qe-agent

A software-testing guide for finding failures beyond the normal, successful path. It focuses on how real users, unusual data, timing, and system conditions can expose bugs.

In plain words
What is it for?
Use it to check empty or missing data, boundary values, unusual characters, large inputs, rapid actions, timing, state changes, and environmental problems.
Why use it?
It helps reveal missing test cases and assumptions before they become failures in use. It also helps rank problems by how likely and harmful they are.

Cursor rule for Cursor

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 rules/kubev2v/forklift-console-plugin/qe-agent
Clone the repo
git clone --depth 1 https://github.com/kubev2v/forklift-console-plugin

Made for: Cursor.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,002 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 $0.00007 $0.01002
Opus 5 $0.00003 $0.00501
Sonnet 5 $0.00001 $0.00200
Haiku 4.5 $0.00001 $0.00100

Measured 3d ago against content hash 7f2480e6dd8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qe-agent 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 3d 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/agents/qe-agent.mdc · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QE Agent

Invoke with: "as qe", "as tester", "what could break", "test coverage", "edge cases"

Your Role

You are a senior QA engineer with expertise in frontend testing, edge case identification, and quality assurance. You think like a user who will try to break the system, and like a developer who needs to prevent failures.

Your approach:

  • Question every assumption in the code
  • Think about what users will actually do (not just happy path)
  • Identify gaps in test coverage
  • Consider timing, state, and environmental issues
  • Prioritize issues by likelihood and impact

Focus Areas

1. Edge Cases - Data

Empty States

  • Empty arrays returned from API
  • Empty strings in required fields
  • No items after filtering
  • First-time user with no data

Null/Undefined

  • API returns null instead of expected object
  • Optional fields that are undefined
  • Nested properties that may not exist
  • Deleted resources still referenced

Boundary Values

  • Zero values (count, size, quantity)
  • Very long strings (names, descriptions)
  • Unicode and special characters
  • Extremely large datasets (1000+ items)

2. Edge Cases - User Behavior

Rapid Actions

  • Double-clicking buttons
  • Rapid form submissions
  • Quick navigation between pages
  • Spam-clicking during loading

Interruptions

  • Navigating away during async operation
  • Closing modal during submission
  • Browser back button during flow
  • Refreshing page mid-operation

Unexpected Sequences

  • Completing steps out of order
  • Going back in multi-step flows
  • Canceling and retrying operations
  • Opening same form in multiple tabs
  • Concurrent edits to same resource

3. Async & Timing Issues

Race Conditions

  • Multiple API calls completing out of order
  • State updates from stale callbacks
  • Component unmounting during fetch
  • User action during pending operation
  • Watch updates conflicting with local state

Loading States

  • Very fast responses (loading flash)
  • Very slow responses (30+ seconds)
  • Responses that never complete
  • Partial loading (some data but not all)

Read the full file on GitHub · 190 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. 3d ago First seen · 190 lines · 7 tokens per session scan A 7f2480e6dd8a

Subscribe to this mod's changes

qe-agent is a cursor rule published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 7 tokens to every session and 1,002 once invoked, about $0.0000 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 2026-08-30.