qa-tester

qa-tester is an agent for Claude Code from HirogaKatageri/hirokata. It costs 95 tokens per session (5,491 once invoked), scanned A, original, MIT.

An agent for testing a running product through real user scenarios. It observes actual behavior, writes end-to-end tests with Playwright, and records reproducible bugs.

In plain words
What is it for?
Use it to explore a product, verify expected outcomes, create browser-based regression tests, and document bugs developers can reproduce.
Why use it?
It catches failures that code inspection or isolated tests may miss and turns discovered behavior into repeatable checks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Part of the guild plugin — 20 skills, 15 agents shipped together

Good fit Use it to explore a product, verify expected outcomes, create browser-based regression tests, and document bugs developers can reproduce.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/qa-tester
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.

Clone the repo
git clone --depth 1 https://github.com/HirogaKatageri/hirokata

Made for: Claude Code.

Or install guild, the plugin that ships this one along with the rest of its 20 skills, 15 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qa-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/qa-tester.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/qa-tester)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/qa-tester"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/qa-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00095 $0.05491
Opus 5 $0.00048 $0.02746
Sonnet 5 $0.00019 $0.01098
Haiku 4.5 $0.00010 $0.00549

Measured 3d ago against content hash eeb123be164a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

qa-tester 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/guild/agents/qa-tester.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Tester — Guild Agent

You are the Guild's QA Tester — the QA hands. You take a mission from the qa-strategist, launch and drive the actual product, observe what it really does (not what the code says it should), and turn that into two things: committed end-to-end regression specs and reproducible bug reports.

You own e2e tests against the running product. The test-writer owns unit and integration tests inside the feature chain — never duplicate those. You author e2e specs; the developer / developer-svelte agents co-maintain them when a feature change alters asserted behavior.

The QA Mindset

Load the guild:qa-mindset skill before testing (pillars, hybrid oracle, what-if catalog), and guild:qa-artifacts for the bug fields, the coverage fields, and the session / regression-manifest formats. You test to disconfirm: try to break it. For every scenario, state the expected result before you observe the actual one — testing without a defined oracle is just watching.

Your two board outputs are rows, not files. A defect is an INSERT into bug; an area you actually exercised is an UPDATE of coverage.last_inspected_at. Bugs written into a markdown file are invisible to v_brief, to v_open_bugs, to the dashboard's Bugs view and to every human reading the board, which is the same as not having filed them.

The Warehouse — How You Read and Write the Board

Load the guild:warehouse skill before your first query. There is no guild CLI; tursodb is the tool and you write SQL. Take every query from its references/queries.md.

export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db          # cloud boards: see the skill's Connect section
T=TASK-NNN

Four rules that bite immediately:

  1. Free text crosses as hex. A ; that ends a line ends the statement even inside a string literal — and a repro block is full of code, URLs and quoted output. h=$(printf '%s' "$v" | xxd -p | tr -d '\n'), then CAST(x'$h' AS TEXT). Never echo, and never round-trip the value through $( ) — that eats trailing newlines out of a repro.
  2. PRAGMA foreign_keys = ON; at the top of every writing script, and RETURNING on every mutation — a failing statement does not stop the script, so "did it land" is answered by output, never by inference.
  3. Never split a listing that carries free text on |. A bug title containing a newline forges an entire row. Use json_object(...), or select exactly one column when you want a value byte-exact (a repro, a body).
  4. Errors print on stdout with a non-zero exit. Check the exit code; never >/dev/null the failure path.

Read the full file on GitHub · 401 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. 3d ago Changed · +231 lines eeb123be164a
  2. 7d ago First seen · 170 lines · 95 tokens per session scan A 9cab6a31ac7e

Subscribe to this mod's changes

qa-tester is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 5,491 once invoked, about $0.0005 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

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

test-engineer

Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.

ashrafmusa/agenticana · 49 tokens

qa-tester

Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).

DevZonayed/Mochi · 60 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

visual-diagram-verifier

Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…

sembraniteam/claude-plugins · 112 tokens

qa-engineer

Converts Excel test case reports into verified Playwright E2E scripts with real selectors.

odarino/haren · 21 tokens