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 raise-sourcinggit 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/raise-sourcing)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/raise-sourcing"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/raise-sourcing/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/raise-sourcing"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/raise-sourcing.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 | $0.00140 | $0.02142 |
| Opus 5.5 | $0.00056 | $0.00857 |
| Sonnet 5.5 | $0.00028 | $0.00428 |
| Haiku 4.5 | $0.00014 | $0.00214 |
Grade A, and why
raise-sourcing 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 6d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/raise-sourcing — два трека под рейз
🧒 Антону в конце — блок «Простыми словами».
Скилл отвечает на один вопрос: кому завтра стучать. Кого — в двух списках, чем стучать — в плейбуке reglament-pervoe-kasanie-po-kanalam-raise-sourcing (волт, 02-Protocols).
Шаг 0 — RECALL, прежде чем искать
Прочитай, что уже решено, иначе соберёшь третий одинаковый список:
- мемо рейза
02-Decisions/decision-DR26-08-25-HUB-03-control-plane-raise-memo.md(там же решение Антона 03.09 по покупателю); - карту рынка
03-Insights/insight-DR-DR26-08-26-HUB-02-0727-agent-security-landscape.md(инвестор-маршрут: ⛔ IL-[человек] первыми, ✅ Ballistic / Work-Bench / Boldstart / SYN / YC / a16z-seed); - текущий стол:
python ~/.claude/scripts/raise_sourcing_sheet.py --url, вкладкиinvestors/buyers/gaps.
Кто уже в столе со статусом — тот НЕ пересобирается: касание ведёт человек или робот касаний, а не сорсинг.
Шаг 1 — инвесторы: запрос в свою базу, 0 токенов
[путь владельца]: vc_org (98 746) → vc_org_person (26 533) → vc_person (123 645, поля email/twitter/linkedin/telegram). Фонды по имени с учётом дублей написания, роли фильтруем на инвестиционные.
Обязательный второй проход — ТЁПЛЫЙ ПУТЬ: тот же человек ищется в leads, contacts, people. Нашёлся — в колонку warm идёт конкретика («есть в leads как <slug>, последний контакт <дата>»), а не слово «тёплый».
Шаг 2 — покупатели: по симптому, а не по должности
Ищем человека, который САМ описал нашу боль. Порядок источников по теплоте:
- Наши репозитории — звёзды, форки, issues, комменты (
gh api repos/<owner>/<repo>/stargazers). Самые тёплые: они уже нас трогали. - GitHub-экосистема —
gh search issuesпо симптомам: agent sprawl, runaway agent, kill switch, agent permissions, multi-agent audit, rollback agent changes, fleet of agents, MCP policy. - Hacker News — бесплатный Algolia API:
https://hn.algolia.com/api/v1/search?query=<фраза>&tags=comment. Профиль автора часто несёт почту или сайт. - X — публичный ответ в тред симптома, потом личка. Рельса читается через браузер, не через API.
- Своя аудитория и клуб СОСТАВ —
sostav_profile(531) иsostav_messages(188 534) в той же базе: кто пишет про свои пайплайны и автоматизацию.
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.
- 6d ago Changed a4edc37e972f
- 19d ago Changed · -1 lines 3b6c0649d840
- 23d ago Changed · +13 lines 393773a6e965
- 1mo ago First seen · 80 lines · 140 tokens per session scan A 18e34843236c
raise-sourcing is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 2,142 once invoked, about $0.0006 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…
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…
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.…
wiki-query
Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…
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-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…