agentiqa-test

A web-app testing tool that uses the Agentiqa command-line program to run saved checklists or explore an app for bugs. It verifies each step of a fixed test plan or investigates without predefined steps.

In plain words
What is it for?
Use it to re-check known workflows, such as logging in or confirming a cart total, or to ask an AI testing agent to explore a web app and look for bugs.
Why use it?
It helps check whether a web app still works and find problems without manually repeating every action. The two modes separate repeatable regression checks from open-ended bug hunting.

Skill for Claude CodeCodex

Part of the agentiqa plugin — 2 skills, 1 hook 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 skills/agentiqa/agentiqa-plugin/agentiqa-test
Any agent
npx skills add Agentiqa/agentiqa-plugin --skill agentiqa-test
Clone the repo
git clone --depth 1 https://github.com/Agentiqa/agentiqa-plugin

Made for: Claude Code, Codex.

Or install agentiqa, the plugin that ships this one along with the rest of its 2 skills, 1 hook.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,250 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 $0.00131 $0.03250
Opus 5 $0.00066 $0.01625
Sonnet 5 $0.00026 $0.00650
Haiku 4.5 $0.00013 $0.00325

Measured 2d ago against content hash 90007fd2dda5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentiqa-test 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 2d 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.

skills/agentiqa-test/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentiqa Test Skill

You have access to the agentiqa CLI, which drives an independent AI testing agent against web apps. It has two commands:

  • agentiqa run — execute a saved or local test plan: fixed, enumerated, repeatable setup/action/verify steps with per-step verification. Use for regression re-checks and any "verify these specific things" request.
  • agentiqa exploreopen-ended discovery: turn the agent loose to find bugs from the UI, no predefined script.

Choosing the command

Pick by whether the check is scripted:

  • Fixed / enumerated / repeatable steps, or a regression re-checkagentiqa run. You (or the user) already know the exact steps and expected outcomes. run executes a deterministic test plan and verifies each step. Prefer this whenever the request reads like a checklist (e.g. "log in, add the Pro plan to the cart, verify the total is $19").
  • Open-ended discovery ("find bugs", "QA this page", "what's broken") → agentiqa explore. No predefined steps; the agent decides what to try.

Rule of thumb: if you can write the steps down, use run; if you're asking the agent to go looking, use explore.

CRITICAL RULES — READ BEFORE DOING ANYTHING

  1. NEVER explore the codebase — do NOT run ls, find, rg, cat, or read any source files. The agentiqa CLI is an external tool, not part of this repo. Go straight to Step 0.
  2. ALWAYS use the global agentiqa CLI — run agentiqa run ... / agentiqa explore ... directly. NEVER run node apps/cli/dist/cli.js, npx agentiqa, or any local build from the repo. The globally installed CLI has its own bundled Chromium and dependencies.
  3. Follow the steps below IN ORDER — do not skip, reorder, or improvise.

How the agent works

The testing agent:

  1. Navigates the app visually (screenshots + actions), like a real user
  2. Has NO knowledge of the codebase — works purely from the UI
  3. Reports issues (explore) or per-step verdicts (run) with severity, category, confidence, and reproduction steps
  4. Self-terminates when done

Read the full file on GitHub · 274 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 274 lines · 131 tokens per session scan A 90007fd2dda5

Subscribe to this mod's changes

agentiqa-test is a skill published in the GitHub repository Agentiqa/agentiqa-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 3,250 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

test-conversion

Workflow for converting unit tests to browser tests for Project Bedrock. Invoke this when the user wants to remove complex Browser dependencies from tests.

chromium/chromium · 31 tokens

agui-dotnet-cross-language-tests

Author cross-language interop tests that verify the AG-UI .NET SDK is wire-compatible with the TypeScript SDK — a Vitest TS client driving a C# CrossLanguage.TestServer over HTTP, both directions, including protobuf byte-parity against @ag-ui/proto. USE FOR: adding or modifying cross-language interop coverage…

ag-ui-protocol/ag-ui · 146 tokens

cli-e2e-testcase-writer

Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.

larksuite/cli · 78 tokens

harness-test-writer

Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…

maximhq/bifrost · 133 tokens

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens