03-skill-testcases

03-skill-testcases is a cursor rule for Cursor from vlad-ryzhkov/ai-context-engineering-for-qa. It costs 168 tokens per session, scanned A, original, Unlicense.

A test-scenario matrix is a table of cases used to check an API against its specification. This procedure generates the matrix for isolated API testing.

In plain words
What is it for?
It is for creating test scenarios from an API specification, including the cases an isolated API test should cover.
Why use it?
It helps turn an API specification into explicit checks instead of relying on ad hoc testing.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths.

Good fit It is for creating test scenarios from an API specification, including the cases an isolated API test should cover.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/vlad-ryzhkov/ai-context-engineering-for-qa/03-skill-testcases
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/vlad-ryzhkov/ai-context-engineering-for-qa

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 03-skill-testcases

README.md
[![agentmods](https://agentmods.dev/badge/rules/vlad-ryzhkov/ai-context-engineering-for-qa/03-skill-testcases.svg)](https://agentmods.dev/rules/vlad-ryzhkov/ai-context-engineering-for-qa/03-skill-testcases)
Your own site
<a href="https://agentmods.dev/rules/vlad-ryzhkov/ai-context-engineering-for-qa/03-skill-testcases"><img src="https://agentmods.dev/badge/rules/vlad-ryzhkov/ai-context-engineering-for-qa/03-skill-testcases.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 This file is loaded in full into every session.
When invoked 168 The same file — it is already loaded in full.
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 $0.00168 $0.00168
Opus 5 $0.00084 $0.00084
Sonnet 5 $0.00034 $0.00034
Haiku 4.5 $0.00017 $0.00017

Measured 8d ago against content hash 32ce4d238379, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

03-skill-testcases 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.

.cursor/rules/03-skill-testcases.mdc · 18 lines

What it actually says

SKILL: TEST CASES

TRIGGER

User explicitly types /api-isolated-tests or asks to generate a test scenarios matrix from an API specification.

EXECUTION INSTRUCTIONS

DO NOT guess the procedure and DO NOT output anything yet. To perform this skill, you MUST dynamically read the instructions using your file-reading capabilities.

  1. First, read the core agent context: .claude/qa_agent.md
  2. Second, read the specific skill protocol: .claude/skills/api-isolated-tests/SKILL.md
  3. Execute based STRICTLY on the logic and output format defined in those files.
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 · 18 lines · 168 tokens per session scan A 32ce4d238379

Subscribe to this mod's changes

03-skill-testcases is a cursor rule published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed 1mo ago), licensed Unlicense. It adds 168 tokens to every session, about $0.0008 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 2026-08-31.