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.
git clone --depth 1 https://github.com/austron24/kalshi-trader-pluginWrote 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/commands/austron24/kalshi-trader-plugin/positions)<a href="https://agentmods.dev/commands/austron24/kalshi-trader-plugin/positions"><img src="https://agentmods.dev/badge/commands/austron24/kalshi-trader-plugin/positions.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 5.1 | $0.00018 | $0.01598 |
| Opus 5 | $0.00009 | $0.00799 |
| Sonnet 5 | $0.00004 | $0.00320 |
| Haiku 4.5 | $0.00002 | $0.00160 |
Grade A, and why
positions 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 8d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Positions - Daily Position Review
This command reviews all open positions using parallel subagents. Each position is evaluated against its original thesis to determine whether to HOLD or SELL.
Run this daily to manage your portfolio actively.
Phase 1: Get Current Positions with P&L
First, get portfolio summary with unrealized P&L:
kalshi summary
This shows all positions with:
- Entry price (calculated from fills)
- Current price
- Unrealized P&L (both $ and %)
If there are no positions, inform the user and exit:
"No open positions to review. Run
/alphato find new opportunities or/finalizeto execute pending trades."
Phase 2: Verify Position Details
The summary command already provides most details. For additional context:
kalshi market <TICKER> # Shows your position + current bid/ask
kalshi trades <TICKER> --summary # Shows recent market activity
Phase 3: Verify Thesis Exists
For each position, check if we have a thesis document:
ls research/markets/<TICKER>/thesis.md
If thesis is missing:
- Note this as a problem position
- We cannot properly review a position without knowing why we entered
- Flag for manual review
Phase 4: Spawn Parallel Position Reviewers
For each position with a thesis, spawn a position-reviewer agent.
CRITICAL: Parallel Blocking Execution
To run agents in parallel (concurrent) but blocking (main agent waits for all to complete):
- Make ALL Task calls in a SINGLE message - This triggers parallel execution
- Do NOT use
run_in_background- Omitting this makes calls blocking - The main agent automatically waits for all agents to complete before continuing
For each agent:
- subagent_type: "position-reviewer"
- model: opus
- prompt: (see below)
Example prompt for each agent:
Review position for <TICKER>.
Position Details:
- Direction: YES/NO
- Contracts: X
- Entry Price: X¢ (from fills)
- Current Price: X¢ (from market)
- Unrealized P&L: +/-$X.XX
- Days held: X
Thesis file: research/markets/<TICKER>/thesis.md
(The thesis contains a Research Reference section with the event folder path)
Determine whether to HOLD or SELL this position.
If SELL: document the outcome in learnings.
Return your decision with reasoning.
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.
- 8d ago First seen · 244 lines · 18 tokens per session scan A 7d1cdeaa8337
positions is a command published in the GitHub repository austron24/kalshi-trader-plugin (12 stars, last pushed 8mo ago), licensed MIT. It adds 18 tokens to every session and 1,598 once invoked, about $0.0001 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 commands, from other repositories
gamma-markets
Access detailed market data, filter markets by various criteria, and build market discovery features.
data-activity
Access user trading activity, transaction history, and order events.
data-positions
Query user positions, portfolio holdings, and calculate P&L metrics.
gamma-events
Events are high-level prediction questions (e.g., "Who will win the 2024 Presidential Election?"). Series are collections of related events (e.g., "Elections 2024").
ws-market-channel
The market channel provides real-time updates for market data including orderbook changes, trades, and price updates.
clob-orders
Create, cancel, and manage orders on Polymarket's Central Limit Order Book.