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 hyper-researchgit 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/hyper-research)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/hyper-research"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/hyper-research/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/hyper-research"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/hyper-research.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 | $0.00087 | $0.02643 |
| Opus 5.5 | $0.00035 | $0.01057 |
| Sonnet 5.5 | $0.00017 | $0.00529 |
| Haiku 4.5 | $0.00009 | $0.00264 |
Grade A, and why
hyper-research 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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hyper — одно исследование, максимум независимых голов
Приказ Антона 14.09.2026: «каждый deep research запускать сразу в максимальном количестве LLM, минимум в 3; цель — как можно больше НЕЗАВИСИМЫХ исследований».
⛔ Это НЕ второй транспорт. Разнос промпта, сбор, синтез, кворум живут в /dr-fanout и
dr_queue.py — там же и остаются. /hyper добавляет ровно три вещи, которых там не было, и
делегирует всё остальное вниз (та же схема, что /rr → /retro).
| Что нового | Прибор | Красный тест |
|---|---|---|
| рельса = вендор#аккаунт (9 живых ног вместо 6) + лок профиля по полному id | ~/.claude/dr_rails.json + dr_rails_registry.py |
_test_dr_rails_registry.py |
| доказанный максимальный режим думания у каждой ноги | поле max_reasoning.proof в реестре |
там же, кейс 5 |
| добор опоздавших после закрытия кворумом | dr_latecomer_sweep.py |
долг виден на живых данных |
| цель без двери заказать нельзя (одна схема имён на заказ и на сбор) | dr_doors.py + гейт в dr_queue new |
_test_dr_door_gate.py, красный показан мутацией 14.09 |
Тизер после синтеза собирает dr_post_draft.py — единственный источник этой работы
(мой близнец dr_flash_teaser.py убит в _scratch 14.09, чтобы не было двух писателей).
Шаг 0. RECALL и дедуп (§8.4)
python "$IMPORTS_ROOT/brain_ask.py" "<тема>"
Уже исследовали → поднимаем старый отчёт, второй раз не заказываем.
Шаг 1. Набрать веер
python ~/.claude/scripts/dr_rails_registry.py pick --n 6
python ~/.claude/scripts/dr_rails_registry.py doors
⭐ CLI-ноги Claude (claudecli#a2, claudecli#bb) — полноценные ДР-рельсы, а не суррогат: замер 14.09.2026 на обоих баках вернул живые URL с материалом, датированным ТЕМ ЖЕ ДНЁМ, то есть веб-поиск работает и ссылки настоящие. Двери у них CLI (dr_headless_dispatch.py --rails claude-a2).
pick берёт СНАЧАЛА по одной ноге на вендора и лишь потом вторые/третьи ноги того же вендора:
шесть вкладок одного вендора — не шесть мнений. doors печатает ноги без доказанной двери —
это долг, а не приговор (perplexity#web: 0 кук во всех Firefox-профилях этого узла,
следы в бэкапе кук Chrome есть ⇒ дверь возможна через Chrome-MCP, но НЕ проверена; честная
формулировка — «я не нашёл двери», а не «её нет», §5.4).
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.
- 3d ago Changed 5aae0277d90f
- 16d ago Changed · -2 lines 68cfef1b895c
- 17d ago Changed · +2 lines · -69 tokens per session a111552f44e5
- 20d ago Changed · +13 lines 656930a66e1f
- 1mo ago First seen · 114 lines · 156 tokens per session scan A fff1f23aceae
hyper-research is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 2,643 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-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.…
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…
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.
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…
posting-mmm
Stage a compliance-passed post in Mai Marketing Machine (GoHighLevel social planner API) as a DRAFT for owner review, and schedule it after approval. Use when a draft has passed compliance-check, or when the owner says "stage this", "send to Mai Marketing Machine", "schedule the post", or asks what is waiting for…