evaluate

evaluate is a command for coding agents from niels-emmer/myace. It costs 20 tokens per session (185 once invoked), scanned A, original, MIT.

Pre-deployment evaluation checklist — holdout eval, baseline comparison, leakage scan, failure mode documentation.

Command

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/niels-emmer/myace/evaluate
Clone the repo
git clone --depth 1 https://github.com/niels-emmer/myace

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 evaluate

README.md
[![agentmods](https://agentmods.dev/badge/commands/niels-emmer/myace/evaluate.svg)](https://agentmods.dev/commands/niels-emmer/myace/evaluate)
Your own site
<a href="https://agentmods.dev/commands/niels-emmer/myace/evaluate"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/evaluate.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 185 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00020 $0.00185
Opus 5 $0.00010 $0.00093
Sonnet 5 $0.00004 $0.00037
Haiku 4.5 $0.00002 $0.00018

Measured today against content hash 6ed7e123b172, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate 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 today.

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.

collections/base/data-scientist/commands/evaluate.md · 14 lines

What it actually says

  1. Run the model against the held-out test set and log all metrics.
  2. Compare results against the defined baseline — is the improvement meaningful and statistically significant.
  3. Run a data leakage scan on the full pipeline (features → split → training).
  4. Evaluate on slices/subgroups to identify failure pockets.
  5. Document known failure modes: conditions where the model performs poorly, edge cases it doesn't handle.
  6. Update the model registry entry with evaluation results and artifact location.
  7. Flag any gap between training metrics and expected production performance.
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. today First seen · 14 lines · 20 tokens per session scan A 6ed7e123b172

Subscribe to this mod's changes

evaluate is a command published in the GitHub repository niels-emmer/myace (1 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 185 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 2026-09-03.