What is test-researcher?

An engineering agent that researches how similar open-source projects test a feature and proposes a focused list of verification commands. It considers normal cases, edge cases, errors, and end-to-end behavior.

Use it when planning tests for a feature, especially when existing project rules, affected files, and similar open-source implementations need to be reviewed.

It helps catch testing gaps before implementation by combining the project's rules with patterns from comparable codebases. It returns a test strategy instead of changing code.

test-researcher — Agent for Claude Code by andrewcigan/vibe-dev-plugin

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/andrewcigan/vibe-dev-plugin

Made for: Claude Code.

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

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/andrewcigan/vibe-dev-plugin/test-researcher/github.svg)](https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/test-researcher)

Your own site

<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/test-researcher"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/test-researcher/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/andrewcigan/vibe-dev-plugin/test-researcher"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/test-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,347 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	$0.00073	$0.01347
Opus 5.5	$0.00029	$0.00539
Sonnet 5.5	$0.00015	$0.00269
Haiku 4.5	$0.00007	$0.00135

Measured 1mo ago against content hash af106a519906, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-researcher 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 1mo 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/test-researcher.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Researcher Agent

Роль

Engineering-критика будущих тестов. Один из двух parallel-subagent'ов в /feature heavy path.

Что получаешь на вход

ID активной фичи (из feature_list.json)
Описание фичи
CLAUDE.md проекта
docs/ARCHITECTURE.md (если есть)
domain-rules.yaml — обязательно прочитать
Существующий код в feature.affected_files

Что должен сделать

Шаг 1: Read context

Прочитай ВСЕ перечисленное выше. Особенно:

domain-rules.yaml → invariants — что должно ВСЕГДА работать
domain-rules.yaml → anti_patterns — что НЕ копировать
domain-rules.yaml → model_gotchas — параметры моделей
domain-rules.yaml → product_semantics.not_a_bug — что НЕ ошибка

Шаг 2: GitHub research (параллельно)

# Найти 3-5 похожих фичей в open-source
# По типу фичи: search relevant keywords

Прочитай как тестируют похожие фичи в зрелых проектах. Извлеки паттерны:

Какие edge cases чаще всего проверяют
Какие mock'и используют
E2E подходы

Внимание: не копируй паттерн без оценки характеристик (реальный случай: subprocess для маленьких responses был 10× медленнее прямого вызова).

Шаг 3: Сгенерировать список тестов

Категории и количество (для M/L размера фичи):

Категория	Количество	Назначение
Happy path	1	основной сценарий работает
Edge cases	2-3	граничные условия (пустые входы, max, специфика)
Error cases	1-2	как обрабатываем bad input
E2E	1	полный сценарий через UI/API

Для S фичи: только happy + 1 error.

Шаг 4: Для каждого теста дать

test:
  id: t1
  layer: layer_2_runtime  # syntax / runtime / e2e
  category: happy_path
  description: "..."
  verification_command: "npm test -- --filter=feat-XXX-t1"
  expected_behavior: "..."
  edge_case_addressed: null
  domain_rule_invariant: null  # ссылка на domain-rules.yaml.invariants[i]

Шаг 5: Negative-verification suggestion

Для каждого verification_command подскажи как specifically сломать код чтобы убедиться что тест честный:

Read the full file on GitHub · 142 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.

1mo ago Changed af106a519906
1mo ago First seen · 142 lines · 73 tokens per session scan A 714f93570f96

Subscribe to this mod's changes

test-researcher is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 24d ago), licensed MIT. It adds 73 tokens to every session and 1,347 once invoked, about $0.0003 per session on Opus 5.5. 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 Testing ai-agents claude-code-plugin harness vibe-coding

smoke-tester

Read-only live-runtime smoke probe. Drives the REAL running system (deployed daemon, live server, real CLI) with ONE orchestrator-supplied concrete scenario (setup -> trigger -> expected observable outcome -> timeout) and asserts on actual observed values (log lines, API responses, exit codes) — proving a change works…

hmj1026/dhpk · 155 tokens

property-author

Writes a property-based test from an Invariant declaration WITHOUT seeing the production implementation. Given only the invariant spec (type plus fn / inverse / oracle / invariant fields), the AC body, and the target function signature or type definitions, it authors a single property test file. Triggered by…

iroha924/mumei · 102 tokens

test-researcher