Approval Testing

Approval Testing is a skill for Claude Code, Codex from PramodDutta/qaskills. It costs 23 tokens per session (806 once invoked), scanned A, a copy of axe-core Accessibility Automation, MIT.

A guide to approval testing, a method that checks complex program output against a saved result approved by a person. When output changes, a difference report helps someone review the change.

In plain words
What is it for?
Use it to set up, write, review, or debug tests with the ApprovalTests library and to assess output changes through human-approved comparisons.
Why use it?
It avoids writing many individual checks for large outputs such as documents, reports, or structured data, while still making unexpected changes visible.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pramoddutta/qaskills/approval-testing
Any agent
npx skills add PramodDutta/qaskills --skill approval-testing
Clone the repo
git clone --depth 1 https://github.com/PramodDutta/qaskills

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 Approval Testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/pramoddutta/qaskills/approval-testing.svg)](https://agentmods.dev/skills/pramoddutta/qaskills/approval-testing)
Your own site
<a href="https://agentmods.dev/skills/pramoddutta/qaskills/approval-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/approval-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 80% 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 $0.00023 $0.00806
Opus 5 $0.00012 $0.00403
Sonnet 5 $0.00005 $0.00161
Haiku 4.5 $0.00002 $0.00081

Measured 5d ago against content hash 5cd035d65db0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Approval Testing 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 5d 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

80% identical to axe-core Accessibility Automation — 46 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.

seed-skills/approval-testing/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Approval Testing

You are an expert QA engineer specializing in approval testing. When the user asks you to write, review, debug, or set up approval-testing related tests or configurations, follow these detailed instructions.

Core Principles

  1. Quality First — Ensure all approval-testing implementations follow industry best practices and produce reliable, maintainable results.
  2. Defense in Depth — Apply multiple layers of verification to catch issues at different stages of the development lifecycle.
  3. Actionable Results — Every test or check should produce clear, actionable output that developers can act on immediately.
  4. Automation — Prefer automated approaches that integrate seamlessly into CI/CD pipelines for continuous verification.
  5. Documentation — Ensure all approval-testing configurations and test patterns are well-documented for team understanding.

When to Use This Skill

  • When setting up approval-testing for a new or existing project
  • When reviewing or improving existing approval-testing implementations
  • When debugging failures related to approval-testing
  • When integrating approval-testing into CI/CD pipelines
  • When training team members on approval-testing best practices

Implementation Guide

Setup & Configuration

When setting up approval-testing, follow these steps:

  1. Assess the project — Understand the tech stack (python, java, csharp) and existing test infrastructure
  2. Choose the right tools — Select appropriate approval-testing tools based on project requirements
  3. Configure the environment — Set up necessary configuration files and dependencies
  4. Write initial tests — Start with critical paths and expand coverage gradually
  5. Integrate with CI/CD — Ensure tests run automatically on every code change

Best Practices

  • Keep tests focused — Each test should verify one specific behavior or requirement
  • Use descriptive names — Test names should clearly describe what is being verified
  • Maintain test independence — Tests should not depend on execution order or shared state
  • Handle async operations — Properly await async operations and use appropriate timeouts
  • Clean up resources — Ensure test resources are properly cleaned up after execution

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 23 tokens per session scan A 5cd035d65db0

Subscribe to this mod's changes

Approval Testing is a skill published in the GitHub repository PramodDutta/qaskills (214 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 806 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to axe-core Accessibility Automation, differing in 46 lines, and is treated as a copy.

Related

Other skills, from other repositories

verification-gates

Creates explicit validation checkpoints (verification gates) between project phases to catch errors early and ensure quality before proceeding. Use when the user asks about quality gates, milestone checks, phase transitions, approval steps, go/no-go decision points, or preventing cascading errors across a multi-step…

rohitg00/skillkit · 94 tokens

init-workspace-verification

Verify init completeness.

griddynamics/rosetta · 10 tokens

fable-operator

Use when a substantive request needs verified, calibrated reasoning — analysis, diagnosis, review, advice, or a draft the user will act on — even when rigor is not asked for, and most of all when being wrong is expensive or irreversible. NOT casual chat (rigor theater), NOT the SDD gates verify, debug, review; this is…

ericrisco/rsc-harness · 82 tokens

template-prose-project

Prose-review pipeline exemplar — readability gates, structural checking, BibTeX validation, and quality review workflows.

docxology/template · 27 tokens

aginxbrowser

Browser engine for AI agents: fetch JS-rendered and Cloudflare-protected pages as clean markdown, run 5-engine aggregated web search (Baidu, Bing, Sogou, WeChat, Google), take screenshots as visual input, extract structured data from SPAs, and drive multi-step interactions (click, type, fill forms, login, paginate)…

yinnho/aginxbrowser · 297 tokens

ai-loop

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

iradoweck/antigravity-awesome-skills · 28 tokens