score

score is a command for coding agents from austron24/kalshi-trader-plugin. It costs 11 tokens per session (1,436 once invoked), scanned A, original, MIT.

A command that scores researched events and ranks them as opportunities. It reads event research from the project and uses judge agents to produce a top-ten list.

In plain words
What is it for?
Use it after event research to score every researched event, compare results, identify the top ten, and choose which opportunities to take into a separate finalization step.
Why use it?
It turns a large set of researched events into a shorter ranked list, so the best opportunities are easier to review and finalize.

Command

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

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.

agentmods
npx agentmods add commands/austron24/kalshi-trader-plugin/score
Clone the repo
git clone --depth 1 https://github.com/austron24/kalshi-trader-plugin

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 score

README.md
[![agentmods](https://agentmods.dev/badge/commands/austron24/kalshi-trader-plugin/score.svg)](https://agentmods.dev/commands/austron24/kalshi-trader-plugin/score)
Your own site
<a href="https://agentmods.dev/commands/austron24/kalshi-trader-plugin/score"><img src="https://agentmods.dev/badge/commands/austron24/kalshi-trader-plugin/score.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00011 $0.01436
Opus 5 $0.00005 $0.00718
Sonnet 5 $0.00002 $0.00287
Haiku 4.5 $0.00001 $0.00144

Measured 5d ago against content hash eb0382c87ac8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

score 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 5d 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.

commands/score.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Event Scoring & Ranking

You are scoring all researched events to identify the top opportunities. Your job is to:

  1. Spawn parallel judge agents to score each event
  2. Collect all scores via bash
  3. Rank and return the top 10 opportunities
  4. Advise the user to take top events to a fresh session for /finalize

Phase 1: Identify Events to Score

List all events with research:

ls research/events/

Each folder is an event ticker that needs scoring.

Guard: If no events found:

No research found in `research/events/`. Run `/alpha` first to scan for opportunities and generate initial research.

Exit the command if no events exist.

Phase 2: Spawn Judge Agents

For each event, spawn a judge agent using the Task tool.

CRITICAL: Parallel Blocking Execution

To run agents in parallel (concurrent) but blocking (main agent waits for all to complete):

  1. Make ALL Task calls in a SINGLE message - This triggers parallel execution
  2. Do NOT use run_in_background - Omitting this makes calls blocking
  3. The main agent automatically waits for all agents to complete before continuing

For each agent:

  • subagent_type: "judge"
  • model: opus
  • prompt: (see below)

Example prompt for each agent:

Score Kalshi event [EVENT_TICKER].

**CRITICAL: Read ALL files in research/events/[EVENT_TICKER]/ completely. No skimming.**

Your job:
1. Read every research file for this event completely
2. Score the opportunity from 0-100 based on:
   - Edge Quality (0-40): How clear and realistic is the edge on the recommended bracket?
   - Research Quality (0-30): How thorough and credible?
   - Actionability (0-30): Is this tradeable? Did senior analyst recommend TRADE with a specific bracket?

3. Write score to: research/events/[EVENT_TICKER]/score.txt

**FORMAT IS CRITICAL:**
<SCORE>|<RECOMMENDED_TICKER>|<ONE_LINE_RATIONALE>

Example: `87|KXCPI-25DEC-T0.3|Strong edge on CPI, solid research, senior analyst recommends TRADE YES`

When done, confirm: files read, score assigned, score file path.

Read the full file on GitHub · 175 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. 5d ago First seen · 175 lines · 11 tokens per session scan A eb0382c87ac8

Subscribe to this mod's changes

score is a command published in the GitHub repository austron24/kalshi-trader-plugin (12 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 1,436 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.