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 agentmods add commands/topprismdata/cultivating-ml-agent/gradegit clone --depth 1 https://github.com/topprismdata/cultivating-ml-agentWrote 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/topprismdata/cultivating-ml-agent/grade)<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>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 | $0.00012 | $0.00288 |
| Opus 5 | $0.00006 | $0.00144 |
| Sonnet 5 | $0.00002 | $0.00058 |
| Haiku 4.5 | $0.00001 | $0.00029 |
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.
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
- Confirms
submissions/<competition>/submission.csvexists - Validates format (header, row count, no empty cells)
- Runs
bash .claude/hooks/grade_submission.sh <slug>for full validation - If mlebench is installed, runs
mlebench gradeand reports score - Emits PASS / WARN / FAIL verdict
- 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)
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.
- 5d ago First seen · 42 lines · 12 tokens per session scan A 94eee96e46e8
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.
Other commands, from other repositories
harness
Take one harness from "wired" to "the agent is visibly smarter for it".
tokenless-stats
Show Tokenless compression statistics.
agent-brain-graph
Search using GraphRAG for relationship and dependency queries.
migrate_plans
Automatically review all plans in .cursor/plans/, determine relevance, and migrate relevant ones to docs/proposals/ for future consideration.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
scorecard
Run a repeatable weekly health check. Score Brain OS out of 100. Compare week-over-week.