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 borrowed-audiencegit 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/borrowed-audience)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/borrowed-audience"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/borrowed-audience/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/borrowed-audience"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/borrowed-audience.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 | $0.00068 | $0.03457 |
| Opus 5.5 | $0.00027 | $0.01383 |
| Sonnet 5.5 | $0.00014 | $0.00691 |
| Haiku 4.5 | $0.00007 | $0.00346 |
Grade A, and why
borrowed-audience 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Добываем внешние ссылки, а не производим артефакты. Отчёт Антону по-русски, в конце блок «🧒 Простыми словами» ([[eli5-always]]).
Зачем этот скилл существует
Замер 27.07.2026: 9 уникальных заходов на флагман за неделю, 100% трафика из нашего же Facebook, внешних человеческих ссылок ноль, форков ноль. Артефакты есть — аудитории нет. Курируемые списки дают чужую аудиторию бесплатно.
Второй замер, 28.07.2026: из 22 наших PR наружу 21 висел открытым, включая 7 почти одинаковых PR по одному рецепту, разосланных веером по вендорам 24.07. Массовая одинаковая подача не работает и портит репутацию. Этот скилл существует, чтобы так больше не делать.
Железные границы (нарушение = провал, а не «оптимизация»)
- Один список — одна запись. Не пихать все 4 репо в один список.
- Один тул — тот, что подходит ЛУЧШЕ ВСЕГО. Не веером.
- Никаких одинаковых PR. Каждое тело PR отвечает на критерии ИМЕННО этого CONTRIBUTING.
- Замер ДО подачи, всегда ([[cold-pr-into-silent-queue]]). Холодный PR в глухую очередь = шум.
- Просят issue-first — значит issue-first. Запрещают PR — значит PR не открываем.
- Не пере-подавать в список, который уже отказал.
- Отправка PR — сама, по мандату [[github-publish-autonomous]] + §4.7 (GitHub-коммуникация без «+» Антона и без гейта [коллега]). Юридическое подписание (CLA/DCO) — Tier-2, аск Антону.
Движки (0 LLM, 0 токенов на замер — только gh + арифметика)
| Скрипт | Что делает |
|---|---|
~/.claude/scripts/list_discover.py |
НАХОДИТ кандидатов: веер поисков → дедуп → предфильтр (звёзды, свежесть push, не архив/форк) |
~/.claude/scripts/list_liveness.py |
МЕРИТ живость: мержи от ЛЮДЕЙ за 90д, число разных авторов, медиана часов до мержа, очередь, CONTRIBUTING → вердикт 🟢/🟡/🔴 |
~/.claude/scripts/issue_match.py |
Сосед: замер ОДНОГО репо под PR с кодом + поиск живого issue |
Токен — отдельная грабля, читать до старта
Fine-grained PAT не умеет форкать чужие репо (403 «Resource not accessible by personal access token»). Нужен classic PAT со скоупом public_repo:
export GH_TOKEN=$(grep '^GITHUB_PAT_PUBLIC_PR=' "$USERPROFILE/!CLAUDE-HP17 May26/secrets/github.env" | cut -d= -f2- | tr -d '\r')
Протух → добывать заново, порядок в памяти [[github-pat-cannot-fork]]. gh auth login --web в этой среде НЕ проходит (вкладки MCP всегда hidden, кнопка Authorize не разблокируется) — не тратить время.
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 Changed · -1 lines 9e577df094b3
- 14d ago Changed · +1 lines · -50 tokens per session 8db4632faf43
- 16d ago Changed · +13 lines ec2b16bee296
- 25d ago First seen · 137 lines · 118 tokens per session scan A 742ed5fac542
borrowed-audience is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 3,457 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-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 and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
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.…
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.