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 deflategit 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/deflate)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/deflate"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/deflate/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/deflate"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/deflate.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 | $0.00081 | $0.01634 |
| Opus 5.5 | $0.00032 | $0.00654 |
| Sonnet 5.5 | $0.00016 | $0.00327 |
| Haiku 4.5 | $0.00008 | $0.00163 |
Grade A, and why
deflate 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 yesterday.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/deflate — меньше тепла и шума на этом узле, вместе с оператором
Движок: python ~/.claude/scripts/node_deflate.py (0 LLM, stdlib, win/mac/linux; --selftest есть). Суждение «нужно / не нужно» — у оператора, не у скрипта.
Шаг 0 — RECALL
Память laptop-fan-noise-root-cause + zbook-no-gpu-without-permission; роль узла из ~/.claude/machine.env (hub = роботы остаются, satellite = минимум фона, §7.1). Термо-история, если есть: ~/.claude/scripts/_power_thermal/*.csv.
Шаг 1 — Аудит (только чтение)
python ~/.claude/scripts/node_deflate.py audit → таблица: запусков/час, наши vs вендорские задачи, автозапуск, держатели GPU, режим питания, топ CPU. На HP-железе температуры и обороты вентиляторов читать HP-сенсором (Get-CimInstance -Namespace root\HP\InstrumentedBIOS -ClassName HP_BIOSNumericSensor), а НЕ nvidia-smi: он сам будит спящую карту.
Шаг 2 — План
python ~/.claude/scripts/node_deflate.py propose → ~/.claude/_deflate/<HOST>-plan.json, каждая строка ok=false. Правила движка: на сателлите наши сторожа чаще 60 мин → растянуть (Desktop-Watchdog 10, термо-логгер 15, Fleet Pulse 30); дубли хаба и мёртвые роботы → выключить; оверлей питания «Best performance» → Balanced; GPU=true на сателлите → заметка. Вендорские задачи скрипт НИКОГДА не предлагает.
Шаг 2-бис — ⛔ ДВЕ ЦИФРЫ ПЕРЕД ЛЮБОЙ РАСТЯЖКОЙ (замер 22.09.2026)
Строка плана, растягивающая интервал СТОРОЖА, не показывается оператору, пока не названы две цифры: (1) фора, которую сторож даёт основному звену, и (2) срок, за который потребитель заметит пропажу. Новый интервал обязан быть меньше обеих; больше — строка из плана выбрасывается, а не «обсуждается». Не знаешь цифр — не трогаешь интервал.
⚠️ Чем оплачено: дефляция 15.09 («все рутины ×2») растянула Claude Voice Backstop 4ч → 8ч. Это 0-токенный детерминированный сторож с форой боту 10 минут, подпадавший под собственное исключение той же дефляции — его срезали по имени («ещё одна запланированная задача»), а не по роли. 22.09 бот-расшифровщик пропустил голосовую Антона, страховка спала, state.json писал status=OK, и пропажу за 14 минут заметил ЧЕЛОВЕК. Нулевой расход LLM = кандидат в исключения по умолчанию, а не в первые жертвы.
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.
- yesterday Changed 505c448a368c
- 14d ago Changed · -2 lines 1498effb521c
- 17d ago Changed d3f945429fd7
- 19d ago Changed · +15 lines · -59 tokens per session 51cd819f4e89
- 28d ago First seen · 35 lines · 140 tokens per session scan A 115ab2ebfc75
deflate is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 1,634 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
wiki-query
Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…
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…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…
defuddle
Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-mode
Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…