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 gh-discussionsgit 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/gh-discussions)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/gh-discussions"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/gh-discussions/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/gh-discussions"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/gh-discussions.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 | $0.00136 | $0.07310 |
| Opus 5.5 | $0.00054 | $0.02924 |
| Sonnet 5.5 | $0.00027 | $0.01462 |
| Haiku 4.5 | $0.00014 | $0.00731 |
Grade A, and why
gh-discussions 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 12d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gh-discussions — Q&A-дверь, где ответ становится Answer
🧒 В конце отчёта Антону — блок «Простыми словами» ([[eli5-always]]).
Зачем отдельная дверь (приказ Антона 03.09: «сделай ОТДЕЛЬНУЮ ДВЕРЬ ПОД ДИСКУССИОНС»)
Discussions — не «issues, только сбоку». Разница механическая: у Q&A-категории есть кнопка Mark as answer, и помеченный ответ — единственная на GitHub форма публичного признания «этот человек решил мою проблему».
Общий комментинг эту дверь не покрывает физически, и это замерено, а не предположено.
Главное гнездо /rep-reply — anthropics/claude-code — имеет hasDiscussionsEnabled: false и ноль дискуссий при 144 001 звезде. Туда этим скиллом ходить некуда.
Набор репо у двух поверхностей почти не пересекается (замер 04.09.2026, 22 вендорских
репо): Discussions включены у 10 из 22, и среди выключенных — modelcontextprotocol/python-sdk,
pydantic/pydantic-ai, openai/openai-agents-python, crewAIInc/crewAI, ollama/ollama,
huggingface/transformers. Это и есть разрыв, который скилл закрывает.
⭐ Разрыв доказан отдельно, а не выведен из удобства (§5.4 — выгодный вывод требует
усиленной проверки). gh search не имеет подкоманды discussions вовсе (только
code/commits/issues/prs/repos), и рельса /rep-reply дискуссии физически не видит:
04.09 запрос gh search issues --repo google/adk-python "load_skill re-returns" вернул
пустой массив, тогда как тот же текст через search(type: DISCUSSION) находит
дискуссию #6997. Тот же gh search issues по слову load_skill при этом честно
отдаёт 5 ИССЮ — значит поиск исправен, а дискуссии для него просто не существуют.
Шаг 0. Гейты (30 секунд, до первой буквы)
- RECALL: писали ли мы в этот тред.
python3 ~/.claude/scripts/gh_discussions.py mine <owner/repo> <N>— проверяет ВСЕ три наши личности (tonydzi,Palo-Alto-AI-Research-Lab,secondbrainstarter). - Прерывание №1: живой человек ответил на наше прошлое исходящее → отвечаем ЕМУ сегодня.
- Автономия: GitHub-коммуникацию шлю САМ, без «+» и без гейта [коллега] (§4.7). Tier-2 остаётся: юр. подписание, деньги, удаление чужого, масс-действия.
- ⛔ Красная черта: одинаковый текст веером в несколько дискуссий. Спам ≠ громкость (§1.5).
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.
- 12d ago Changed · -1 lines 34b841c13641
- 16d ago Changed · +13 lines a4d478707834
- 25d ago First seen · 348 lines · 136 tokens per session scan A fad188def960
gh-discussions is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 7,310 once invoked, about $0.0005 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.…
tutorial
Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".