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 local-qagit 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/local-qa)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/local-qa"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/local-qa/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/local-qa"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/local-qa.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 | $0.00583 | $0.03770 |
| Opus 5.5 | $0.00233 | $0.01508 |
| Sonnet 5.5 | $0.00117 | $0.00754 |
| Haiku 4.5 | $0.00058 | $0.00377 |
Grade A, and why
local-qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa — тест и паспорт на каждую деталь
🧒 При докладе Антону: заверши блоком «Простыми словами» ([[eli5-always]]). Только ему — не внутри паспортов.
Когда зову: родилась НОВАЯ деталь · починил старую · чиню ВТОРОЙ раз ту же (перепочинка) · подкрутил поведение. Любой из четырёх случаев = деталь меняется, значит её спутники устарели.
Граница с соседями (не дублируем, каждый уровень ссылается вниз — АК-47):
| вопрос | когда | живёт сколько | |
|---|---|---|---|
/tt |
работает ли то, что мы только что собрали? | сразу после сборки, горячий контекст | один прогон |
/qa |
заметим ли, когда сломается, и починит ли это Антон без меня? | перед тем как отпустить деталь в жизнь | навсегда: тест в сетке + паспорт |
/retro |
что мы вообще насобирали за сессию | конец сессии | аудит строки «покрыто? ✅/❌» |
Шаг 0 — RECALL и границы детали
- Что именно правили: файл, зона (
~/.claude/scripts·$IMPORTS_ROOT·$MACHINE_BUS_DIR/_engine· скилл · хук). - Деталь уже известна системе?
grep -n "<имя>" 00-System/Coverage-Map.mdиls 00-System/Parts/*/<имя>.md. - Есть ли уже тест/паспорт — их обновляем, а не пишем второй ([[«один источник, ноль копий»|coverage-and-docs-every-part]]).
- Деталь МЁРТВАЯ (никто не ссылается, не трогали 30 дней) и мы её не оживляем → не покрываем, а предлагаем снести (
00-System/Dead-Code-Candidates.md). Док, который врёт, дороже отсутствующего. - ⚠️ НОВАЯ деталь покрывается ВСЕГДА, безусловно — «подождём, приживётся ли» запрещено (anton 28.07).
Шаг 1 — /tt прогнан?
Нет → сперва /tt (живой прогон + внешний ломатель Codex/Grok/Gemini). /qa не заменяет горячую проверку и не повторяет её.
Шаг 2 — Чинили? Сперва тест, который КРАСНЕЕТ
Порядок при починке и особенно при перепочинке:
- Написать проверку, воспроизводящую баг на текущем сломанном коде → она обязана упасть. Не упала — ты не понял баг, лечишь не то.
- Только потом чинить корень ([[fix-root-cause-not-symptoms]]).
- Прогнать снова → зелёный. Проверка остаётся в сетке навсегда как регрессия.
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.
- 25d ago First seen · 144 lines · 583 tokens per session scan A b8470efe325f
local-qa is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 583 tokens to every session and 3,770 once invoked, about $0.0023 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
lint
A health check for the LLM Wiki, a knowledge base about large language models. It looks for missing pages, broken links, conflicting or outdated content, missing fields, incomplete topic maps, weak bias checks, and an old core-context snapshot.
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-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…
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.…