grade

grade is a command for Claude Code from topprismdata/cultivating-ml-agent. It costs 12 tokens per session (288 once invoked), scanned A, original, MIT.

A command that checks a competition submission file before it is sent to a leaderboard. It verifies the file's structure and may run the competition's grading tool to report a pass, warning, or failure.

In plain words
What is it for?
Use it after generating or changing a CSV submission, when investigating a grading failure, or before uploading a competition result.
Why use it?
It catches missing rows, empty values, incorrect headers, and other submission problems before manual submission. It also keeps validation separate from the agent that created the file.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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/topprismdata/cultivating-ml-agent/grade
Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent

Made for: Claude Code.

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 grade

README.md
[![agentmods](https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/grade.svg)](https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/grade)
Your own site
<a href="https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/grade"><img src="https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/grade.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 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 5.1 $0.00012 $0.00288
Opus 5 $0.00006 $0.00144
Sonnet 5 $0.00002 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 5d ago against content hash 94eee96e46e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

grade 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.

ml-agent-code-template/.claude/commands/grade.md · 42 lines

What it actually says

/grade — Validate and Grade Submission

Run the Grader agent on submissions/<competition>/submission.csv.

Usage

/grade <competition-slug>

Example: /grade tps-may-2022

What This Does

  1. Confirms submissions/<competition>/submission.csv exists
  2. Validates format (header, row count, no empty cells)
  3. Runs bash .claude/hooks/grade_submission.sh <slug> for full validation
  4. If mlebench is installed, runs mlebench grade and reports score
  5. Emits PASS / WARN / FAIL verdict
  6. Suggests next steps

Team Pattern

This command invokes the Grader agent role, which is the read-only validator in the Builder/Grader team pattern. Builder produces the file; Grader validates it.

When To Use

  • After Builder agent finishes producing submission
  • Before manually submitting to leaderboard
  • After any change to the submission
  • When debugging a grade failure

Anti-Patterns

  • ❌ Don't run mlebench grade repeatedly on the same file (wastes quota)
  • ❌ Don't modify the submission from this command (Grader is read-only)
  • ❌ Don't ignore WARN (format OK but score below expectation)
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 · 42 lines · 12 tokens per session scan A 94eee96e46e8

Subscribe to this mod's changes

grade is a command published in the GitHub repository topprismdata/cultivating-ml-agent (4 stars, last pushed 8d ago), licensed MIT. It adds 12 tokens to every session and 288 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 2026-08-31.