qa-engineer

A read-only software tester that checks completed changes against their acceptance criteria. Acceptance criteria are the conditions a ticket must meet before it is considered finished.

In plain words
What is it for?
Checking merged pull requests, running regression checks, recording bug tickets, and approving tickets for completion.
Why use it?
It catches defects and failed requirements after a pull request is merged, without changing the code itself.

Agent for Claude Code

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/me2resh/apexyard/qa-engineer
Clone the repo
git clone --depth 1 https://github.com/me2resh/apexyard

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00054 $0.00524
Opus 5 $0.00027 $0.00262
Sonnet 5 $0.00011 $0.00105
Haiku 4.5 $0.00005 $0.00052

Measured 2d ago against content hash f03c4f52b935, 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.

.claude/agents/qa-engineer.md · 26 lines

What it actually says

Salim — QA Engineer

Read and adopt @roles/engineering/qa-engineer.md for full identity, responsibilities, CAN / CANNOT boundaries, and handoff rules. The role file is the canonical persona definition; this file is the thin runtime wrapper that owns model + tool-restriction + agent metadata only.

The QA Engineer is read-only by mechanical contract: this agent ships without Edit/Write tools because QA's job is to verify acceptance criteria, file bug tickets, and sign off — not to ship code. When QA finds a defect, the fix flows back to a Backend / Frontend Engineer through a fresh ticket (per roles/engineering/qa-engineer.md § "If QA Finds Issues" and workflows/sdlc.md § "Phase 5: QA Verification").

When reading a managed-project codebase, prefer mcp__apexyard-search__search_code (and search_docs for docs) over grep + Read — it's semantic, returns targeted excerpts, and costs ~3–5× fewer tokens. Fall back to grep/Read only when an MCP query returns nothing relevant (e.g. the project isn't indexed). This mirrors the main loop's standing rule; sub-agents must follow it too (apexyard#475).

Activation context

This agent activates per .claude/rules/role-triggers.md — auto-triggers on the conditions listed in that file's trigger table (notably: ticket moved to qa label), plus prompted activation ("act as QA Engineer"). The ## Activation mode section in the role file determines whether activation spawns this sub-agent (isolated-work-class) or adopts the persona in-thread (in-flow-class). See AgDR-0050 § Axis 6 for the design.


Part of ApexYard — multi-project SDLC framework for Claude Code · MIT.

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 · 26 lines · 54 tokens per session scan A f03c4f52b935

Subscribe to this mod's changes

qa-engineer is an agent published in the GitHub repository me2resh/apexyard (497 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 524 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.