What is prompt-eval-debug?

A prompt-testing workflow that checks a prompt against a small set of normal, unusual, and boundary cases.

Use it to test a pasted prompt, diagnose failures, and choose the smallest next change. Results are run and scored manually.

It helps identify why a prompt fails before changing it, so you avoid replacing working instructions unnecessarily.

prompt-eval-debug — Command for Claude Code and Cursor by emaraschio

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/emaraschio/cursor-commands

Made for: Claude Code, Cursor.

Or install cursor-commands, the plugin that ships this one along with the rest of its 44 skills, 43 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/emaraschio/cursor-commands/prompt-eval-debug/github.svg)](https://agentmods.dev/commands/emaraschio/cursor-commands/prompt-eval-debug)

Your own site

<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/prompt-eval-debug"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/prompt-eval-debug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/prompt-eval-debug"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/prompt-eval-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 664 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00664
Opus 5.5	$0.00012	$0.00266
Sonnet 5.5	$0.00006	$0.00133
Haiku 4.5	$0.00003	$0.00066

Measured 1mo ago against content hash e6cd993ee5c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prompt-eval-debug 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 1mo 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.

.cursor/commands/prompt-eval-debug.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Improve a pasted prompt by designing a tiny eval suite, diagnosing failures, and proposing the smallest next change, without rewriting blindly. Full workflow: .cursor/skill-contracts/prompt-eval-debug/SKILL.md (user install: ~/.cursor/skill-contracts/prompt-eval-debug/SKILL.md).

Defaults

Setting	Default
Eval suite	1 control (C0) + 3 edge (E1 to E3) + 1 capability-boundary (B1)
Prompt change	Smallest next change only (no full rewrite in v1)
Scoring	User runs cases manually; skill does not claim CI or automated scores
Examples	Generic names only (`service-a`, `task-handler`)

Steps

Read .cursor/skill-contracts/prompt-eval-debug/SKILL.md for the full agent contract; if that file is missing, read ~/.cursor/skill-contracts/prompt-eval-debug/SKILL.md.
Execute phases in order (Intake → Tiny eval suite → Run guidance → Diagnosis → Smallest next change → Deliver).
Report suite table, diagnoses, and one smallest next change in chat.

Anti-patterns

Do not rewrite blindly. Trigger: the user asks to rewrite the whole prompt and skip the eval work. Wrong: replacing the entire prompt in one shot with no suite or diagnosis. Correct: produce the tiny eval suite and the smallest next change first, and rewrite fully only after explicit request. Reason: a blind rewrite discards what worked and hides why the prompt failed.
Keep the capability-boundary case. Trigger: building the five-case suite. Wrong: dropping B1 or expecting the model to succeed without the tools it needs. Correct: include a capability-boundary case that expects escalate, ask, or refuse, and diagnose missing tool or capability when relevant. Reason: instructions are not capabilities, and skipping B1 hides hallucinated success.
Do not claim catalog CI scored the suite. Trigger: reporting suite outcomes. Wrong: stating automated pass/fail scores the user never ran. Correct: present the suite and ask the user to run it, reporting only results they confirm. Reason: this skill does not execute the catalog CI, so asserting scores would misrepresent what was verified.

Read the full file on GitHub · 45 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.

1mo ago First seen · 45 lines · 31 tokens per session scan A e6cd993ee5c1

Subscribe to this mod's changes

prompt-eval-debug is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 16d ago), licensed MIT. It adds 31 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 5.5. 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.

Data and AI Prompting Testing agent-skills ai-agents cursor cursor-ide developer-tools dotfiles

test-prompt

Test an AI prompt against multiple scenarios to verify consistent, quality output.

rohitg00/awesome-claude-code-toolkit · 18 tokens

ai-feature-eval-harness

Design an eval plan for a product AI feature: success criteria, a held-out labeled dataset, per-criterion grading (code-based, then LLM-based), and a pass threshold. Use when a task ships or changes a feature with non-deterministic model output (classification, extraction, summarization, ranking, agent action) needing…

Mozurok/fhorja.dev · 0 tokens

prompt-eval-debug