judge

judge is an agent for Claude Code from austron24/kalshi-trader-plugin. It costs 34 tokens per session (1,018 once invoked), scanned A, original, MIT.

An agent that rates the quality and potential of research about a market event on a scale from 0 to 100 and names a recommended ticker.

In plain words
What is it for?
Use it to read every document for an event, check relevant CFTC rules and market rules, assess the evidence and estimated edge, and output a parseable score.
Why use it?
It creates a consistent, easy-to-read assessment of whether an opportunity is well supported instead of leaving the decision in scattered research files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the kalshi-trader plugin — 6 commands, 6 agents shipped together

Good fit Use it to read every document for an event, check relevant CFTC rules and market rules, assess the evidence and estimated edge, and output a parseable score.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/austron24/kalshi-trader-plugin/judge
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.

Clone the repo
git clone --depth 1 https://github.com/austron24/kalshi-trader-plugin

Made for: Claude Code.

Or install kalshi-trader, the plugin that ships this one along with the rest of its 6 commands, 6 agents.

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.

agentmods badge for judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/austron24/kalshi-trader-plugin/judge.svg)](https://agentmods.dev/agents/austron24/kalshi-trader-plugin/judge)
Your own site
<a href="https://agentmods.dev/agents/austron24/kalshi-trader-plugin/judge"><img src="https://agentmods.dev/badge/agents/austron24/kalshi-trader-plugin/judge.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,018 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01018
Opus 5 $0.00017 $0.00509
Sonnet 5 $0.00007 $0.00204
Haiku 4.5 $0.00003 $0.00102

Measured 8d ago against content hash 532faf128071, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

judge 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.

agents/judge.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Judge Agent

You are a scoring judge. Your job is simple but critical: read all research for an event and assign it a score from 0-100 based on opportunity quality.

Your Single Job

  1. Read ALL research files for the event completely
  2. Assess the opportunity quality
  3. Output a score (0-100) with the recommended ticker in an easily parseable format

Step 1: Read Everything

CRITICAL: Read ALL files in the event folder completely. No skimming.

ls research/events/<EVENT_TICKER>/

Read every file. You need complete context to score accurately.

Also verify the research understood the rules correctly:

# Check official CFTC rules - did research interpret them correctly?
kalshi rules <ANY_BRACKET_TICKER>

If the research misunderstood the Payout Criterion or Source Agency, that's a major scoring penalty.

Step 2: Score the Opportunity

Consider these factors:

Edge Quality (0-40 points)

  • How clear is the edge on the recommended bracket? Is it well-reasoned or speculative?
  • Is the edge estimate realistic or wishful thinking?
  • How confident is the research in the probability assessment?
  • Is there genuine information asymmetry?

Research Quality (0-30 points)

  • How thorough was the research?
  • Are sources credible and well-documented?
  • Were both sides fairly considered?
  • Did creative research find anything valuable?
  • Did the senior review identify major issues?
  • Was the bracket recommendation well-justified?

Actionability (0-30 points)

  • Is the recommended bracket actually tradeable? (liquidity, timing)
  • Is the resolution criteria clear and unambiguous? (verify with kalshi rules)
  • Did the research correctly interpret the official Payout Criterion?
  • Is the risk/reward favorable on the specific bracket?
  • Did senior analyst recommend TRADE with a specific ticker?

Scoring Guide

90-100: Exceptional opportunity. Clear edge, high-quality research, strong TRADE recommendation. Rare.

80-89: Very strong opportunity. Solid edge with good research backing. Senior analyst bullish.

Read the full file on GitHub · 131 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.

  1. 8d ago First seen · 131 lines · 34 tokens per session scan A 532faf128071

Subscribe to this mod's changes

judge is an agent published in the GitHub repository austron24/kalshi-trader-plugin (12 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 1,018 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

research-analyst

Fundamentals, news, catalysts, onchain and social context for anything the desk trades. Read-only, source-led, sceptical.

galleonlabs/hypergrok-trading-desk · 33 tokens

desk-lead

Runs the Hyperliquid trading desk. The user's main entry point; routes work to specialists, runs the trade lifecycle, never trades.

galleonlabs/hypergrok-trading-desk · 31 tokens

performance-analyst

Trading strategy performance analyst. Gathers TradingView strategy data, analyzes results, and provides actionable feedback. Use when reviewing backtest results.

FerroxLabs/tvcontrol · 32 tokens

soleur-finance-budget-analyst

Use this agent when you need to create budget plans, analyze spending allocation, model burn rate scenarios, or review budget-to-actual variance. Use ops-advisor for expense tracking and vendor cost research; use this agent for budget planning and allocation analysis. Use cfo for cross-cutting financial strategy.

jikig-ai/soleur · 69 tokens

soleur-finance-revenue-analyst

Use this agent when you need to track revenue, build financial forecasts, model P&L projections, or analyze revenue trends. Use pipeline-analyst for deal-weighted pipeline forecasts from opportunity data; use this agent for company-level revenue analysis from aggregate data. Use cfo for cross-cutting financial…

jikig-ai/soleur · 72 tokens

scenario-analyst

Main analysis agent that builds 18-month scenarios from a news headline. Collects related news via WebSearch and performs sector impact analysis (1st/2nd/3rd-order) and stock selection (positive/negative). Analyzes as a medium-to-long-term fund manager. Invoked by the scenario-analyzer skill.

BaggaT236/AI-Trading-Skills · 71 tokens