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 tonydzi/second-brain-starter-kit --skill slotgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/slot)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/slot"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/slot/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/tonydzi/second-brain-starter-kit/slot"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/slot.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 | $0.00050 | $0.05433 |
| Opus 5.5 | $0.00020 | $0.02173 |
| Sonnet 5.5 | $0.00010 | $0.01087 |
| Haiku 4.5 | $0.00005 | $0.00543 |
Grade A, and why
slot 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 7d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/slot — реестр переиспользуемых сессий
⭐⭐⭐ ГЛАВНОЕ СВЕРХУ (24.08.2026): ПЕРЕИСПОЛЬЗОВАНИЕ — ПЕРВЫЙ выбор, create — второй
Приказ Антона 24.08 голосом: «нужно переиспользовать сессии, чтобы они как можно реже запрашивали аппрувы». Порядок 31.07 («сначала create») отменён, потому что премиса, на которой он стоял, опровергнута замером в тот же вечер.
Что замерено 24.08 18:42 на хабе (живой прогон, не рассуждение):
update_scheduled_task(слот, description + prompt + fireAt)прошёл молча.- Сессия поднялась мгновенно (у разовой задачи задержки диспетчера нет).
- Сессия переименовала себя сама первым ходом через
mcp__ccd_session_mgmt__set_session_titleи вlist_sessionsвидна как «ПРОБА переиспользования слота 1842» (titleSource=tool), а НЕ под чужимtaskId. Старое утверждение «список title сессии не читает» — мертво. - Приложение само называет цену холодного
create(текст ответа инструмента): «Tool approvals granted during a run are stored on the task and auto-applied to future runs» — апрувы живут НА ЗАДАЧЕ. Новая задача = пустая история апрувов = сессия встанет на первом коннекторе, и окно будет ждать Антона. Прогретая — не встанет.
Процедура (единственная):
python ~/.claude/scripts/session_slot.py --claim "<суть сессии>" # даст taskId слота
update_scheduled_task(
taskId="<слот>",
description="<человеческое имя, видно в разделе Scheduled>",
fireAt="<ТОЛЬКО из двери: `python ~/.claude/scripts/_shared/fireat_now.py --in 15`>", notifyOnCompletion=true,
prompt="ПЕРВЫМ ДЕЛОМ переименуй эту сессию: вызови mcp__ccd_session_mgmt__set_session_title
с title \"<суть>\". Затем: <сид>")
⛔ Строка про set_session_title обязательна — без неё сессия висит под чужим именем,
и это ровно та невидимость, из-за которой канон переворачивали в июле.
create_scheduled_task остаётся честным путём только когда пул пуст — гейт
spawn_slot_guard.py теперь сам отбивает create при непустом пуле и печатает готовый
вызов update. Пул не посчитался — гейт пускает create, но кричит в stderr
(fail-open обязан быть громким, урок 29.07).
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.
- 7d ago Changed · +36 lines · -97 tokens per session 65fd7ada7520
- 11d ago Changed · -1 lines 136276d30e7c
- 14d ago Changed 4e5d44411bfb
- 16d ago First seen · 247 lines · 147 tokens per session scan A 7b88661d5db4
slot is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 5,433 once invoked, about $0.0002 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 2026-10-04.
Other skills, from other repositories
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
email-sorting
Customize and use a human-reviewed email sorting system for Gmail, Google Workspace, Outlook, Microsoft 365 or another connected mailbox. Use for first-time setup, folder or label recommendations from a read-only email sample, inbox triage, and applying approved sorting batches. Not for sending, replying to or…
inbox
An inbox-management skill for scanning an LLM Wiki inbox, previewing pending files, choosing how to process them, and sending selected material through an import step.
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.