prompt-regression-gate

prompt-regression-gate is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 29 tokens per session (307 once invoked), scanned A, original, MIT.

A review process for comparing two AI prompts on the same fixed evaluation set. It records the models and settings, measures important cases, and applies release thresholds agreed in advance.

In plain words
What is it for?
Run baseline and candidate prompts on equivalent cases, repeat stochastic runs when needed, review subjective outputs, and report failures, uncertainty, sample size, and rollback instructions.
Why use it?
A new prompt may improve average results while making refusals, costly mistakes, or specific user groups worse. Paired evaluation exposes those regressions before release.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the mas-ai-workflows plugin — 10 skills shipped together

Good fit Run baseline and candidate prompts on equivalent cases, repeat stochastic runs when needed, review subjective outputs, and report failures, uncertainty, sample size, and rollback instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/prompt-regression-gate
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 alivirgo/Major-AI-Skills --skill prompt-regression-gate
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install mas-ai-workflows, the plugin that ships this one along with the rest of its 10 skills.

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-gate

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/prompt-regression-gate"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/prompt-regression-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 307 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 $0.00029 $0.00307
Opus 5 $0.00015 $0.00153
Sonnet 5 $0.00006 $0.00061
Haiku 4.5 $0.00003 $0.00031

Measured today against content hash b66dcbe3b575, 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-gate 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 today.

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.

plugins/mas-ai-workflows/skills/prompt-regression-gate/SKILL.md · 35 lines

What it actually says

Prompt Regression Gate

Scope

Capture baseline and candidate prompts, model identifiers, tool schemas, retrieval revision, and generation settings. Agree on acceptance thresholds before running the comparison. Reuse a held-out evaluation set rather than tuning against final test failures.

Procedure

Run paired cases with equivalent context. If outputs are stochastic, repeat cases enough to expose variability within the agreed budget. Record missing runs and provider errors rather than treating them as ordinary wrong answers.

Checks

Use deterministic assertions for structured tasks and rubric-based review for subjective ones. Blind human reviewers to candidate identity where practical. Never use the candidate model's self-confidence as the sole quality metric.

Failure Handling

Compare aggregate results and important slices, including refusals, ambiguous requests, and high-cost mistakes. Report uncertainty and sample size; a small average gain must not hide a critical regression.

Deliverable

Deliver a go/no-go recommendation tied to predefined thresholds, failing examples, and rollback instructions. Without executed runs, provide the gate configuration and mark the result untested.

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. today First seen · 35 lines · 29 tokens per session scan A b66dcbe3b575

Subscribe to this mod's changes

prompt-regression-gate is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 307 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 2026-09-12.