prompt-regression-suite

prompt-regression-suite is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 97 tokens per session (1,184 once invoked), scanned A, original, MIT.

A regression test suite for an AI feature. It stores representative inputs and checks whether prompt, model, or context changes cause responses that previously worked to fail.

In plain words
What is it for?
It helps create golden test cases, choose scoring methods, set continuous-integration checks, and investigate flaky tests versus real regressions.
Why use it?
It turns model and prompt changes into testable changes, helping teams catch quality regressions before release.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit It helps create golden test cases, choose scoring methods, set continuous-integration checks, and investigate flaky tests versus real regressions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/prompt-regression-suite
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

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/mohitagw15856/pm-claude-skills

Made for: Cursor.

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-suite

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/prompt-regression-suite/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/prompt-regression-suite)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/prompt-regression-suite"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/prompt-regression-suite/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-suite

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/prompt-regression-suite"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/prompt-regression-suite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,184 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 $0.00097 $0.01184
Opus 5 $0.00048 $0.00592
Sonnet 5 $0.00019 $0.00237
Haiku 4.5 $0.00010 $0.00118

Measured 8d ago against content hash 191aa6958ee6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-regression-suite 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 8d 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.

exports/cursor/pm-agentops/prompt-regression-suite/prompt-regression-suite.mdc · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Regression Suite Skill

Every prompt tweak, model upgrade, and context change is a deploy. This skill designs the suite that runs on each one and answers a single question: did anything that used to work stop working?

What This Skill Produces

  • A golden case set: curated inputs with per-case pass criteria
  • Scoring methods per case class (exact, rubric-judge, property checks)
  • CI gate thresholds — what blocks a merge vs. what warns
  • A failure triage protocol — flaky vs. regressed vs. golden-set-wrong

Required Inputs

Ask for (if not already provided):

  • The feature and its contract — what the LLM step receives and must produce
  • What has broken before (or nearly) — past incidents seed the best cases
  • Real traffic examples — 10-20 representative inputs, including ugly ones
  • What triggers a run — prompt edits, model bumps, retrieval changes, all of the above?

Building the Golden Set

Compose the set from four deliberate classes — not a random sample:

Class Purpose Share
Core paths The 5-10 inputs that represent most real traffic ~40%
Past failures Every input that caused a bug, complaint, or incident — permanently ~25%
Edge & adversarial Empty/huge inputs, wrong language, injection attempts, off-topic ~25%
Canaries Cases pinned to behaviours you never want to change (refusals, format, tone) ~10%

Keep it small enough to run on every change (30-80 cases beats 500 nobody runs). Version it in git next to the prompt.

Scoring Per Case

Choose the cheapest check that catches the regression:

  1. Exact / structural — JSON parses, required fields present, enum values legal. Free and deterministic; use wherever the contract is structural.
  2. Property checks — output contains/never-contains X, length bounds, citation count. Deterministic proxies for quality.
  3. LLM-as-judge with a rubric — only where judgement is unavoidable. Pin the judge model + rubric version, score against the baseline output, and spot-check judge agreement with a human on ~20 cases before trusting it.

Read the full file on GitHub · 93 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. 8d ago First seen · 93 lines · 97 tokens per session scan A 191aa6958ee6

Subscribe to this mod's changes

prompt-regression-suite is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 1,184 once invoked, about $0.0005 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.