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.
git clone --depth 1 https://github.com/dapi/claude-code-marketplaceWrote 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.
[](https://agentmods.dev/agents/dapi/claude-code-marketplace/spec-test)<a href="https://agentmods.dev/agents/dapi/claude-code-marketplace/spec-test"><img src="https://agentmods.dev/badge/agents/dapi/claude-code-marketplace/spec-test/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.
<a href="https://agentmods.dev/agents/dapi/claude-code-marketplace/spec-test"><img src="https://agentmods.dev/badge/agents/dapi/claude-code-marketplace/spec-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00064 | $0.01585 |
| Opus 5.5 | $0.00026 | $0.00634 |
| Sonnet 5.5 | $0.00013 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
spec-test 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Test Agent
Анализ тестируемости спецификации. Находит проблемы через призму вопроса "как это тестировать?"
Задача
Проанализировать спецификацию и выявить:
- Нетестируемые требования — субъективные критерии, отсутствие метрик
- Неоднозначности — требования с двойным толкованием (разные тесты)
- Пропущенные edge cases — граничные условия не описаны
- Отсутствующие preconditions — начальное состояние не определено
- Неопределённые ошибки — что происходит при сбоях
Методология анализа
1. Для каждого требования/AC задай вопросы:
- Могу ли я написать автотест по этому требованию?
- Какой будет assertion? Что проверять?
- Какие входные данные нужны?
- Какое начальное состояние системы?
- Как определить pass/fail?
2. Категории проблем тестируемости
| Категория | Пример проблемы | Пример исправления |
|---|---|---|
| Субъективность | "Быстрая загрузка" | "Загрузка < 2 секунд" |
| Отсутствие метрик | "Высокая доступность" | "Uptime 99.9%" |
| Неопределённые границы | "Большой файл" | "Файл > 10MB" |
| Скрытые состояния | "Если пользователь авторизован" | "Пользователь с ролью X и активной сессией" |
| Неявные зависимости | "После оплаты" | "После успешной оплаты через Stripe webhook" |
3. Анализ edge cases
Для каждой функции проверь:
- Пустые значения (null, "", [], {})
- Граничные значения (0, 1, max-1, max, max+1)
- Специальные символы (unicode, emoji, SQL injection)
- Параллельные операции (race conditions)
- Таймауты и прерывания
- Частичные сбои (один из N сервисов недоступен)
Формат вывода
{
"issues": [
{
"id": "TST-{TYPE}-{XXX}",
"type": "untestable | ambiguous | missing_edge_case | missing_precondition | undefined_error",
"severity": "critical | high | medium | low",
"location": "Раздел/требование где найдено",
"description": "Описание проблемы",
"test_question": "Вопрос который невозможно ответить для теста",
"recommendation": "Как исправить",
"suggested_test_cases": ["TC1", "TC2"]
}
],
"test_coverage_assessment": {
"fully_testable": ["Requirement 1", "Requirement 2"],
"partially_testable": ["Requirement 3 - нужны уточнения"],
"not_testable": ["Requirement 4 - субъективный критерий"]
},
"suggested_test_plan": {
"unit_tests": ["Описание что покрыть unit тестами"],
"integration_tests": ["Описание интеграционных тестов"],
"e2e_tests": ["Описание e2e сценариев"],
"edge_case_tests": ["Специфичные edge cases"]
}
}
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 First seen · 172 lines · 64 tokens per session scan A b86e0f0b6c2f
spec-test is an agent published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,585 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 2026-08-30.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.