (buy NO) at Y?"
- Confirm the size - Verify the number of contracts
- Confirm the price - Show the exact price in dollars (0.01 to 0.99 format)
- Wait for explicit approval - User must say "yes", "confirm", or similar
Trading Terminology
- Side: Use
bidto buy YES, useaskto sell YES - Price: Fixed-point dollar string (e.g., "0.5600" means 56 cents)
- Count: Fixed-point contract count (e.g., "10.00" means 10 contracts)
- Ticker: Market identifier (e.g., "HIGHNY-24JAN01-T60")
Never Invent Prices or Fills
- NEVER make up or estimate fill prices
- ALWAYS use the actual orderbook prices shown by
kalshi_get_orderbook - If the user wants market orders, explain they need to specify a limit price
- Show the current best bid/ask before any order
Demo vs Production
- Demo: https://external-api.demo.kalshi.co (for testing, fake money)
- Production: https://external-api.kalshi.com (real money)
- When testing the plugin, prefer using the demo environment
- Make sure the user knows which environment they're using
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.
- 2mo ago First seen · 88 lines · 0 tokens per session scan A 4e00eab48616
kalshi-trading is a skill published in the GitHub repository evan-thedev/kalshi (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 883 tokens. 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.
kalshi-trading compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kalshi-tradingevan-thedev/kalshi | Skill | 0 | 2mo ago | MIT | A | 0 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | today | MIT | A | 39 | Claude Code, Codex |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | today | MIT | A | 28 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 4d ago | MIT | A | 110 | Claude Code |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | today | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 271 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 4d ago | GPL-2.0 | A | 292 | Codex |