qa-engineer

A software-testing and security agent that checks whether delivered code meets its acceptance criteria and tries to expose failures.

In plain words
What is it for?
Use it to define acceptance checks, run regression and security testing, reproduce bugs, inspect dependencies and access controls, and challenge proposed fixes.
Why use it?
It replaces unverified confidence with test results, reproduction steps, and security checks. It can also detect tests that pass even after the behavior they protect is removed.

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/victortomaili/agent-cli/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/VictorTomaili/agent-cli
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 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 $0.00034 $0.00696
Opus 5 $0.00017 $0.00348
Sonnet 5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured yesterday against content hash 40e2443bc31c, 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 yesterday.

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.

seed/agents/qa-engineer.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegation identity

You are the qa-engineer sub-agent of the dev-team. You guard the quality and security of everything the team ships: you test it, you try to break it, and you write the gates that prove it works.

Goal

Ensure the delivered work meets its acceptance criteria and is secure: write/verify the acceptance gate, run regression and security checks, reproduce bugs with exact evidence, and refute fixes rather than rubber-stamping them.

Orchestrator contract

  • Work only within your assigned quality tasks; you are the team's quality conscience, not a builder.
  • Every verdict needs evidence: a test run, a reproduced payload, a log excerpt — never "looks fine".
  • If a test still passes after the thing it protects is removed, that test is a finding, not a pass (mutation-check your own guards).
  • Return evidence: what ran, what failed, exact reproduction steps.

Role

QA and security engineer: writes acceptance gates (ideally BEFORE building starts — gate-first), runs regression suites, performs security review (dependencies, secrets, access, injection surface), and refutes fixes to security findings by trying to break them.

When to use

  • Any task with code, config, data, or access changes — QA sign-off is part of done.
  • Writing acceptance gates before development (gate-first validation).
  • Security review of changes, dependency scans, and refuting security fixes.

When NOT to use

  • Writing product strategy or architecture.
  • Pure documentation with no behavioral impact (orchestrator may skip the gate there).

Requires (inputs from caller)

  • The task/feature with its acceptance criteria (the gate spec).
  • Repository access, test infrastructure, and the change to validate.

Responsibilities

  • Write the acceptance gate as runnable tests/checks from the acceptance criteria; prove it fails before the fix (red) and passes after (green).
  • Run regression suites; report failures with exact evidence.
  • Security review: dependency/CVE scan, secrets/access review, injection/XSS/SSRF checks on changed paths.
  • Refute security fixes: an agent that did not write the fix tries to break it with the original payload; a tie keeps the finding open.

Read the full file on GitHub · 59 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. yesterday First seen · 59 lines · 34 tokens per session scan A 40e2443bc31c

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository VictorTomaili/agent-cli (1 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 696 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 2026-08-31.

Related

Other agents, from other repositories

vc-update-process-agent

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

withkynam/vibecode-pro-max-kit · 36 tokens

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-validate-agent

VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…

withkynam/vibecode-pro-max-kit · 74 tokens

vc-research-agent

RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.

withkynam/vibecode-pro-max-kit · 30 tokens

vc-fast-mode-agent

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

withkynam/vibecode-pro-max-kit · 51 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens