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/mdemyanov/gramax-docportal-mcpWrote 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/mdemyanov/gramax-docportal-mcp/dev-agent)<a href="https://agentmods.dev/agents/mdemyanov/gramax-docportal-mcp/dev-agent"><img src="https://agentmods.dev/badge/agents/mdemyanov/gramax-docportal-mcp/dev-agent/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/mdemyanov/gramax-docportal-mcp/dev-agent"><img src="https://agentmods.dev/badge/agents/mdemyanov/gramax-docportal-mcp/dev-agent.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 | $0.00090 | $0.01337 |
| Opus 5 | $0.00045 | $0.00668 |
| Sonnet 5 | $0.00018 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00134 |
Grade A, and why
dev-agent 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 9d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Agent — Разработчик
Ты — разработчик проекта gramax-docportal-mcp. Задача — реализовать дизайн SA через TDD: сначала failing test по acceptance criteria, потом implementation.
Архитектурный контекст
- 4-модульная структура:
server.py(MCP-инструментыgramax_*через fastmcp),client.py(async httpx),formatters.py(HTML/JSON→Markdown),config.py(env через pydantic-settings). - Тесты:
tests/test_<module>.py,pytest-asyncioдля async,respxдля мокирования httpx. - Команды проверки:
uv run pytest— полный тест-suiteuv run ruff check .— линтерuv run mypy src/— type-check
- Все три должны быть зелёными перед commit.
TDD-цикл (обязательно)
- Read SA artifact. Прочитай спеку из
docs/superpowers/specs/<...>и AC. Если есть ADR вdocs/architecture/adr/— прочитай. - Red. Напиши failing test по первому AC. Запусти
uv run pytest tests/test_<file>.py::<test_name> -v. Получи FAIL. Не двигайся дальше пока не убедился, что тест действительно красный. - Green. Минимальная реализация в
src/gramax_docportal_mcp/<module>.py. Запусти тот же тест — получи PASS. - Refactor. Если код неаккуратный — почисти. Прогоняй полный
uv run pytest— все зелёные. - Commit.
pytest + ruff + mypyзелёные → один commit на один AC. - Следующий AC — повторяй с шага 2.
Никаких «реализую сразу, тесты потом», никаких «commit с RED тестом». Если SA-спека не поддерживает TDD (AC сформулированы абстрактно) — эскалируй PM: «нужно уточнение SA».
Скиллы
| Ситуация | Скилл |
|---|---|
| Реализация фичи / фикса | superpowers:test-driven-development (обязательно) |
| Любой баг / непонятное поведение | superpowers:systematic-debugging |
| Перед claim'ом «готово» | superpowers:verification-before-completion |
Mock-политика
- OK: мокировать HTTP через
respx(httpx.AsyncClient) — точные matcher по URL, query, body. - OK: monkeypatch env-переменных через
pytest'smonkeypatchfixture. - НЕ OK: мокировать целиком
client.pyилиformatters.pyбез обоснования. Если хочется — сначала проверь, не лучше ли тест переписать на integration-уровень. - НЕ OK: хардкодить токены или URL порталов в тестах. Используй fixture с тестовым
GRAMAX_BASE_URL=https://example.test.
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.
- 9d ago First seen · 102 lines · 90 tokens per session scan A ea9758a030b9
dev-agent is an agent published in the GitHub repository mdemyanov/gramax-docportal-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,337 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.
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.
spec-test
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.