prompt-regression-tester

prompt-regression-tester is a skill for Claude Code, Codex from patricio0312rev/skillset. It costs 52 tokens per session (1,381 once invoked), scanned A, a copy of prompt-regression-tester, MIT.

A test tool that runs old and new versions of a prompt against the same test cases and compares the results. A prompt is the instruction given to an AI model.

In plain words
What is it for?
Use it to compare prompt versions, run repeatable test cases, summarize differences, measure improvements and regressions, and suggest fixes for breakages.
Why use it?
It helps reveal when a prompt change improves one answer but breaks another, before the change reaches users.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare prompt versions, run repeatable test cases, summarize differences, measure improvements and regressions, and suggest fixes for breakages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patricio0312rev/skillset/prompt-regression-tester
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.

Any agent
npx skills add patricio0312rev/skillset --skill prompt-regression-tester
Clone the repo
git clone --depth 1 https://github.com/patricio0312rev/skillset

Made for: Claude Code, Codex.

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 prompt-regression-tester

README.md
[![agentmods](https://agentmods.dev/badge/skills/patricio0312rev/skillset/prompt-regression-tester/github.svg)](https://agentmods.dev/skills/patricio0312rev/skillset/prompt-regression-tester)
Your own site
<a href="https://agentmods.dev/skills/patricio0312rev/skillset/prompt-regression-tester"><img src="https://agentmods.dev/badge/skills/patricio0312rev/skillset/prompt-regression-tester/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.

agentmods 80×15 button for prompt-regression-tester

Your own site · 80×15
<a href="https://agentmods.dev/skills/patricio0312rev/skillset/prompt-regression-tester"><img src="https://agentmods.dev/badge/skills/patricio0312rev/skillset/prompt-regression-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,381 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 100% copy Near-identical to another mod 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 $0.00052 $0.01381
Opus 5 $0.00026 $0.00691
Sonnet 5 $0.00010 $0.00276
Haiku 4.5 $0.00005 $0.00138

Measured 12d ago against content hash 718287a23607, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prompt-regression-tester 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 12d 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.

Origin

This is a copy

100% identical to prompt-regression-tester — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

templates/ai-engineering/prompt-regression-tester/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Regression Tester

Systematically test prompt changes to prevent regressions.

Test Case Format

{
  "test_cases": [
    {
      "id": "test_001",
      "input": "Summarize this article",
      "context": "Article text here...",
      "expected_behavior": "Concise 2-3 sentence summary",
      "baseline_output": "Output from v1.0 prompt",
      "must_include": ["main point", "conclusion"],
      "must_not_include": ["opinion", "speculation"]
    }
  ]
}

Comparison Framework

def compare_prompts(old_prompt, new_prompt, test_cases):
    results = {
        "test_cases": [],
        "summary": {
            "total": len(test_cases),
            "improvements": 0,
            "regressions": 0,
            "unchanged": 0,
        },
        "breakages": []
    }

    for test in test_cases:
        old_output = llm(old_prompt.format(**test))
        new_output = llm(new_prompt.format(**test))

        comparison = {
            "test_id": test["id"],
            "old_output": old_output,
            "new_output": new_output,
            "diff": compute_diff(old_output, new_output),
            "scores": {
                "old": score_output(old_output, test),
                "new": score_output(new_output, test),
            },
            "verdict": classify_change(old_output, new_output, test)
        }

        results["test_cases"].append(comparison)
        results["summary"][comparison["verdict"]] += 1

        if comparison["verdict"] == "regressions":
            results["breakages"].append(analyze_breakage(comparison, test))

    return results

Stability Metrics

def calculate_stability_metrics(results):
    return {
        "output_stability": measure_output_consistency(results),
        "format_stability": check_format_preservation(results),
        "constraint_adherence": check_constraints(results),
        "behavioral_consistency": measure_behavior_delta(results),
    }

def measure_output_consistency(results):
    """How similar are outputs between versions?"""
    similarities = []
    for result in results["test_cases"]:
        sim = semantic_similarity(
            result["old_output"],
            result["new_output"]
        )
        similarities.append(sim)
    return sum(similarities) / len(similarities)

Read the full file on GitHub · 217 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.

  1. 12d ago First seen · 217 lines · 52 tokens per session scan A 718287a23607

Subscribe to this mod's changes

prompt-regression-tester is a skill published in the GitHub repository patricio0312rev/skillset (6 stars, last pushed 8mo ago), licensed MIT. It adds 52 tokens to every session and 1,381 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to prompt-regression-tester, differing in 0 lines, and is treated as a copy.