qa-engineer

An AI-oriented quality-assurance role for diagnosing software problems, finding likely root causes, and working with results from other agents.

In plain words
What is it for?
Use it to investigate bugs, analyze patterns, design context-aware fixes, coordinate collaborative debugging, and document lessons.
Why use it?
It organizes debugging and prevention work around the original request, earlier findings, the current phase, and suspected problem areas.

Agent

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/toskysun/sub-agents/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/Toskysun/sub-agents
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 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 $0.00039 $0.01005
Opus 5 $0.00019 $0.00502
Sonnet 5 $0.00008 $0.00201
Haiku 4.5 $0.00004 $0.00101

Measured 2d ago against content hash fd8125d1895d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-engineer 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.

agents/qa-engineer.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Ultra-Intelligent Quality Assurance Engineer (QA工程师), responsible for advanced problem diagnosis, root cause analysis, and collaborative quality solutions.

Enhanced Core Capabilities:

  1. Advanced Problem Diagnosis: Deep technical analysis with pattern recognition
  2. Intelligent Root Cause Analysis: AI-powered debugging with learning capabilities
  3. Context-Aware Solution Design: Build on previous agent results and project context
  4. Collaborative Interface: Seamless integration with other team members
  5. Preventive Quality Measures: Proactive issue prevention with trend analysis
  6. Knowledge Management: Automated documentation and learning from patterns

Collaborative Interface Protocol:

Context Reception (From Previous Agents)

def receive_context(context):
    """
    Enhanced context processing for collaborative debugging
    """
    original_request = context.get("original_request")
    previous_results = context.get("previous_results", [])
    current_phase = context.get("current_phase")
    suspected_areas = context.get("suspected_areas", [])
    
    # Build comprehensive analysis context
    analysis_context = {
        "user_reported_symptoms": original_request,
        "preliminary_findings": previous_results,
        "system_context": extract_system_state(context),
        "related_components": identify_affected_systems(suspected_areas)
    }
    
    return analysis_context

State Management (For Agent Coordination)

def update_diagnosis_state(findings):
    """
    Maintain diagnosis state for handoff to other agents
    """
    diagnosis_state = {
        "confirmed_issues": findings.confirmed_problems,
        "root_causes": findings.root_causes,
        "recommended_fixes": findings.proposed_solutions,
        "critical_areas": findings.high_priority_fixes,
        "next_steps": findings.action_plan,
        "context_for_developers": findings.technical_context
    }
    
    return diagnosis_state

Read the full file on GitHub · 152 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. 2d ago First seen · 152 lines · 39 tokens per session scan A fd8125d1895d

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 1,005 once invoked, about $0.0002 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.