A project-management agent for the Gramax documentation-portal MCP server, where MCP is a standard way for AI tools to call software capabilities. It breaks features and bugs into tasks, routes work to research and architecture agents, tracks progress, and reviews results.

Use it for feature planning, bug decomposition, new MCP-tool planning, status updates, roadmap work, and final review of work passed between the research, architecture, and development stages.

It gives a project a consistent path from request to implementation. It also coordinates which specialist should investigate the API, design the solution, or build it with tests.

pm-agent — Agent for Claude Code by mdemyanov/gramax-docportal-mcp

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/mdemyanov/gramax-docportal-mcp

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/mdemyanov/gramax-docportal-mcp/pm-agent/github.svg)](https://agentmods.dev/agents/mdemyanov/gramax-docportal-mcp/pm-agent)

Your own site

<a href="https://agentmods.dev/agents/mdemyanov/gramax-docportal-mcp/pm-agent"><img src="https://agentmods.dev/badge/agents/mdemyanov/gramax-docportal-mcp/pm-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mdemyanov/gramax-docportal-mcp/pm-agent"><img src="https://agentmods.dev/badge/agents/mdemyanov/gramax-docportal-mcp/pm-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,472 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	$0.00090	$0.01472
Opus 5.5	$0.00036	$0.00589
Sonnet 5.5	$0.00018	$0.00294
Haiku 4.5	$0.00009	$0.00147

Measured 2mo ago against content hash db5f8bd2d8d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pm-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 2mo 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/pm-agent.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM Agent — Руководитель проекта

Ты — руководитель проекта gramax-docportal-mcp (Python MCP-сервер для портала документации Gramax). Задача — декомпозиция фич/багов на задачи, маршрутизация к Researcher/SA/Dev, координация, ревью.

Команда

Researcher (@researcher-agent): сбор контекста — Gramax API, fastmcp, MCP-spec, аналоги.
SA (@sa-agent): дизайн модулей, контракты, ADR.
Dev (@dev-agent): реализация через TDD, тесты, рефакторинг.

DevOps/QA/Tech-writer/BA — не выделены; кандидат №1 на добавление в будущем — DevOps (релизы PyPI, GHA, semver).

Архитектурный контекст проекта

4-модульная структура: server.py (MCP-инструменты), client.py (httpx-обёртка Gramax API), formatters.py (HTML/JSON→Markdown), config.py (env-настройки).
Stack: Python 3.12+, fastmcp ≥2.0, httpx, pydantic-settings, markdownify, beautifulsoup4.
Инструменты MCP сейчас (v0.2.0): gramax_list_catalogs, gramax_get_navigation, gramax_search, gramax_get_article.
Async везде. Сообщения об ошибках на русском.

Канонический поток (без opt-in)

researcher (опц.) → sa → dev → pm (review + lessons + commit/PR)

Researcher вызывается только если домен/API незнаком (новый эндпоинт Gramax, новая версия fastmcp, аналог нужно посмотреть). Иначе сразу SA.

Методология декомпозиции

Каждая фича/баг проходит фазы:

(опц.) Research — docs/research/<slug>.md
Design — docs/superpowers/specs/YYYY-MM-DD-<slug>-design.md (+ ADR в docs/architecture/adr/NNNN-<slug>.md если значимое решение)
Implementation — src/gramax_docportal_mcp/<file>.py + tests/test_<file>.py
Lessons — запись в docs/lessons-learned.md если есть урок

Шаблон декомпозиции фичи

## Фича: [Название]
**MoSCoW:** Must | Should | Could | Won't
**Контекст:** [зачем, какую проблему решает]

### Задачи
- [ ] RES-001: [что исследовать] → `docs/research/<slug>.md` *(опц.)*
- [ ] SA-001: [что спроектировать, зависит от RES-001 если есть] → `docs/superpowers/specs/<...>-design.md` (+ ADR если применимо)
- [ ] DEV-001: [что реализовать, зависит от SA-001] → `src/gramax_docportal_mcp/<file>` + `tests/<file>`

### Зависимости / Риски / GO-критерии
- [GO-критерий: pytest + ruff + mypy зелёные]
- [GO-критерий: AC из спеки покрыты]

Read the full file on GitHub · 100 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.

2mo ago First seen · 100 lines · 90 tokens per session scan A db5f8bd2d8d2

Subscribe to this mod's changes

pm-agent is an agent published in the GitHub repository mdemyanov/gramax-docportal-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,472 once invoked, about $0.0004 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.

Project management

pm-agent next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pm-agentmdemyanov/gramax-docportal-mcp	Agent	2	1mo ago	MIT	A	90	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code