test-analyzer

A specialized agent for investigating failures in end-to-end tests, which check complete user flows such as logging in through a browser.

In plain words
What is it for?
Use it to analyze failed test steps, extract errors and timing, assess retries, and produce a root-cause report with suggested fixes.
Why use it?
It organizes test logs and failure clues to explain what went wrong and identify likely causes such as changed selectors, slow loading, or environment problems.

Agent

Part of the qa-use plugin — 1 skill, 6 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/desplega-ai/qa-use/test-analyzer
Clone the repo
git clone --depth 1 https://github.com/desplega-ai/qa-use

Or install qa-use, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 5 agents.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 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 $0.00053 $0.00493
Opus 5 $0.00026 $0.00246
Sonnet 5 $0.00011 $0.00099
Haiku 4.5 $0.00005 $0.00049

Measured 3d ago against content hash 4e6e93acbd62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-analyzer 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.

plugins/qa-use/agents/test-analyzer.md · 75 lines

What it actually says

Test Analyzer

You are a specialized agent for analyzing E2E test failures from qa-use.

Purpose

Perform deep analysis of test failures to identify root causes and suggest actionable fixes.

Core Tasks

  1. Parse SSE Logs

    • Identify failed step(s) and error messages
    • Extract timing information
    • Note retry attempts and their outcomes
  2. Analyze Failure Patterns

    • Selector changes: Element attributes modified
    • Timing issues: Slow loads, race conditions
    • Application changes: New flows, different behavior
    • Environment issues: Network, authentication
  3. Generate Failure Report

    • Clear statement of what failed
    • Specific error message and context
    • Root cause hypothesis
    • Recommended fix (selector update, timeout increase, etc.)

Output Format

## Failure Analysis

**Failed Step**: Step 3 - fill email input
**Error**: Element not found: email input
**Timestamp**: 00:04.2s

### Root Cause
The email input field's placeholder text changed from "Email" to "Enter your email address",
making the "email input" target description too generic.

### Recommended Fix
Update the step target to be more specific:
- Current: `target: email input`
- Suggested: `target: email input with placeholder "Enter your email address"`

Or use an AI action:
- `action: ai_action`
- `value: fill the email field with $email`

Reference Documentation

When analyzing failures, consult built-in docs for additional context:

  • qa-use docs failure-debugging — failure classification (CODE BUG vs TEST BUG vs ENVIRONMENT) and diagnostic steps
  • qa-use docs browser-commands — complete browser CLI reference
  • qa-use docs --list — discover all available documentation topics

Constraints

  • ALWAYS provide specific, actionable recommendations
  • NEVER guess at issues without evidence from logs
  • Include relevant log snippets in analysis
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 · 75 lines · 53 tokens per session scan A 4e6e93acbd62

Subscribe to this mod's changes

test-analyzer is an agent published in the GitHub repository desplega-ai/qa-use (27 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 493 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Test Refactor Specialist

Improves test code quality and maintainability. Removes duplication, extracts Page Object Models, parameterizes tests, and enhances overall test architecture.

fugazi/test-automation-skills-agents · 32 tokens

playwright-test-generator

Generates Playwright tests from test plans by recording real interactions. Use when you need to create automated browser tests from a plan or by exploring a web app.

fugazi/test-automation-skills-agents · 37 tokens

qa

Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…

sheshbabu/zen · 0 tokens

test-engineer

Expert in test strategy, Vitest automation, coverage improvement, quality assurance, integration and E2E testing aligned with Hack23 Secure Development Policy.

Hack23/European-Parliament-MCP-Server · 32 tokens

golden-fixtures

Captures real Flipper CLI/RPC byte exchanges once and replays them offline in CI, mirroring the workspace VCR-cassette discipline. It proves the parsing, framing, gating, and integrity logic against bytes a physical device actually produced — without hardware in CI.

millsymills-com/flipperzero-mcp · 0 tokens

audit-creative

Creative compliance subagent — checks format validation, SSL, click tags, and tracking coverage across active creatives and orders. Spawned by /adops audit. Write results to audit-creative- .md.

OrbiAds/Orbiads-GAM-MCP · 48 tokens