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 takeout-pullgit 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/takeout-pull)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/takeout-pull"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/takeout-pull/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/takeout-pull"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/takeout-pull.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 | $0.00069 | $0.01523 |
| Opus 5.5 | $0.00028 | $0.00609 |
| Sonnet 5.5 | $0.00014 | $0.00305 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
takeout-pull scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anton's Takeout retrieval actor. Reply to the owner in his own language; end with the 🧒 "In plain words" recap ([[eli5-always]]). Full project notes: memory [[youtube-history-import]].
Why this exists (the root it fixes)
2026-06: a scoped "YouTube → history only" export completed but its 7-day link EXPIRED un-downloaded — the only follow-up was a passive calendar reminder, which does nothing if no session is open when it fires. A reminder is not an actor. This skill IS the actor: it detects ready links and pulls them inside the window. Root-cause class = "handoff with no auto-executor" (Connect-rule).
Step 1 — Detect (the actor, ~0 tokens, autonomous)
Run the deterministic scan over the personal mailbox (Takeout links land in a@, never a2 — a2 only gets recovery-copy security alerts):
cd "$IMPORTS_ROOT/youtube"
python takeout_pull.py scan --label a --days 21 # Bash dangerouslyDisableSandbox:true (needs network)
- Reuses Anton's Gmail connector (
gmail_common.get_service) — single source of truth, no browser. - Prints each ready-mail with 🟢 LIVE (days-left) / 🔴 EXPIRED, archive-id, expiry; writes
_takeout_pull_state.json. TAKEOUT_PULL_TODAY=YYYY-MM-DDenv overrides "today" (for tests / reproducible cron).- 🟢 LIVE present → exit 0 + ">>> ACTION: DOWNLOAD NOW". 🔴 all expired → re-create the export (Step 3).
Step 2 — Download a LIVE archive (pre-authorized; drive Chrome)
Takeout download needs an interactive a@ Google session (cookies) → can't be headless; drive the already-logged-in Chrome (claude-in-chrome MCP):
navigatetohttps://takeout.google.com/manage/archive/<archive_id>(id from Step 1).- Click "Download" (use
findref-click, more reliable than coordinates). - Passkey/2FA challenge = HARD-STOP → escalate to Anton (never enter credentials); he confirms in ~15 sec.
- Multi-part (>4 GB) → download every part. Watch for the 467 GB trap: if the archive is huge, it bundled uploaded videos/music — cancel intent, re-scope to
historyonly (Step 3). NEVER click Takeout "Cancel scheduled exports" (kills queued ones). - Zip lands in
$USERPROFILE/Downloads\.
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.
- 17d ago Changed · -2 lines 9baf303fa36a
- 21d ago Changed · -1 lines 702e25efb491
- 1mo ago First seen · 88 lines · 69 tokens per session scan A 1aa8035942ee
takeout-pull is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,523 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
ingest
A tool for adding a URL, file, text, or Inbox item to the LLM Wiki. It checks the material's purpose, preserves the original source, compiles a wiki page, updates indexes and logs, and reviews the result.
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.…
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 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-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…