A command that checks whether changes to an inline AI prompt still match the application's expected output contract. An output contract is the required set of fields, values, and types returned by a program.

Use it as a regression check for `/api/analyze` prompts, including required output fields, allowed enum values, variable mappings, and compatibility with the declared TypeScript types.

It catches prompt changes that could produce missing fields, invalid strategy values, or data that no longer matches the application's TypeScript types. It only runs the check when the relevant prompt has changed.

How ultra-ai-dle/frogger configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ultra-ai-dle/frogger. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ultra-ai-dle/frogger/develop/.claude/commands/prompt-diff.md

Clone the repo

git clone --depth 1 https://github.com/ultra-ai-dle/frogger

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ultra-ai-dle/frogger/prompt-diff/github.svg)](https://agentmods.dev/commands/ultra-ai-dle/frogger/prompt-diff)

Your own site

<a href="https://agentmods.dev/commands/ultra-ai-dle/frogger/prompt-diff"><img src="https://agentmods.dev/badge/commands/ultra-ai-dle/frogger/prompt-diff/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/ultra-ai-dle/frogger/prompt-diff"><img src="https://agentmods.dev/badge/commands/ultra-ai-dle/frogger/prompt-diff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 508 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	$0.00000	$0.00508
Opus 5.5	$0.00000	$0.00203
Sonnet 5.5	$0.00000	$0.00102
Haiku 4.5	$0.00000	$0.00051

Measured 27d ago against content hash 7f0ac136a9c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prompt-diff 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 27d 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.

.claude/commands/prompt-diff.md · 35 lines

What it actually says

/prompt-diff — AI 프롬프트 변경 회귀 테스트

목적

/api/analyze/route.ts 내 인라인 프롬프트 문자열을 수정한 후, 계약 조건이 여전히 만족되는지 정적으로 검증한다.

입력

$ARGUMENTS — (선택) 대상 엔드포인트 지정 (analyze). 미지정 시 analyze를 검사.

실행 절차

프롬프트 변경 감지:
- git diff로 /api/analyze/route.ts 내 인라인 프롬프트 변경을 확인한다.
- 변경이 없으면 "프롬프트 변경 없음 — 스킵" 으로 종료한다.
계약 조건 정적 검증 (프롬프트 텍스트 분석):

/api/analyze 계약:
- 출력에 algorithm, strategy, key_vars, var_mapping, display_name 필드를 요구하는 지시가 있는지
- var_mapping[].var_name이 "반드시 varTypes 키 중 하나"라는 제약이 프롬프트에 명시되어 있는지
- strategy가 GRID | LINEAR | GRID_LINEAR | GRAPH 중 하나로 제한되는 지시가 있는지
- linear_pivots 관련 지시가 있으면 pivot_mode enum 값이 타입과 일치하는지
타입 호환성 크로스체크:
- 프롬프트에서 요구하는 출력 스키마가 src/types/prova.ts의 AnalyzeMetadata, AnnotatedStep, AiErrorInfo 타입과 일치하는지 확인한다.
- 프롬프트에 새 필드를 추가했는데 타입 정의에 없으면 경고한다.
결과 보고:
- 각 계약 조건별 PASS/FAIL 표 형태로 출력한다.
- FAIL 항목은 프롬프트의 어느 부분이 문제인지 구체적으로 인용한다.

검증 체크리스트

analyze: 필수 출력 필드 5종 요구됨
analyze: var_mapping.var_name ∈ varTypes 제약 명시됨
analyze: strategy enum 값이 타입과 일치
프롬프트 출력 스키마 ⊆ prova.ts 타입 정의

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.

27d ago First seen · 35 lines · 0 tokens per session scan A 7f0ac136a9c9

Subscribe to this mod's changes

prompt-diff is a command published in the GitHub repository ultra-ai-dle/frogger (8 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 508 tokens. 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 2026-10-02.

Data and AI Prompting Testing ai algorithm-visualizer debugger javascript

frogger: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/prompt-diff — AI 프롬프트 변경 회귀 테스트

목적

입력

실행 절차

검증 체크리스트

What this file has done since we first saw it

Other commands, from other repositories

test-prompt

dados-distribuidos

caracterizar-prompt

promptfoo

prompt-eval-debug

prompt-tuner