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 github-growthgit 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/github-growth)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/github-growth"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/github-growth/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/github-growth"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/github-growth.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 | $0.00113 | $0.06736 |
| Opus 5.5 | $0.00045 | $0.02694 |
| Sonnet 5.5 | $0.00023 | $0.01347 |
| Haiku 4.5 | $0.00011 | $0.00674 |
Grade A, and why
github-growth scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 10 | **Security / race reports** | LEASH-8, agent-leash, lease/clobber/общий буфер обмена | Макс | ⭐ Ярус A, но **высокий риск репутации**: только детерминированный reproducer + конкретный impact + приватный канал. «Во How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GITHUB-GROWTH — как мы продвигаемся на GitHub
ЗАЧЕМ: Миссия №2 — чтобы нас заметили и позвали. GitHub — главная витрина: нанимающий смотрит туда, а не в резюме. Считаем ВХОДЯЩИЙ КОНТАКТ, не активность.
Шаг 0. Гейты (30 секунд, до первой буквы)
- RECALL по репо/человеку: были ли мы там, кому уже писали (
gh search prs --author tonydzi, память,outreach_log.py check). - Прерывание №1: живой человек ответил на наше прошлое исходящее → отвечаем ЕМУ сегодня, всё остальное ждёт (
pr_watch). - Автономия: GitHub-коммуникацию и код шлю САМ, без «+» и без гейта [коллега]. Tier-2 остаётся: CLA/DCO и любое юр. подписание, деньги, удаление чужого, масс-действия.
- ⛔ Красная черта: покупка звёзд/форков, фиктивные коммиты, любое действие ради сдвига цифры вместо создания события.
Шаг 1. Выбрать поверхность ПО ЧИТАТЕЛЮ, не по звёздам
gh api "repos/OWNER/REPO/issues/comments?per_page=30&sort=created&direction=desc" \
--jq '.[] | "\(.created_at[:10]) @\(.user.login): \(.body[:70]|gsub("\n";" "))"'
Живая = за последние недели пишут РАЗНЫЕ люди по делу, среди них мейнтейнер. Мёртвая = спам/тишина.
Замер 29.07: karpathy/llm-council 23 338★ — трекер свалка, идти некуда. karpathy/nanochat 56 757★, мержей нет с 14.04, но трекер живой → идём (и пошли: коммент в #800, PR #814).
Шаг 1-бис. ⭐ АУДИТ ЖИВОСТИ ЦЕЛИ — обязателен ДО первого вклада (DR-1537, 31.07)
Беглый взгляд на комменты — не аудит. Снять выборку: последние 30 внешних PR + 30 внешних issue, посчитать:
- p50 и p90 времени до первого человеческого ответа (ботов исключить — так требует CHAOSS);
- долю внешних PR, получивших человека за 7 дней;
- merged / closed-unmerged;
- число решений в месяц (не размер бэклога) и число уникальных живых ревьюеров;
- сколько новичков получили мерж за 90 дней; есть ли issue-first процесс.
⛔ Kill-критерий: меньше 30% последних внешних вкладов получили человека за 14 дней → цель отложить, не заходить.
Именованный ранжир под нашу нишу (DR-1537, ChatGPT): modelcontextprotocol/python-sdk 5/5 · pydantic/pydantic-ai 5/5 (формализованный путь issue → champion → PLAN.md → assignment → PR) · openai/openai-agents-python 5/5 · huggingface/smolagents 4/5 · huggingface/transformers 3/5 · llama.cpp 3/5 · vllm 2.5/5 · ⛔ tldraw, godot — не цель, внешние PR закрыты/ограничены.
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 be7c8c96ee4a
- 14d ago Changed 619b64a9aae2
- 16d ago Changed · +13 lines 63a6dd58f0d2
- 25d ago First seen · 178 lines · 113 tokens per session scan A f33c8167627a
github-growth is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 6,736 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
Other skills, from other repositories
gh-issue-triage
An automated workflow for handling issues in a project's GitHub repository, from collecting and analysing them through fixing, testing, and closing them.
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.
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.
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…
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…