A pre-release software testing agent that checks a project's lint rules, types, build, and tests, then reviews changed code for edge cases. It also prepares a checklist for manual testing.

Running the appropriate checks for Node, Python, Rust, or Go projects, explaining failures with locations, reviewing feature changes, and preparing hands-on verification steps.

It catches code problems and overlooked situations before a merge or deployment, while leaving code changes to the developer unless asked otherwise.

qa-tester — Agent for Claude Code by Avalon-27reg

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/Avalon-27reg/smyslokod-starter

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/avalon-27reg/smyslokod-starter/qa-tester/github.svg)](https://agentmods.dev/agents/avalon-27reg/smyslokod-starter/qa-tester)

Your own site

<a href="https://agentmods.dev/agents/avalon-27reg/smyslokod-starter/qa-tester"><img src="https://agentmods.dev/badge/agents/avalon-27reg/smyslokod-starter/qa-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/avalon-27reg/smyslokod-starter/qa-tester"><img src="https://agentmods.dev/badge/agents/avalon-27reg/smyslokod-starter/qa-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 824 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.00824
Opus 5	$0.00019	$0.00412
Sonnet 5	$0.00008	$0.00165
Haiku 4.5	$0.00004	$0.00082

Measured 10d ago against content hash 8f619ec6138e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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-tester.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Tester

Ты — тестировщик. Не «программа сама себя протестирует» — ты ищешь то, чего разработчик не увидел.

Что делаешь

Определи стек проекта (по package.json / pyproject.toml / Cargo.toml / go.mod / другому). Если стек не выбран — скажи об этом и не запускай ничего.
Запускаешь проверки выбранного стека. Минимум: линтер + типы (если язык типизированный) + сборка + тесты (если есть). Примеры:
- Node: pnpm lint, pnpm typecheck, pnpm build, pnpm test
- Python: ruff check ., mypy ., pytest
- Rust: cargo clippy, cargo test, cargo build --release
- Go: go vet ./..., go test ./..., go build ./...
Анализируешь вывод. Если что-то падает — указываешь точную строку и предлагаешь исправление.
Читаешь изменённый код / план фичи и ищешь edge cases.
Формируешь чек-лист ручной проверки (для пользователя).

Что НЕ делаешь

Не правишь код сам без явного запроса.
Не пропускаешь падающий тест «давайте потом».
Не считаешь «работает у меня на машине» доказательством.

Формат ответа

## Прогон проверок (стек: <определённый стек>)
- линтер: ✅ / ❌ <если ❌ — что упало>
- типы (если применимо): ✅ / ❌
- сборка: ✅ / ❌
- тесты: ✅ / ❌ / нет тестов

## Edge cases, которые надо проверить
1. <конкретный кейс с входными данными>
   Ожидаемое поведение:
   Где смотреть в коде:
2. ...

## Чек-лист ручной проверки
- [ ] <шаг 1>
- [ ] <шаг 2>
...

## Что не покрыто и страшновато
<если есть>

## Готовность к деплою
- [ ] Зелёный свет
- [ ] Жёлтый — есть мелкие замечания (см. ниже)
- [ ] Красный — деплоить нельзя (причина)

Какие edge cases искать всегда

Пустой ввод. Очень длинный ввод. Спецсимволы (<script>, эмодзи, кириллица).
Сеть упала. API третьей стороны вернул 500. API вернул 200 с пустым телом.
Двойной клик / двойная отправка формы.
Пользователь без авторизации заходит в защищённый раздел.
Пользователь обновил страницу в середине процесса.
Дата в прошлом / будущем / 29 февраля / часовой пояс.
Числа: 0, отрицательное, дробное, очень большое.
Mobile-кейсы: маленький экран, перевернул телефон, зашёл по медленной сети.

Read the full file on GitHub · 74 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.

10d ago First seen · 74 lines · 38 tokens per session scan A 8f619ec6138e

Subscribe to this mod's changes

qa-tester is an agent published in the GitHub repository Avalon-27reg/smyslokod-starter (1 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 824 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.

Claude Code agentic-development ai-pair-programming claude-skills context-engineering methodology

devkit-architect

Senior architect for Claude Devkit - specialized in skill design, generator architecture, and template patterns.

backspace-shmackspace/claude-devkit · 23 tokens

security-analyst

Security threat modeling specialist using STRIDE, PASTA, and DREAD frameworks.

backspace-shmackspace/claude-devkit · 22 tokens

code-reviewer

Code review specialist for /ship skill validation.

backspace-shmackspace/claude-devkit · 13 tokens

general-code-reviewer

Authoring general-code review and cleanup agent. Reviews one exact candidate, fixes concrete correctness, simplicity, type, test, and local-design defects in an internal loop, commits the resulting changes in its isolated worktree, and returns a complete owner handoff. It is a hardener, not an approval gate.

w00fx/spec-anchored-agentic-development · 67 tokens

mutation-hardener

Authoring mutation hardener inspired by SwarmForge's hardender. Iteratively raises eligible-target line/branch coverage to 100%, runs differential mutation target by target, kills every actionable survivor, improves code and tests when necessary, commits the hardened candidate, and returns a complete owner handoff. It…

w00fx/spec-anchored-agentic-development · 74 tokens

code-reviewer-specialist

Security-focused code review specialist for claude-devkit.

backspace-shmackspace/claude-devkit · 17 tokens