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-engineer-outreachgit 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-engineer-outreach)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/local-engineer-outreach"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/local-engineer-outreach/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-engineer-outreach"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/local-engineer-outreach.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 | $0.00280 | $0.03468 |
| Opus 5.5 | $0.00112 | $0.01387 |
| Sonnet 5.5 | $0.00056 | $0.00694 |
| Haiku 4.5 | $0.00028 | $0.00347 |
Grade A, and why
local-engineer-outreach 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 22d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚖️ ШАГ 0 — СНАЧАЛА БИБЛИЯ (обязательно, origin: anton 2026-07-26)
Перед ЛЮБЫМ действием этого скилла подними выстраданные правила Библии по лидам:
python3 ~/.claude/scripts/bible_leads.py # карта (0 токенов)
python3 ~/.claude/scripts/bible_leads.py --grep <тема> # срез
Идёт РАНЬШЕ outreach_log.py check и раньше RECALL по человеку. Нет правила в Библии →
это находка, после работы занести через /intake, а не импровизировать молча.
Канон: reglament-lyubaya-rabota-s-lidami-snachala-bibliya · _Bible-Outreach-MOC · CLAUDE.md §9.5
local-engineer-outreach — ежедневный цикл воронки A
📖 Работает под Библией (
_Bible-Outreach-MOC) и/outbound-gate. Голос = Антон (авторский, Opus в рутине / Fable в живой сессии), без ELI5 в сообщениях лидам. Учёт:tracker.json(состояние контакта) +outreach_log.py(флот-журнал, капы).
Рутина (как это живёт само)
launchd ai.paloalto.engineer-outreach → ~/.claude/scripts/engineer_outreach.command → этот скилл.
Три тика в сутки: 10:30 · 14:30 · 18:30 Лиссабона (⚠️ намеренное исключение из §4.6 «рутины
ночью» — рутина пишет живым людям, значит работает в их день; три тика = страховка от спящего Мака,
лишние безвредны из-за lock + правила «≤1 касание контакту в день»). Обёртка сама: окно-гейт · lock ·
механический HARD-STOP engineer_outreach_state.py precheck (трекер битый/недоступен → LLM даже
не стартует, алярм в 03) · hang-guard 2400с · сентинел-гейт · запись прогона со счётчиками + дашборд.
Руками: bash ~/.claude/scripts/engineer_outreach.command (в окне = live) ·
EO_FORCE=1 bash … вне окна = принудительно dry (читает и планирует, не отправляет).
Артефакты: _outreach/ledger/engineer-outreach-runs.jsonl (evidence со счётчиками и полем
worked = ДОКАЗАННОЕ Δ журнала/трекера) · _Dashboards/Engineer-Funnel.html (кто на какой ступени).
Сторож = результат, не тик: engineer_outreach_state.py stalecheck краснеет, если контакты ждут
хода, а доказанного движения нет >72ч — один чек ловит смерть launchd, сдвиг DST, мёртвый TG-MCP и
пустой тик разом. Зовётся из automations_shard.py (другой агент, 21:25) — сторож не живёт в том,
что сторожит.
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.
- 22d ago Changed ccb97c82b2ad
- 1mo ago First seen · 142 lines · 280 tokens per session scan A 8fc1d6ddfaf6
local-engineer-outreach is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed yesterday), licensed MIT. It adds 280 tokens to every session and 3,468 once invoked, about $0.0011 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-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.…
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…
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…
ariadne:workstream-tracking
Create, audit, or improve Obsidian Kanban work boards and Dataview dashboards for durable project, roadmap, evaluation, implementation, QA, or recurring workstream tracking inside an agent-maintained vault.