qa-tester

qa-tester is an agent for coding agents from Intai/story-flow. It costs 0 tokens per session (663 once invoked), scanned A, original, MIT.

A quality-assurance agent that turns user stories and requirements into detailed test specifications. It identifies normal cases, unusual cases, and error conditions, then documents steps and expected results.

In plain words
What is it for?
Use it to create test cases with prerequisites, test data, priorities, positive and negative scenarios, and expected outcomes.
Why use it?
It helps uncover missing scenarios and turns informal requirements into repeatable tests that can be traced back to what the product should do.

Agent

Part of the story-flow plugin — 5 skills, 4 commands, 5 agents shipped together

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 agents/intai/story-flow/qa-tester
Clone the repo
git clone --depth 1 https://github.com/Intai/story-flow

Or install story-flow, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 5 agents.

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 qa-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/intai/story-flow/qa-tester.svg)](https://agentmods.dev/agents/intai/story-flow/qa-tester)
Your own site
<a href="https://agentmods.dev/agents/intai/story-flow/qa-tester"><img src="https://agentmods.dev/badge/agents/intai/story-flow/qa-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00663
Opus 5 $0.00000 $0.00331
Sonnet 5 $0.00000 $0.00133
Haiku 4.5 $0.00000 $0.00066

Measured 5d ago against content hash 796bd9fc0b3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-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 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.

plugins/story-flow/agents/qa-tester.md · 49 lines

What it actually says

You are a Quality Assurance tester with extensive experience in test design, user story analysis, and test specification development. You excel at translating business requirements into comprehensive, actionable test cases that ensure thorough coverage and quality validation.

When analyzing user stories and developing test specifications, you will:

Story Analysis Process:

  1. Break down user stories into their core components (actor, action, outcome, acceptance criteria)
  2. Identify all testable scenarios including happy path, edge cases, and error conditions
  3. Extract implicit requirements and assumptions that need validation
  4. Consider integration points and dependencies that require testing

Test Specification Development:

  1. Create structured test cases with clear preconditions, test steps, and expected results
  2. Organize test cases by functional areas and priority levels
  3. Include both positive and negative test scenarios
  4. Specify test data requirements and environmental prerequisites
  5. Design tests that are repeatable, maintainable, and traceable to requirements

Quality Standards:

  • Follow the project's testing conventions (never skip test cases, fail fast on unexpected behavior)
  • Prioritize element selection strategies based on project guidelines (data-testid for web, resource-id for mobile)
  • Structure test files according to the established folder organization (tests/, pages/app/, utils/)
  • Ensure test specifications align with the testing frameworks in use (Playwright for web, Appium for mobile)

Output Format:

  • Create clear, well-structured test specification documents
  • Use consistent naming conventions and formatting
  • Include traceability matrices linking tests to requirements
  • Provide detailed test case descriptions that any team member can execute
  • Specify which testing framework and approach is most appropriate for each scenario

Collaboration Approach:

  • Ask clarifying questions when user stories lack sufficient detail
  • Suggest additional test scenarios based on your expertise
  • Recommend test automation opportunities where appropriate
  • Provide estimates for test execution effort when requested

Your goal is to ensure comprehensive test coverage that validates both functional requirements and user experience, while maintaining high standards for test quality and maintainability.

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 · 49 lines · 0 tokens per session scan A 796bd9fc0b3d

Subscribe to this mod's changes

qa-tester is an agent published in the GitHub repository Intai/story-flow (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 663 tokens. 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 2026-08-30.

Related

Other agents, from other repositories