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 fb-likesgit 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/fb-likes)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/fb-likes"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/fb-likes/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/fb-likes"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/fb-likes.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 | $0.00082 | $0.02662 |
| Opus 5.5 | $0.00033 | $0.01065 |
| Sonnet 5.5 | $0.00016 | $0.00532 |
| Haiku 4.5 | $0.00008 | $0.00266 |
Grade A, and why
fb-likes 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fb-likes — лайки как ежедневная механика, а не разовое действие
⛔ ЛИЧНОСТЬ БРАУЗЕРА (канон 30.08.2026). Chrome профиля Default на хабе = личность Антона (claude.ai там под [рабочий аккаунт], всегда). Робот здесь ЧИТАЕТ и действует, но НЕ ТРОГАЕТ ЛОГИНЫ: ни logout, ни смены аккаунта, ни «самолечения входа», ни инжекта кук. Увидел «не тот аккаунт» → доложи и работай из робо-профиля (
_chrome_profile_a2, Firefox-профили). Канон:reglament-hab-brauzernye-lichnosti-bb-i-roboty.
Зачем. Голосовая Антона 04.08.2026: «все наши посты и комментарии должны получать лайки — это ничего не стоит, а людям приятно», плюс отдельная задача — каждый день заходить к 5–10 случайным лидам с реальным контактом и лайкать их. Ключевое слово — КАЖДЫЙ ДЕНЬ: важна не разовая пробежка, а то, что активность в аккаунте есть постоянно.
До этого было покрыто ровно одно: шаг 7 в /fb-post — селф-лайк своего поста. Комменты под нашими постами, наши собственные ответы и обход лидов не покрывал никто.
⛔ ШАГ 0 — где можно исполнять (проверяй ВСЕГДА, до браузера)
python -c "import os;print(os.environ.get('COMPUTERNAME'))"
- Хаб
[машина флота]→ работаем. - Любая другая машина → боевые лайки отсюда НЕ ставим (CLAUDE.md §7.2,
reglament-ip-sensitive-deystviya-tolko-s-haba: FB-действия идут с постоянного IP хаба). С не-хаба можно всё, кроме браузера: чинить ростер, смотреть счётчик, готовить список. Работу текстом на хаб через шину.
ЛЕЙН 1 — хвост публикации (запускается САМ после каждого нашего поста/ответа)
Это не отдельная команда для Антона, а штатный хвост /fb-post и /fb-reply. Отдельно спрашивать не нужно: лайк своего контента обратим, наружу ничего не пишет, не Tier-2.
Порядок под КАЖДЫМ нашим постом:
- Гейт темпа перед серией:
python "$USERPROFILE/.claude/scripts/fb_guard.py" check like_ownBLOCKED(exit 3) → СТОП, доложить, не обходить. - Свой пост — Like (если ещё не стоит после шага 7
/fb-post). - Все комментарии под постом — Like каждому. Минимум топовые, цель — все. Свои ответы в тредах тоже (Антон назвал это явно).
- Наши собственные комментарии (футер-коммент, ответы) — Like им же.
- После КАЖДОГО поставленного лайка:
python "$USERPROFILE/.claude/scripts/fb_guard.py" record like_own - Один раз на пост — запись в счётчик механики:
python "$USERPROFILE/.claude/scripts/fb_like_roster.py" record --person "<permalink поста>" \ --kind own --outcome ok --note "пост + N комментов"
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 61709690183a
- 14d ago Changed · -1 lines 0d8d89b0cb67
- 19d ago Changed · +13 lines 7a3ea28ab606
- 28d ago First seen · 137 lines · 82 tokens per session scan A 6554ff42dc08
fb-likes is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 2,662 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
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…
last30days-plus
The last30days research skill with your own subscriptions added as extra research lanes, driven inside Agent Chrome. Grok (Private Chat) for X/Twitter, Perplexity Deep research (Incognito) for the web and news, and Meta's Muse for Facebook groups and Instagram (experimental). Runs the upstream last30days skill…
muse-browser
EXPERIMENTAL. Research Facebook and Instagram (trends, Reels, creators, and conversations in Facebook groups you belong to) by asking Meta's own AI agent Muse (muse.ai) inside Agent Chrome, in a fresh side chat with a read-only instruction. Muse searches Facebook, Instagram and Threads posts your account can see and…
perplexity-browser
Research with your own Perplexity subscription inside Agent Chrome instead of the paid Perplexity API. Quick cited web answers (Search) or Perplexity Deep research reports with dozens of sources, always in Incognito and with a neutral preface so your personalization and memory don't shape the answer. Use when asked to…
facebook-personal-browser
Read your own signed-in personal Facebook inside Agent Chrome, strictly read-only. Open and read a specific post and its comments (fb-read), look inside a group you belong to, or check your own notifications or posts. Use when asked to "open this Facebook post", "read the comments on", "check my Facebook…
grok-browser
Research what people are saying on X (Twitter) through Grok on grok.com inside Agent Chrome, always in Grok Private Chat so nothing lands in your Grok history, memory or model training. Grok searches X live (with engagement filters like minfaves) and returns posts with handles, dates and status URLs; the driver checks…