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.
npx skills add dzhokhov/markdown-agent-vault-ru --skill project-creatorgit clone --depth 1 https://github.com/dzhokhov/markdown-agent-vault-ruWrote 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/skills/dzhokhov/markdown-agent-vault-ru/project-creator)<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/project-creator"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/project-creator/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/skills/dzhokhov/markdown-agent-vault-ru/project-creator"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/project-creator.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 | $0.00236 | $0.03345 |
| Opus 5 | $0.00118 | $0.01673 |
| Sonnet 5 | $0.00047 | $0.00669 |
| Haiku 4.5 | $0.00024 | $0.00334 |
Grade A, and why
project-creator 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Создание проекта в vault
Ты создаёшь новый проект в 01_now/projects/ и всю стартовую документацию: plan.md, tasks.md, context.md, log.md, README.md, и обновляешь индексы. План и всю документацию ты пишешь сам — по методологии автономного планирования LLM-агентом. Это главная гарантия скилла: владелец получает готовый проект, а не пустой бриф с просьбой заполнить.
Главное правило
Агент сам составляет проектную документацию. Нельзя просить владельца написать план, пункты плана, критерии качества, рубежи или проверить план построчно. Уточняющие вопросы разрешены только тогда, когда без ответа нельзя безопасно выбрать основу проекта (цель, контур, границы, цена ошибки, источник правды). Всё остальное агент выводит из чата, команды и локальных правил и фиксирует как допущение.
Обоснование: методология планирования для LLM-агента и Правило 12 в AGENTS.md.
Что прочитать перед работой
Устойчивые источники правды (не полагайся на память модели):
- Методология планирования для LLM-агента — как писать план против дрифта.
- Шаблон plan.md — канонические секции контракта проекта.
- Инструкция восстановления намерения — как понять недосказанное.
- Протокол записи — frontmatter, ссылки, обновление индексов.
- Task routing — что в plan.md, что в tasks.md, что вне проекта.
Требуется доступ к файлам
Скиллу нужен доступ на запись в vault. В Cowork: подними целевые пути через device-tools, собирай файлы в рабочей папке и записывай на диск владельца через device_commit_files. В Claude Code / локальном агенте: пиши файлы напрямую. Если доступа к файлам нет — не выдумывай, попроси владельца подключить папку vault.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 149 lines · 236 tokens per session scan A b713df47c157
project-creator is a skill published in the GitHub repository dzhokhov/markdown-agent-vault-ru (2 stars, last pushed 2d ago), licensed MIT. It adds 236 tokens to every session and 3,345 once invoked, about $0.0012 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 skills, from other repositories
project-sync
On-demand AI-powered sync of a project's repo state into the brain vault. Reads live git/GitHub/Jira data, updates the project status doc, and makes targeted edits to relevant brain docs where content is clearly stale. Triggered by "/project-sync [name]", "sync [project]", "what's the current state of [project]".
log-decision
Log cross-cutting business/product/hiring/vendor decisions to decisions/ directory with context and alternatives.
prd-os
PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this…
project-flow-ops
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
tasks
Create or update the live task dashboard (TASKS.md) in Obsidian. Use when the user wants to view or regenerate the task dashboard — 'show my tasks', 'update TASKS.md', 'open task view'. Do NOT use for: the vault portal/map (use moc), capturing new tasks (add them inside project notes directly), or daily briefing (use…
tasks
View and manage the task stack and processing queue. Shows pending work, active tasks, completed items, and queue state. Triggers on "/tasks", "show tasks", "what's pending", "task list", "queue status".