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 obsidian-ingestgit 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/obsidian-ingest)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/obsidian-ingest"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/obsidian-ingest/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/obsidian-ingest"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/obsidian-ingest.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 | $0.00092 | $0.07115 |
| Opus 5.5 | $0.00037 | $0.02846 |
| Sonnet 5.5 | $0.00018 | $0.01423 |
| Haiku 4.5 | $0.00009 | $0.00711 |
Grade C, and why
obsidian-ingest scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Don't `rm -rf` inside `%VAULT_ROOT%\`** — Obsidian and the Windows indexer hold file handles ("Device or resource busy"). Delete with `find ... -delete`, or generate into a fresh directory. How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian Ingest
🧒 Always, in every reply and progress log to the operator: end with a child-simple "In plain words" recap in their language (plain words, no jargon) — their standing request. Scope: reports TO the operator only, never inside the vault notes you generate. See memory
eli5-always/ globalCLAUDE.md.
This skill captures how the operator wants raw text turned into a clean, linked knowledge base. He is a perfectionist and values thorough extraction over speed — the goal is not to dump files but to transform raw material into atomic, well-linked notes that compound in value over time.
Read references/vault-conventions.md for the exact folder layout, naming, tag canon, and frontmatter templates. Read references/pipeline.md for the big-batch script pipeline. Read references/source-adapters.md for per-source parse specs (Facebook, Telegram, ChatGPT, WhatsApp, etc.). Read references/second-brain-layer.md for the distillation & retrieval layer (concept-synthesis "what I think about X" notes, prediction ledger, semantic search) — build/refresh after a big import so the vault stays a thinking partner, not just an archive. This SKILL.md is the decision layer; the references are the mechanics.
Step zero: establish ownership
Before processing ANY material, establish provenance. For known source types (see table below) the provenance is already confirmed — skip the question and proceed. For unknown material (a file the operator just dropped, a pasted note, an unfamiliar export), always ask: "Whose material is this — your own thinking, a conversation with others, or external content?"
Known-provenance sources (no need to ask)
| Source | origin | authored_by | Extra tags |
|---|---|---|---|
Facebook posts export (posts.md) |
anton |
human |
facebook-diary, anton-original |
| Telegram voice archive (content team) | anton |
human (voice) / hybrid (summaries) |
anton-original |
| the operator's own voice notes (m4a → transcribed) | anton |
human |
anton-original |
| ChatGPT conversations (the operator's chats) | mixed |
hybrid |
— |
| Nexus distilled (02-Decisions/03-Insights/05-Resources) | anton |
claude-cowork |
— |
| External podcasts / YouTube transcripts | external |
ai |
— |
| Dialogue subfolders (dialogues_work_acct_b_*) | mixed |
hybrid |
— |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/pipeline.md 15 KB
- references/second-brain-layer.md 9.2 KB
- references/source-adapters.md 60 KB
- references/vault-conventions.md 11 KB
- scripts/backfill_provenance.py 1.6 KB runs code
- scripts/build_moc.py 4.8 KB runs code
- scripts/dedup.py 3.0 KB runs code
- scripts/generate.py 7.6 KB runs code
- scripts/parse_telegram.py 4.7 KB runs code
- scripts/precheck_corpus.py 5.1 KB runs code
- scripts/triage.py 2.6 KB runs code
- SKILL.md.snapshot-2026-06-07-origin-concepts 20 KB
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.
- 3d ago Changed · +27 lines 37f9a01068aa
- 16d ago Changed · -1 lines 042b92a2f5c2
- 20d ago Changed · +16 lines · +9 tokens per session 69be431d5ba4
- 29d ago Changed · -18 lines · -9 tokens per session af9b11cb64df
- 1mo ago First seen · 175 lines · 92 tokens per session scan C 1a0116e1aab2
obsidian-ingest is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 7,115 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.
Other skills, from other repositories
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, list, or version-gated kanban views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
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…
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
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-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-cli
Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.