evaluate

evaluate is a command for Claude Code from isabela-valonni/prompt-evaluator. It costs 13 tokens per session (184 once invoked), scanned A, original, MIT.

A prompt-review command that scores your latest request and gives one focused improvement. A prompt is the instruction you give to an AI assistant.

In plain words
What is it for?
It reviews the current prompt, optionally reads a saved prompting profile, returns a fixed four-line feedback format, and updates that profile.
Why use it?
It turns vague feedback into one concrete change and records recurring patterns so later advice can become more specific.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the prompt-evaluator plugin — 1 command shipped together

Good fit It reviews the current prompt, optionally reads a saved prompting profile, returns a fixed four-line feedback format, and updates that profile.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/isabela-valonni/prompt-evaluator/evaluate
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/isabela-valonni/prompt-evaluator

Made for: Claude Code.

Or install prompt-evaluator, the plugin that ships this one along with the rest of its 1 command.

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/isabela-valonni/prompt-evaluator/evaluate.svg)](https://agentmods.dev/commands/isabela-valonni/prompt-evaluator/evaluate)
Your own site
<a href="https://agentmods.dev/commands/isabela-valonni/prompt-evaluator/evaluate"><img src="https://agentmods.dev/badge/commands/isabela-valonni/prompt-evaluator/evaluate.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 184 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 $0.00013 $0.00184
Opus 5 $0.00006 $0.00092
Sonnet 5 $0.00003 $0.00037
Haiku 4.5 $0.00001 $0.00018

Measured 7d ago against content hash f876c9bd6a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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/evaluate.md · 19 lines

What it actually says

Evaluate the user's most recent prompt for prompting quality. If the user pasted text after the command, evaluate that text instead.

First, if user_prompting_profile.md exists in the working folder, read it so the evaluation reflects the user's recurring patterns rather than starting fresh.

Respond using exactly this format, rendered as a four-line blockquote:

PROMPTING FEEDBACK X / 10 — one-line rationale What worked: one specific observation To sharpen: one concrete suggestion, with an example

Keep it tight: one score, one strength, one fix. No paragraphs of advice, no theory.

After evaluating, update user_prompting_profile.md with the new observation and a "Pattern to watch" line linking this evaluation to earlier ones. Create the file if it does not exist.

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. 7d ago First seen · 19 lines · 13 tokens per session scan A f876c9bd6a6c

Subscribe to this mod's changes

evaluate is a command published in the GitHub repository isabela-valonni/prompt-evaluator (5 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 184 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.