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 new-dialog-handoffgit 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/new-dialog-handoff)<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/new-dialog-handoff"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/new-dialog-handoff/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/new-dialog-handoff"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/new-dialog-handoff.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 | $0.00136 | $0.01240 |
| Opus 5 | $0.00068 | $0.00620 |
| Sonnet 5 | $0.00027 | $0.00248 |
| Haiku 4.5 | $0.00014 | $0.00124 |
Grade A, and why
new-dialog-handoff 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 11d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Переход в новый диалог
Ты выполняешь протокол безопасного handoff в свежий чат. Цель: не потерять рабочее состояние, не дублировать память и не тащить критичный контекст только в историю разговора.
Принцип
Сначала сохрани состояние в durable source of truth, потом переводи работу в новый чат. Не делай длинный пересказ беседы, если уже есть log.md, tasks.md, context.md, research-note, spec или другой канонический артефакт.
Когда применять
- Чат стал длинным и качество следующих ответов может просесть.
- Агент показывает критический хвост
CTX. - Пользователь явно просит продолжить в новом чате.
- Предстоит длинный следующий шаг: review, большой diff, большой ресёрч, многофайловая правка, длинное объяснение.
Протокол
Шаг 1. Определи, где должен жить state
Спроси себя:
- это проектная работа;
- это standalone research/knowledge;
- или уже есть готовый канонический артефакт, на который можно опереться.
Приоритет источника правды (в порядке медленные слои → быстрые, как в write-protocol.md §5):
- существующий проектный контур —
README.md→plan.md→context.md→tasks.md→log.md; 01_now/ops/<contour>/delegations/<person-slug>.md— если state — это открытое делегирование;01_now/personal/tasks.md— если state — личное обязательство владельца;- уже созданный standalone note в
03_knowledge/; 00_inbox/— если это curiosity без проекта;- новый checkpoint только если без него состояние реально потеряется.
Если handoff касается активного проекта, а plan.md ещё не существует (legacy) — сначала создай plan.md из шаблона, затем фиксируй состояние уже в новом slow-layer контракте. Handoff не должен опираться только на log.md, если проект уже активный.
Шаг 2. Переиспользуй parking, а не заменяй его
Если работа относится к проекту:
- сначала выполни протокол из
skills/parking/SKILL.md— он сам разведёт state по правильным файлам (plan / log / tasks / delegations / personal) согласно task-routing decision tree (см. task-routing-methodology-2026-04.md §4); - не изобретай параллельную систему фиксации;
- в следующем чате рекомендуй вход через
resume— он сам перечитает README → plan → context → tasks → log и сделает passive recall по delegations.
What ships with it
3 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.
- 11d ago First seen · 100 lines · 136 tokens per session scan A b60ebb1c9692
new-dialog-handoff is a skill published in the GitHub repository dzhokhov/markdown-agent-vault-ru (2 stars, last pushed 4d ago), licensed MIT. It adds 136 tokens to every session and 1,240 once invoked, about $0.0007 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
log
Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.
lint-brain
Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".
ingest-article
Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.
analyse-call
Use this when a local call transcript or meeting note should be analyzed into traceable PersonalOS context. Preserves the source, separates evidence from interpretation, updates only proven owner truth, routes confirmed commitments through task-manager, and never sends messages or triggers external actions without…
wrap-session-up
End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.
kickoff
Guided first-run setup for a forked brain-starter vault. Walks through identity, first project, semantic search, integrations, indexes, and the first commit - verifying each phase before moving on. Use when the user has just forked or cloned brain-starter, says "set up my brain", "I just forked brain-starter", or runs…